Token | Advertisement |
Token ID | 4723 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
eele | +0.649 |
ogical | +0.645 |
�� | +0.637 |
nature | +0.637 |
Dul | +0.616 |
Neg logit contributions | |
ILLE | -0.720 |
ctions | -0.685 |
ESSION | -0.678 |
lp | -0.652 |
ned | -0.640 |
Token | Continue |
Token ID | 10054 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
ILLE | +1.377 |
ctions | +1.300 |
ESSION | +1.293 |
lp | +1.230 |
ned | +1.202 |
Neg logit contributions | |
eele | -1.583 |
�� | -1.572 |
ogical | -1.538 |
nature | -1.513 |
aiman | -1.470 |
Token | reading |
Token ID | 3555 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
ILLE | +2.557 |
ctions | +2.444 |
ESSION | +2.428 |
lp | +2.352 |
ned | +2.334 |
Neg logit contributions | |
�� | -1.754 |
eele | -1.728 |
ogical | -1.669 |
nature | -1.629 |
aiman | -1.588 |
Token | the |
Token ID | 262 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ILLE | +0.156 |
ctions | +0.148 |
ESSION | +0.148 |
lp | +0.143 |
ned | +0.140 |
Neg logit contributions | |
eele | -0.102 |
�� | -0.102 |
ogical | -0.101 |
nature | -0.099 |
Dul | -0.095 |
Token | main |
Token ID | 1388 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ILLE | +1.131 |
ctions | +1.064 |
ESSION | +1.046 |
lp | +1.009 |
ned | +0.999 |
Neg logit contributions | |
�� | -1.426 |
eele | -1.418 |
ogical | -1.388 |
nature | -1.362 |
Dul | -1.331 |
Token | story |
Token ID | 1621 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ILLE | +4.037 |
ctions | +3.890 |
ned | +3.784 |
ESSION | +3.756 |
lp | +3.715 |
Neg logit contributions | |
�� | -3.966 |
eele | -3.832 |
ogical | -3.645 |
nature | -3.574 |
aiman | -3.537 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ILLE | +6.288 |
ctions | +5.992 |
ned | +5.815 |
ESSION | +5.619 |
lp | +5.516 |
Neg logit contributions | |
�� | -10.696 |
eele | -9.930 |
ogical | -9.583 |
elaide | -9.484 |
aiman | -9.457 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ILLE | +2.715 |
ctions | +2.590 |
ESSION | +2.534 |
lp | +2.476 |
ned | +2.465 |
Neg logit contributions | |
�� | -3.448 |
eele | -3.293 |
ogical | -3.210 |
nature | -3.111 |
aiman | -3.089 |
Token | Thus |
Token ID | 19093 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
ILLE | +2.986 |
ESSION | +2.768 |
ctions | +2.747 |
lp | +2.642 |
CLE | +2.604 |
Neg logit contributions | |
�� | -3.917 |
eele | -3.788 |
ogical | -3.684 |
nature | -3.578 |
aiman | -3.563 |
Token | Massachusetts |
Token ID | 10140 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
ILLE | +0.982 |
ctions | +0.931 |
ESSION | +0.927 |
lp | +0.889 |
ned | +0.883 |
Neg logit contributions | |
�� | -0.885 |
eele | -0.867 |
ogical | -0.851 |
nature | -0.837 |
aiman | -0.809 |
Token | is |
Token ID | 318 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ILLE | +1.082 |
ctions | +1.035 |
ESSION | +1.019 |
lp | +0.981 |
ned | +0.971 |
Neg logit contributions | |
�� | -0.979 |
eele | -0.971 |
ogical | -0.946 |
nature | -0.930 |
Dul | -0.898 |
Token | Up |
Token ID | 3205 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ILLE | +1.380 |
ctions | +1.304 |
ESSION | +1.299 |
lp | +1.249 |
ned | +1.223 |
Neg logit contributions | |
eele | -1.229 |
�� | -1.218 |
ogical | -1.214 |
nature | -1.192 |
Dul | -1.162 |
Token | Continue |
Token ID | 10054 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
ILLE | +0.474 |
ctions | +0.447 |
ESSION | +0.445 |
lp | +0.429 |
atown | +0.419 |
Neg logit contributions | |
eele | -0.442 |
�� | -0.440 |
ogical | -0.437 |
nature | -0.430 |
Dul | -0.425 |
Token | reading |
Token ID | 3555 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ILLE | +2.785 |
ctions | +2.675 |
ESSION | +2.629 |
ned | +2.556 |
lp | +2.553 |
Neg logit contributions | |
�� | -2.031 |
eele | -1.976 |
ogical | -1.925 |
nature | -1.862 |
aiman | -1.846 |
Token | the |
Token ID | 262 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
eele | +0.612 |
ogical | +0.606 |
�� | +0.606 |
nature | +0.596 |
Sor | +0.575 |
Neg logit contributions | |
ILLE | -0.995 |
ctions | -0.947 |
ESSION | -0.945 |
lp | -0.914 |
ned | -0.896 |
Token | main |
Token ID | 1388 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ILLE | +1.602 |
ctions | +1.511 |
ESSION | +1.471 |
lp | +1.427 |
ned | +1.424 |
Neg logit contributions | |
�� | -2.132 |
eele | -2.125 |
ogical | -2.064 |
nature | -2.037 |
aiman | -1.990 |
Token | story |
Token ID | 1621 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
ILLE | +4.747 |
ctions | +4.611 |
ned | +4.448 |
ESSION | +4.413 |
lp | +4.350 |
Neg logit contributions | |
�� | -4.932 |
eele | -4.806 |
ogical | -4.489 |
nature | -4.454 |
aiman | -4.438 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
ILLE | +5.715 |
ctions | +5.345 |
ned | +4.971 |
ESSION | +4.945 |
CLE | +4.872 |
Neg logit contributions | |
�� | -10.795 |
eele | -10.714 |
aiman | -10.293 |
ogical | -10.213 |
nature | -9.985 |
Token | verify |
Token ID | 11767 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ILLE | +1.874 |
ctions | +1.783 |
ESSION | +1.752 |
lp | +1.672 |
ned | +1.670 |
Neg logit contributions | |
�� | -2.374 |
eele | -2.345 |
ogical | -2.302 |
nature | -2.259 |
aiman | -2.228 |
Token | you |
Token ID | 345 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ILLE | +3.028 |
ctions | +2.877 |
ESSION | +2.836 |
lp | +2.728 |
ned | +2.686 |
Neg logit contributions | |
�� | -4.289 |
eele | -4.214 |
ogical | -4.133 |
nature | -4.061 |
Dul | -3.981 |
Token | 're |
Token ID | 821 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
eele | +0.364 |
�� | +0.360 |
ogical | +0.360 |
nature | +0.354 |
Dul | +0.346 |
Neg logit contributions | |
ILLE | -0.316 |
ctions | -0.294 |
ESSION | -0.293 |
lp | -0.280 |
ned | -0.274 |
Token | not |
Token ID | 407 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
ILLE | +0.201 |
ctions | +0.191 |
ESSION | +0.191 |
lp | +0.184 |
ned | +0.180 |
Neg logit contributions | |
eele | -0.128 |
�� | -0.127 |
ogical | -0.126 |
nature | -0.123 |
Dul | -0.119 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
eele | +0.006 |
�� | +0.006 |
ogical | +0.006 |
nature | +0.006 |
Dul | +0.006 |
Neg logit contributions | |
ILLE | -0.006 |
ctions | -0.006 |
ESSION | -0.006 |
lp | -0.006 |
ned | -0.005 |
Token | Continue |
Token ID | 10054 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
ILLE | +1.426 |
ctions | +1.352 |
ESSION | +1.340 |
lp | +1.275 |
ned | +1.246 |
Neg logit contributions | |
eele | -1.650 |
�� | -1.640 |
ogical | -1.605 |
nature | -1.579 |
aiman | -1.532 |
Token | reading |
Token ID | 3555 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ILLE | +2.921 |
ctions | +2.797 |
ESSION | +2.772 |
lp | +2.687 |
ned | +2.671 |
Neg logit contributions | |
�� | -2.052 |
eele | -2.019 |
ogical | -1.946 |
nature | -1.895 |
aiman | -1.857 |
Token | the |
Token ID | 262 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ILLE | +1.271 |
ctions | +1.211 |
ESSION | +1.206 |
lp | +1.164 |
ned | +1.150 |
Neg logit contributions | |
�� | -0.892 |
eele | -0.889 |
ogical | -0.870 |
nature | -0.849 |
Dul | -0.823 |
Token | main |
Token ID | 1388 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ILLE | +1.487 |
ctions | +1.403 |
ESSION | +1.372 |
lp | +1.326 |
ned | +1.318 |
Neg logit contributions | |
�� | -1.934 |
eele | -1.922 |
ogical | -1.877 |
nature | -1.839 |
aiman | -1.799 |
Token | story |
Token ID | 1621 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
ILLE | +4.581 |
ctions | +4.423 |
ned | +4.324 |
ESSION | +4.251 |
lp | +4.202 |
Neg logit contributions | |
�� | -4.702 |
eele | -4.524 |
ogical | -4.282 |
nature | -4.205 |
aiman | -4.180 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ILLE | +6.200 |
ctions | +5.934 |
ned | +5.755 |
ESSION | +5.567 |
lp | +5.459 |
Neg logit contributions | |
�� | -10.644 |
eele | -9.907 |
ogical | -9.589 |
elaide | -9.507 |
aiman | -9.428 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ILLE | +3.107 |
ctions | +2.968 |
ESSION | +2.890 |
ned | +2.836 |
lp | +2.835 |
Neg logit contributions | |
�� | -4.137 |
eele | -3.914 |
ogical | -3.812 |
nature | -3.684 |
aiman | -3.677 |
Token | When |
Token ID | 2215 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
ILLE | +3.468 |
ESSION | +3.185 |
ctions | +3.171 |
lp | +3.032 |
CLE | +3.019 |
Neg logit contributions | |
�� | -4.382 |
eele | -4.203 |
ogical | -4.124 |
aiman | -3.990 |
agine | -3.963 |
Token | it |
Token ID | 340 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
ILLE | +2.880 |
ctions | +2.739 |
ESSION | +2.704 |
ned | +2.586 |
lp | +2.577 |
Neg logit contributions | |
�� | -2.480 |
eele | -2.425 |
ogical | -2.368 |
nature | -2.322 |
aiman | -2.274 |
Token | is |
Token ID | 318 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
eele | +0.963 |
�� | +0.956 |
ogical | +0.953 |
nature | +0.934 |
Dul | +0.912 |
Neg logit contributions | |
ILLE | -1.257 |
ESSION | -1.191 |
ctions | -1.186 |
lp | -1.144 |
ned | -1.116 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
ILLE | +0.024 |
ctions | +0.023 |
ESSION | +0.023 |
lp | +0.022 |
ned | +0.021 |
Neg logit contributions | |
eele | -0.025 |
�� | -0.025 |
ogical | -0.024 |
nature | -0.024 |
Dul | -0.023 |
Token | Continue |
Token ID | 10054 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
ILLE | +1.610 |
ctions | +1.517 |
ESSION | +1.511 |
lp | +1.427 |
CLE | +1.399 |
Neg logit contributions | |
eele | -1.931 |
�� | -1.903 |
ogical | -1.872 |
nature | -1.843 |
aiman | -1.792 |
Token | reading |
Token ID | 3555 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ILLE | +3.105 |
ctions | +2.966 |
ESSION | +2.942 |
lp | +2.855 |
ned | +2.842 |
Neg logit contributions | |
�� | -2.176 |
eele | -2.141 |
ogical | -2.065 |
nature | -2.013 |
aiman | -1.968 |
Token | the |
Token ID | 262 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
ILLE | +1.248 |
ctions | +1.190 |
ESSION | +1.184 |
lp | +1.142 |
ned | +1.130 |
Neg logit contributions | |
�� | -0.886 |
eele | -0.881 |
ogical | -0.862 |
nature | -0.840 |
Dul | -0.816 |
Token | main |
Token ID | 1388 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ILLE | +1.550 |
ctions | +1.460 |
ESSION | +1.428 |
lp | +1.381 |
ned | +1.372 |
Neg logit contributions | |
�� | -2.020 |
eele | -2.005 |
ogical | -1.959 |
nature | -1.923 |
aiman | -1.876 |
Token | story |
Token ID | 1621 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ILLE | +4.536 |
ctions | +4.356 |
ned | +4.266 |
ESSION | +4.213 |
lp | +4.159 |
Neg logit contributions | |
�� | -4.532 |
eele | -4.379 |
ogical | -4.163 |
nature | -4.084 |
aiman | -4.034 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ILLE | +6.280 |
ctions | +5.954 |
ned | +5.768 |
ESSION | +5.616 |
lp | +5.492 |
Neg logit contributions | |
�� | -10.299 |
eele | -9.621 |
ogical | -9.336 |
elaide | -9.183 |
aiman | -9.152 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ILLE | +3.169 |
ctions | +3.018 |
ESSION | +2.941 |
ned | +2.882 |
lp | +2.881 |
Neg logit contributions | |
�� | -4.182 |
eele | -3.966 |
ogical | -3.862 |
nature | -3.740 |
aiman | -3.728 |
Token | Some |
Token ID | 4366 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ILLE | +3.561 |
ESSION | +3.286 |
ctions | +3.247 |
lp | +3.126 |
CLE | +3.107 |
Neg logit contributions | |
�� | -4.479 |
eele | -4.323 |
ogical | -4.216 |
nature | -4.059 |
aiman | -4.055 |
Token | teenagers |
Token ID | 17366 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
ILLE | +4.481 |
ctions | +4.266 |
ESSION | +4.184 |
ned | +4.047 |
lp | +4.030 |
Neg logit contributions | |
�� | -3.794 |
eele | -3.658 |
ogical | -3.616 |
nature | -3.533 |
Dul | -3.404 |
Token | threw |
Token ID | 9617 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
ILLE | +1.128 |
ctions | +1.070 |
ESSION | +1.064 |
lp | +1.026 |
ned | +1.012 |
Neg logit contributions | |
�� | -0.919 |
eele | -0.917 |
ogical | -0.901 |
nature | -0.883 |
Dul | -0.858 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
eele | +0.080 |
�� | +0.079 |
ogical | +0.079 |
nature | +0.078 |
Dul | +0.076 |
Neg logit contributions | |
ILLE | -0.077 |
ctions | -0.072 |
ESSION | -0.072 |
lp | -0.069 |
ned | -0.067 |
Token | Continue |
Token ID | 10054 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ILLE | +1.469 |
ctions | +1.387 |
ESSION | +1.372 |
lp | +1.310 |
ned | +1.275 |
Neg logit contributions | |
eele | -1.725 |
�� | -1.711 |
ogical | -1.669 |
nature | -1.648 |
aiman | -1.601 |
Token | reading |
Token ID | 3555 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ILLE | +2.456 |
ctions | +2.352 |
ESSION | +2.329 |
lp | +2.261 |
ned | +2.249 |
Neg logit contributions | |
�� | -1.739 |
eele | -1.706 |
ogical | -1.639 |
nature | -1.603 |
aiman | -1.568 |
Token | the |
Token ID | 262 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
ILLE | +0.604 |
ctions | +0.576 |
ESSION | +0.573 |
lp | +0.553 |
ned | +0.546 |
Neg logit contributions | |
�� | -0.418 |
eele | -0.417 |
ogical | -0.408 |
nature | -0.399 |
Dul | -0.387 |
Token | main |
Token ID | 1388 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ILLE | +1.247 |
ctions | +1.177 |
ESSION | +1.146 |
lp | +1.115 |
ned | +1.107 |
Neg logit contributions | |
�� | -1.658 |
eele | -1.642 |
ogical | -1.598 |
nature | -1.569 |
aiman | -1.537 |
Token | story |
Token ID | 1621 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
ILLE | +4.086 |
ctions | +3.962 |
ned | +3.866 |
ESSION | +3.803 |
lp | +3.781 |
Neg logit contributions | |
�� | -4.141 |
eele | -4.012 |
ogical | -3.780 |
nature | -3.729 |
aiman | -3.696 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ILLE | +6.106 |
ctions | +5.850 |
ned | +5.659 |
ESSION | +5.451 |
lp | +5.384 |
Neg logit contributions | |
�� | -10.515 |
eele | -9.732 |
ogical | -9.414 |
elaide | -9.280 |
aiman | -9.271 |
Token |
|
Token ID | 198 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ILLE | +2.795 |
ctions | +2.669 |
ESSION | +2.605 |
lp | +2.549 |
ned | +2.541 |
Neg logit contributions | |
�� | -3.580 |
eele | -3.415 |
ogical | -3.327 |
nature | -3.229 |
aiman | -3.204 |
Token | In |
Token ID | 818 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ILLE | +3.062 |
ctions | +2.828 |
ESSION | +2.827 |
lp | +2.682 |
ned | +2.669 |
Neg logit contributions | |
�� | -3.958 |
eele | -3.825 |
ogical | -3.712 |
nature | -3.610 |
agine | -3.597 |
Token | the |
Token ID | 262 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ILLE | +0.423 |
ctions | +0.404 |
ESSION | +0.400 |
lp | +0.386 |
ned | +0.383 |
Neg logit contributions | |
�� | -0.325 |
eele | -0.323 |
ogical | -0.317 |
nature | -0.311 |
Dul | -0.298 |
Token | capital |
Token ID | 3139 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ILLE | +0.585 |
ctions | +0.555 |
ESSION | +0.551 |
lp | +0.531 |
ned | +0.524 |
Neg logit contributions | |
�� | -0.482 |
eele | -0.481 |
ogical | -0.472 |
nature | -0.463 |
Dul | -0.446 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
eele | +0.754 |
ogical | +0.746 |
�� | +0.744 |
nature | +0.737 |
Dul | +0.712 |
Neg logit contributions | |
ILLE | -0.750 |
ctions | -0.714 |
ESSION | -0.706 |
lp | -0.676 |
ned | -0.663 |
Token | Continue |
Token ID | 10054 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ILLE | +1.610 |
ctions | +1.522 |
ESSION | +1.506 |
lp | +1.446 |
ned | +1.414 |
Neg logit contributions | |
eele | -1.832 |
�� | -1.831 |
ogical | -1.788 |
nature | -1.758 |
aiman | -1.704 |
Token | reading |
Token ID | 3555 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ILLE | +2.461 |
ctions | +2.356 |
ESSION | +2.333 |
lp | +2.269 |
ned | +2.253 |
Neg logit contributions | |
�� | -1.726 |
eele | -1.693 |
ogical | -1.636 |
nature | -1.600 |
aiman | -1.561 |
Token | the |
Token ID | 262 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
ILLE | +0.461 |
ctions | +0.439 |
ESSION | +0.437 |
lp | +0.422 |
ned | +0.416 |
Neg logit contributions | |
�� | -0.313 |
eele | -0.313 |
ogical | -0.307 |
nature | -0.300 |
Dul | -0.291 |
Token | main |
Token ID | 1388 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ILLE | +1.292 |
ctions | +1.222 |
ESSION | +1.197 |
lp | +1.157 |
ned | +1.149 |
Neg logit contributions | |
�� | -1.659 |
eele | -1.648 |
ogical | -1.607 |
nature | -1.579 |
Dul | -1.542 |
Token | story |
Token ID | 1621 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
ILLE | +4.317 |
ctions | +4.162 |
ned | +4.089 |
ESSION | +3.975 |
lp | +3.975 |
Neg logit contributions | |
�� | -4.602 |
eele | -4.418 |
ogical | -4.142 |
nature | -4.118 |
aiman | -4.078 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ILLE | +6.082 |
ctions | +5.789 |
ned | +5.618 |
ESSION | +5.428 |
lp | +5.393 |
Neg logit contributions | |
�� | -10.155 |
eele | -9.461 |
ogical | -9.169 |
elaide | -9.060 |
aiman | -9.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ILLE | +2.957 |
ctions | +2.825 |
ESSION | +2.755 |
lp | +2.701 |
ned | +2.694 |
Neg logit contributions | |
�� | -3.866 |
eele | -3.674 |
ogical | -3.577 |
nature | -3.469 |
aiman | -3.450 |
Token | � |
Token ID | 447 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
ILLE | +3.237 |
ESSION | +2.994 |
ctions | +2.958 |
lp | +2.884 |
ned | +2.839 |
Neg logit contributions | |
�� | -3.820 |
eele | -3.688 |
ogical | -3.603 |
Dul | -3.483 |
nature | -3.480 |
Token | � |
Token ID | 250 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
ILLE | +1.753 |
ctions | +1.620 |
ESSION | +1.592 |
lp | +1.533 |
ned | +1.469 |
Neg logit contributions | |
eele | -2.726 |
ogical | -2.701 |
�� | -2.676 |
nature | -2.650 |
Dul | -2.598 |
Token | If |
Token ID | 1532 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
ILLE | +1.679 |
ctions | +1.566 |
ESSION | +1.566 |
lp | +1.497 |
ned | +1.470 |
Neg logit contributions | |
�� | -1.973 |
eele | -1.959 |
ogical | -1.925 |
nature | -1.887 |
Dul | -1.847 |
Token | Up |
Token ID | 3205 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ILLE | +1.381 |
ctions | +1.304 |
ESSION | +1.300 |
lp | +1.250 |
ned | +1.224 |
Neg logit contributions | |
eele | -1.225 |
�� | -1.210 |
ogical | -1.210 |
nature | -1.189 |
Dul | -1.159 |
Token | Continue |
Token ID | 10054 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
ILLE | +0.370 |
ctions | +0.349 |
ESSION | +0.349 |
lp | +0.335 |
atown | +0.327 |
Neg logit contributions | |
eele | -0.345 |
�� | -0.343 |
ogical | -0.341 |
nature | -0.336 |
Dul | -0.331 |
Token | reading |
Token ID | 3555 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ILLE | +2.264 |
ctions | +2.166 |
ESSION | +2.141 |
lp | +2.078 |
ned | +2.066 |
Neg logit contributions | |
�� | -1.544 |
eele | -1.517 |
ogical | -1.478 |
nature | -1.440 |
aiman | -1.402 |
Token | the |
Token ID | 262 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
eele | +0.620 |
ogical | +0.615 |
�� | +0.610 |
nature | +0.604 |
Sor | +0.585 |
Neg logit contributions | |
ILLE | -1.013 |
ctions | -0.963 |
ESSION | -0.963 |
lp | -0.929 |
atown | -0.909 |
Token | main |
Token ID | 1388 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ILLE | +1.301 |
ctions | +1.227 |
ESSION | +1.207 |
lp | +1.162 |
ned | +1.150 |
Neg logit contributions | |
�� | -1.627 |
eele | -1.621 |
ogical | -1.583 |
nature | -1.559 |
Dul | -1.517 |
Token | story |
Token ID | 1621 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
ILLE | +4.497 |
ctions | +4.370 |
ned | +4.239 |
ESSION | +4.179 |
lp | +4.148 |
Neg logit contributions | |
�� | -4.802 |
eele | -4.614 |
nature | -4.323 |
ogical | -4.310 |
aiman | -4.289 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
ILLE | +5.467 |
ctions | +5.103 |
ned | +4.778 |
ESSION | +4.726 |
CLE | +4.616 |
Neg logit contributions | |
�� | -10.209 |
eele | -9.946 |
aiman | -9.637 |
ogical | -9.546 |
nature | -9.337 |
Token | verify |
Token ID | 11767 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ILLE | +1.755 |
ctions | +1.663 |
ESSION | +1.640 |
lp | +1.564 |
ned | +1.556 |
Neg logit contributions | |
�� | -2.162 |
eele | -2.137 |
ogical | -2.100 |
nature | -2.066 |
Dul | -2.029 |
Token | you |
Token ID | 345 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
ILLE | +2.699 |
ctions | +2.555 |
ESSION | +2.523 |
lp | +2.424 |
ned | +2.382 |
Neg logit contributions | |
�� | -3.653 |
eele | -3.598 |
ogical | -3.539 |
nature | -3.477 |
Dul | -3.411 |
Token | 're |
Token ID | 821 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
eele | +0.906 |
ogical | +0.895 |
�� | +0.888 |
nature | +0.884 |
Dul | +0.860 |
Neg logit contributions | |
ILLE | -0.827 |
ESSION | -0.765 |
ctions | -0.763 |
lp | -0.732 |
ned | -0.714 |
Token | not |
Token ID | 407 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
ILLE | +0.223 |
ctions | +0.211 |
ESSION | +0.211 |
lp | +0.204 |
ned | +0.200 |
Neg logit contributions | |
eele | -0.142 |
�� | -0.140 |
ogical | -0.139 |
nature | -0.136 |
Dul | -0.132 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
eele | +0.597 |
ogical | +0.594 |
nature | +0.587 |
�� | +0.586 |
Dul | +0.568 |
Neg logit contributions | |
ILLE | -0.560 |
ctions | -0.530 |
ESSION | -0.526 |
lp | -0.504 |
atown | -0.494 |
Token | Continue |
Token ID | 10054 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
ILLE | +1.607 |
ctions | +1.519 |
ESSION | +1.503 |
lp | +1.440 |
ned | +1.419 |
Neg logit contributions | |
�� | -1.843 |
eele | -1.834 |
ogical | -1.794 |
nature | -1.761 |
aiman | -1.714 |
Token | reading |
Token ID | 3555 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
ILLE | +2.570 |
ctions | +2.460 |
ESSION | +2.431 |
lp | +2.362 |
ned | +2.353 |
Neg logit contributions | |
�� | -1.796 |
eele | -1.765 |
ogical | -1.700 |
nature | -1.670 |
aiman | -1.624 |
Token | the |
Token ID | 262 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
ILLE | +0.284 |
ctions | +0.270 |
ESSION | +0.269 |
lp | +0.260 |
ned | +0.256 |
Neg logit contributions | |
eele | -0.187 |
�� | -0.186 |
ogical | -0.184 |
nature | -0.180 |
Dul | -0.175 |
Token | main |
Token ID | 1388 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ILLE | +1.082 |
ctions | +1.021 |
ESSION | +1.006 |
lp | +0.968 |
ned | +0.957 |
Neg logit contributions | |
�� | -1.348 |
eele | -1.339 |
ogical | -1.309 |
nature | -1.289 |
Dul | -1.257 |
Token | story |
Token ID | 1621 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ILLE | +3.775 |
ctions | +3.688 |
ned | +3.583 |
ESSION | +3.532 |
lp | +3.503 |
Neg logit contributions | |
�� | -3.931 |
eele | -3.820 |
nature | -3.569 |
ogical | -3.553 |
aiman | -3.492 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ILLE | +5.942 |
ctions | +5.667 |
ned | +5.519 |
ESSION | +5.337 |
lp | +5.264 |
Neg logit contributions | |
�� | -9.921 |
eele | -9.195 |
ogical | -8.926 |
elaide | -8.834 |
aiman | -8.758 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ILLE | +2.617 |
ctions | +2.501 |
ESSION | +2.440 |
lp | +2.385 |
ned | +2.376 |
Neg logit contributions | |
�� | -3.292 |
eele | -3.150 |
ogical | -3.074 |
nature | -2.986 |
aiman | -2.954 |
Token | Although |
Token ID | 7003 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ILLE | +2.779 |
ctions | +2.584 |
ESSION | +2.574 |
lp | +2.442 |
ned | +2.430 |
Neg logit contributions | |
�� | -3.600 |
eele | -3.496 |
ogical | -3.398 |
nature | -3.312 |
Dul | -3.291 |
Token | the |
Token ID | 262 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
ILLE | +1.247 |
ctions | +1.189 |
ESSION | +1.178 |
lp | +1.134 |
ned | +1.124 |
Neg logit contributions | |
�� | -0.969 |
eele | -0.961 |
ogical | -0.939 |
nature | -0.923 |
Dul | -0.890 |
Token | mar |
Token ID | 1667 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
eele | +0.045 |
�� | +0.044 |
ogical | +0.044 |
nature | +0.043 |
Dul | +0.042 |
Neg logit contributions | |
ILLE | -0.059 |
ESSION | -0.056 |
ctions | -0.056 |
lp | -0.054 |
ned | -0.053 |
Token | Up |
Token ID | 3205 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ILLE | +1.012 |
ctions | +0.956 |
ESSION | +0.954 |
lp | +0.917 |
ned | +0.897 |
Neg logit contributions | |
eele | -0.888 |
ogical | -0.878 |
�� | -0.874 |
nature | -0.863 |
Dul | -0.842 |
Token | Continue |
Token ID | 10054 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
ILLE | +0.443 |
ctions | +0.420 |
ESSION | +0.417 |
lp | +0.403 |
atown | +0.391 |
Neg logit contributions | |
eele | -0.407 |
�� | -0.403 |
ogical | -0.401 |
nature | -0.395 |
Dul | -0.392 |
Token | reading |
Token ID | 3555 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
ILLE | +1.890 |
ctions | +1.803 |
ESSION | +1.790 |
lp | +1.734 |
ned | +1.719 |
Neg logit contributions | |
�� | -1.238 |
eele | -1.222 |
ogical | -1.198 |
nature | -1.166 |
Dul | -1.130 |
Token | the |
Token ID | 262 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
eele | +0.810 |
ogical | +0.804 |
�� | +0.793 |
nature | +0.792 |
Sor | +0.769 |
Neg logit contributions | |
ILLE | -1.362 |
ctions | -1.296 |
ESSION | -1.294 |
lp | -1.249 |
atown | -1.225 |
Token | main |
Token ID | 1388 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ILLE | +1.429 |
ctions | +1.347 |
ESSION | +1.327 |
lp | +1.275 |
ned | +1.262 |
Neg logit contributions | |
�� | -1.772 |
eele | -1.767 |
ogical | -1.727 |
nature | -1.700 |
Dul | -1.654 |
Token | story |
Token ID | 1621 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
ILLE | +4.336 |
ctions | +4.214 |
ned | +4.107 |
ESSION | +4.053 |
lp | +4.019 |
Neg logit contributions | |
�� | -4.560 |
eele | -4.410 |
nature | -4.143 |
ogical | -4.127 |
aiman | -4.074 |
Token | Please |
Token ID | 4222 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
ILLE | +5.439 |
ctions | +5.026 |
ESSION | +4.716 |
ned | +4.687 |
CLE | +4.538 |
Neg logit contributions | |
�� | -9.689 |
eele | -9.501 |
aiman | -9.157 |
ogical | -9.138 |
nature | -8.941 |
Token | verify |
Token ID | 11767 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ILLE | +1.763 |
ctions | +1.663 |
ESSION | +1.648 |
lp | +1.576 |
ned | +1.554 |
Neg logit contributions | |
�� | -2.039 |
eele | -2.028 |
ogical | -1.999 |
nature | -1.964 |
Dul | -1.922 |
Token | you |
Token ID | 345 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ILLE | +2.557 |
ctions | +2.417 |
ESSION | +2.390 |
lp | +2.291 |
ned | +2.247 |
Neg logit contributions | |
�� | -3.369 |
eele | -3.326 |
ogical | -3.280 |
nature | -3.222 |
Dul | -3.156 |
Token | 're |
Token ID | 821 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
eele | +0.968 |
ogical | +0.954 |
�� | +0.948 |
nature | +0.942 |
Dul | +0.918 |
Neg logit contributions | |
ILLE | -0.884 |
ESSION | -0.818 |
ctions | -0.818 |
lp | -0.783 |
ned | -0.765 |
Token | not |
Token ID | 407 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
ILLE | +0.092 |
ESSION | +0.087 |
ctions | +0.087 |
lp | +0.084 |
ned | +0.082 |
Neg logit contributions | |
eele | -0.057 |
�� | -0.056 |
ogical | -0.056 |
nature | -0.055 |
Dul | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
eele | +0.457 |
ogical | +0.453 |
�� | +0.452 |
nature | +0.442 |
Dul | +0.431 |
Neg logit contributions | |
ILLE | -0.595 |
ESSION | -0.563 |
ctions | -0.562 |
lp | -0.540 |
ned | -0.531 |
Token | perhaps |
Token ID | 3737 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
ILLE | +0.266 |
ctions | +0.252 |
ESSION | +0.251 |
lp | +0.241 |
ned | +0.238 |
Neg logit contributions | |
�� | -0.219 |
eele | -0.219 |
ogical | -0.216 |
nature | -0.211 |
Dul | -0.205 |
Token | to |
Token ID | 284 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
eele | +0.060 |
�� | +0.060 |
ogical | +0.059 |
nature | +0.058 |
Dul | +0.057 |
Neg logit contributions | |
ILLE | -0.073 |
ctions | -0.069 |
ESSION | -0.069 |
lp | -0.067 |
ned | -0.065 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
eele | +0.552 |
�� | +0.546 |
ogical | +0.546 |
nature | +0.532 |
Dul | +0.520 |
Neg logit contributions | |
ILLE | -0.713 |
ESSION | -0.675 |
ctions | -0.674 |
lp | -0.648 |
ned | -0.634 |
Token | a |
Token ID | 257 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
ILLE | +0.355 |
ctions | +0.334 |
ESSION | +0.333 |
lp | +0.317 |
ned | +0.310 |
Neg logit contributions | |
eele | -0.371 |
�� | -0.368 |
ogical | -0.367 |
nature | -0.361 |
Dul | -0.353 |
Token | Chevy |
Token ID | 40688 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ILLE | +0.921 |
ctions | +0.869 |
ESSION | +0.868 |
lp | +0.832 |
ned | +0.817 |
Neg logit contributions | |
eele | -0.856 |
�� | -0.853 |
ogical | -0.845 |
nature | -0.828 |
Dul | -0.810 |
Token | Volt |
Token ID | 22702 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
ILLE | +8.037 |
ctions | +7.444 |
ESSION | +7.420 |
CLE | +7.289 |
ned | +7.238 |
Neg logit contributions | |
�� | -6.805 |
eele | -6.268 |
ogical | -6.175 |
nature | -5.994 |
agine | -5.777 |
Token | from |
Token ID | 422 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
ILLE | +1.690 |
ctions | +1.597 |
ESSION | +1.591 |
lp | +1.530 |
ned | +1.507 |
Neg logit contributions | |
�� | -1.501 |
eele | -1.495 |
ogical | -1.470 |
nature | -1.444 |
Dul | -1.401 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ILLE | +0.643 |
ctions | +0.611 |
ESSION | +0.608 |
lp | +0.588 |
ned | +0.579 |
Neg logit contributions | |
�� | -0.466 |
eele | -0.462 |
ogical | -0.453 |
nature | -0.443 |
Dul | -0.427 |
Token | bailed |
Token ID | 47739 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ILLE | +0.388 |
ctions | +0.367 |
ESSION | +0.366 |
lp | +0.352 |
ned | +0.346 |
Neg logit contributions | |
eele | -0.320 |
�� | -0.319 |
ogical | -0.316 |
nature | -0.309 |
Dul | -0.302 |
Token | - |
Token ID | 12 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
ILLE | +0.558 |
ctions | +0.525 |
ESSION | +0.525 |
lp | +0.504 |
ned | +0.496 |
Neg logit contributions | |
�� | -0.547 |
eele | -0.545 |
ogical | -0.534 |
nature | -0.527 |
Dul | -0.510 |
Token | for |
Token ID | 329 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ILLE | +0.301 |
ctions | +0.286 |
ESSION | +0.284 |
lp | +0.274 |
ned | +0.271 |
Neg logit contributions | |
�� | -0.233 |
eele | -0.232 |
ogical | -0.228 |
nature | -0.224 |
Dul | -0.217 |
Token | those |
Token ID | 883 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
ILLE | +0.290 |
ctions | +0.274 |
ESSION | +0.273 |
lp | +0.262 |
ned | +0.258 |
Neg logit contributions | |
eele | -0.267 |
�� | -0.267 |
ogical | -0.263 |
nature | -0.258 |
Dul | -0.252 |
Token | who |
Token ID | 508 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ILLE | +2.319 |
ctions | +2.198 |
ESSION | +2.170 |
lp | +2.088 |
ned | +2.074 |
Neg logit contributions | |
�� | -2.242 |
eele | -2.232 |
ogical | -2.180 |
nature | -2.151 |
Dul | -2.084 |
Token | prefer |
Token ID | 4702 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
ILLE | +2.975 |
ctions | +2.846 |
ESSION | +2.802 |
lp | +2.745 |
ned | +2.716 |
Neg logit contributions | |
�� | -2.553 |
eele | -2.503 |
ogical | -2.438 |
nature | -2.372 |
Dul | -2.305 |
Token | full |
Token ID | 1336 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
eele | +0.919 |
�� | +0.915 |
ogical | +0.906 |
nature | +0.890 |
Dul | +0.867 |
Neg logit contributions | |
ILLE | -1.076 |
ctions | -1.020 |
ESSION | -1.016 |
lp | -0.979 |
ned | -0.957 |
Token | throttle |
Token ID | 29976 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
eele | +0.258 |
�� | +0.258 |
ogical | +0.255 |
nature | +0.250 |
Dul | +0.244 |
Neg logit contributions | |
ILLE | -0.274 |
ctions | -0.259 |
ESSION | -0.258 |
lp | -0.247 |
ned | -0.243 |
Token | all |
Token ID | 477 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ILLE | +7.077 |
ctions | +6.673 |
ESSION | +6.518 |
ned | +6.481 |
lp | +6.344 |
Neg logit contributions | |
�� | -7.136 |
eele | -6.974 |
ogical | -6.658 |
nature | -6.529 |
aiman | -6.412 |
Token | the |
Token ID | 262 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
eele | +0.549 |
�� | +0.548 |
ogical | +0.546 |
nature | +0.532 |
Dul | +0.518 |
Neg logit contributions | |
ILLE | -0.689 |
ctions | -0.651 |
ESSION | -0.650 |
lp | -0.630 |
ned | -0.613 |
Token | time |
Token ID | 640 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
eele | +0.315 |
�� | +0.314 |
ogical | +0.312 |
nature | +0.306 |
Dul | +0.298 |
Neg logit contributions | |
ILLE | -0.408 |
ESSION | -0.388 |
ctions | -0.388 |
lp | -0.374 |
ned | -0.366 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
eele | +1.656 |
ogical | +1.653 |
�� | +1.638 |
nature | +1.615 |
Dul | +1.577 |
Neg logit contributions | |
ILLE | -1.988 |
ESSION | -1.879 |
ctions | -1.878 |
lp | -1.807 |
CLE | -1.757 |
Token | like |
Token ID | 588 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
eele | +0.377 |
�� | +0.373 |
ogical | +0.372 |
nature | +0.365 |
Dul | +0.356 |
Neg logit contributions | |
ILLE | -0.457 |
ESSION | -0.433 |
ctions | -0.433 |
lp | -0.415 |
ned | -0.407 |
Token | to |
Token ID | 284 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
ILLE | +0.019 |
ctions | +0.018 |
ESSION | +0.018 |
lp | +0.017 |
ned | +0.017 |
Neg logit contributions | |
eele | -0.015 |
�� | -0.015 |
ogical | -0.015 |
nature | -0.015 |
Dul | -0.014 |
Token | bring |
Token ID | 2222 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ILLE | +0.082 |
ctions | +0.078 |
ESSION | +0.078 |
lp | +0.075 |
ned | +0.074 |
Neg logit contributions | |
�� | -0.068 |
eele | -0.068 |
ogical | -0.067 |
nature | -0.066 |
Dul | -0.064 |
Token | powerful |
Token ID | 3665 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
eele | +0.518 |
�� | +0.514 |
ogical | +0.512 |
nature | +0.500 |
Dul | +0.488 |
Neg logit contributions | |
ILLE | -0.716 |
ctions | -0.681 |
ESSION | -0.680 |
lp | -0.656 |
ned | -0.641 |
Token | ARM |
Token ID | 20359 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
eele | +0.037 |
�� | +0.036 |
ogical | +0.036 |
nature | +0.035 |
Dul | +0.035 |
Neg logit contributions | |
ILLE | -0.044 |
ESSION | -0.042 |
ctions | -0.042 |
lp | -0.040 |
ned | -0.039 |
Token | micro |
Token ID | 4580 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ILLE | +4.013 |
ctions | +3.778 |
ESSION | +3.764 |
lp | +3.647 |
ned | +3.601 |
Neg logit contributions | |
�� | -4.103 |
eele | -3.977 |
ogical | -3.900 |
nature | -3.876 |
Dul | -3.755 |
Token | cont |
Token ID | 3642 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ILLE | +3.404 |
ctions | +3.275 |
ESSION | +3.215 |
lp | +3.108 |
ned | +3.026 |
Neg logit contributions | |
�� | -4.063 |
eele | -4.014 |
ogical | -3.938 |
nature | -3.872 |
Dul | -3.783 |
Token | rollers |
Token ID | 36667 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ctions | +2.762 |
ILLE | +2.462 |
ESSION | +2.430 |
lp | +2.258 |
ned | +2.207 |
Neg logit contributions | |
�� | -11.292 |
eele | -10.831 |
ogical | -10.630 |
nature | -10.577 |
Dul | -10.424 |
Token | to |
Token ID | 284 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ILLE | +3.607 |
ctions | +3.442 |
ESSION | +3.384 |
ned | +3.277 |
lp | +3.261 |
Neg logit contributions | |
�� | -3.471 |
eele | -3.463 |
ogical | -3.321 |
nature | -3.314 |
Dul | -3.182 |
Token | hobby |
Token ID | 20005 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
eele | +0.677 |
�� | +0.670 |
ogical | +0.668 |
nature | +0.654 |
Dul | +0.637 |
Neg logit contributions | |
ILLE | -0.935 |
ESSION | -0.886 |
ctions | -0.886 |
lp | -0.853 |
ned | -0.837 |
Token | ists |
Token ID | 1023 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ogical | +2.422 |
eele | +2.370 |
�� | +2.332 |
nature | +2.326 |
Sor | +2.253 |
Neg logit contributions | |
ILLE | -2.606 |
ESSION | -2.437 |
ctions | -2.426 |
lp | -2.354 |
CLE | -2.275 |
Token | . |
Token ID | 13 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
eele | +0.369 |
�� | +0.368 |
ogical | +0.365 |
nature | +0.357 |
Dul | +0.348 |
Neg logit contributions | |
ILLE | -0.431 |
ctions | -0.408 |
ESSION | -0.406 |
lp | -0.391 |
ned | -0.383 |
Token | from |
Token ID | 422 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
ogical | +2.582 |
eele | +2.571 |
�� | +2.527 |
nature | +2.505 |
Dul | +2.461 |
Neg logit contributions | |
ILLE | -3.238 |
ctions | -3.086 |
ESSION | -3.067 |
lp | -2.958 |
CLE | -2.877 |
Token | Mitch |
Token ID | 20472 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ILLE | +0.209 |
ctions | +0.199 |
ESSION | +0.198 |
lp | +0.191 |
ned | +0.189 |
Neg logit contributions | |
eele | -0.151 |
�� | -0.151 |
ogical | -0.148 |
nature | -0.145 |
Dul | -0.140 |
Token | McConnell |
Token ID | 18184 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ILLE | +3.211 |
ESSION | +3.012 |
ctions | +2.974 |
lp | +2.906 |
ned | +2.878 |
Neg logit contributions | |
�� | -3.448 |
eele | -3.426 |
ogical | -3.278 |
nature | -3.254 |
Dul | -3.117 |
Token | and |
Token ID | 290 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ILLE | +5.278 |
ctions | +4.987 |
ESSION | +4.935 |
ned | +4.747 |
lp | +4.744 |
Neg logit contributions | |
�� | -5.259 |
eele | -5.208 |
ogical | -5.003 |
nature | -4.957 |
aiman | -4.837 |
Token | Chuck |
Token ID | 14663 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ILLE | +1.769 |
ctions | +1.677 |
ESSION | +1.676 |
lp | +1.611 |
ned | +1.598 |
Neg logit contributions | |
�� | -1.452 |
eele | -1.447 |
ogical | -1.400 |
nature | -1.380 |
Dul | -1.333 |
Token | Grassley |
Token ID | 44050 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ILLE | +2.933 |
ESSION | +2.819 |
ctions | +2.731 |
lp | +2.646 |
ned | +2.542 |
Neg logit contributions | |
�� | -3.918 |
eele | -3.859 |
ogical | -3.754 |
nature | -3.663 |
agine | -3.637 |
Token | would |
Token ID | 561 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
ILLE | +6.713 |
ctions | +6.360 |
ESSION | +6.277 |
ned | +6.045 |
lp | +6.024 |
Neg logit contributions | |
�� | -7.109 |
eele | -6.881 |
ogical | -6.637 |
nature | -6.566 |
aiman | -6.415 |
Token | be |
Token ID | 307 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
ILLE | +0.252 |
ctions | +0.239 |
ESSION | +0.237 |
lp | +0.229 |
ned | +0.226 |
Neg logit contributions | |
�� | -0.222 |
eele | -0.222 |
ogical | -0.217 |
nature | -0.214 |
Dul | -0.208 |
Token | the |
Token ID | 262 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
ILLE | +0.060 |
ctions | +0.057 |
ESSION | +0.057 |
lp | +0.055 |
ned | +0.054 |
Neg logit contributions | |
eele | -0.044 |
�� | -0.043 |
ogical | -0.043 |
nature | -0.042 |
Dul | -0.041 |
Token | end |
Token ID | 886 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ILLE | +1.698 |
ctions | +1.611 |
ESSION | +1.605 |
lp | +1.545 |
ned | +1.520 |
Neg logit contributions | |
eele | -1.354 |
�� | -1.353 |
ogical | -1.333 |
nature | -1.306 |
Dul | -1.270 |
Token | result |
Token ID | 1255 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
ILLE | +2.105 |
ctions | +2.007 |
ESSION | +1.982 |
lp | +1.919 |
ned | +1.898 |
Neg logit contributions | |
�� | -1.655 |
eele | -1.652 |
ogical | -1.602 |
nature | -1.588 |
Dul | -1.527 |
Token | Up |
Token ID | 3205 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
ILLE | +0.876 |
ctions | +0.828 |
ESSION | +0.825 |
lp | +0.793 |
ned | +0.775 |
Neg logit contributions | |
eele | -0.753 |
ogical | -0.744 |
�� | -0.739 |
nature | -0.733 |
Dul | -0.715 |
Token | Continue |
Token ID | 10054 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
ILLE | +0.130 |
ctions | +0.123 |
ESSION | +0.122 |
lp | +0.118 |
atown | +0.116 |
Neg logit contributions | |
eele | -0.115 |
�� | -0.114 |
ogical | -0.114 |
nature | -0.113 |
Dul | -0.112 |
Token | reading |
Token ID | 3555 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
ILLE | +1.959 |
ctions | +1.874 |
ESSION | +1.858 |
lp | +1.799 |
ned | +1.786 |
Neg logit contributions | |
�� | -1.304 |
eele | -1.287 |
ogical | -1.259 |
nature | -1.223 |
aiman | -1.189 |
Token | the |
Token ID | 262 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
ogical | +1.226 |
eele | +1.225 |
nature | +1.211 |
�� | +1.206 |
Sor | +1.176 |
Neg logit contributions | |
ILLE | -2.184 |
ctions | -2.075 |
ESSION | -2.075 |
lp | -2.008 |
atown | -1.969 |
Token | main |
Token ID | 1388 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ILLE | +0.771 |
ctions | +0.725 |
ESSION | +0.716 |
lp | +0.687 |
ned | +0.679 |
Neg logit contributions | |
eele | -0.938 |
�� | -0.937 |
ogical | -0.921 |
nature | -0.905 |
Dul | -0.881 |
Token | story |
Token ID | 1621 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ILLE | +4.105 |
ctions | +3.965 |
ESSION | +3.819 |
ned | +3.810 |
lp | +3.750 |
Neg logit contributions | |
�� | -3.976 |
eele | -3.885 |
ogical | -3.668 |
nature | -3.630 |
aiman | -3.588 |
Token | Please |
Token ID | 4222 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
ILLE | +5.215 |
ctions | +4.857 |
ESSION | +4.596 |
ned | +4.558 |
CLE | +4.444 |
Neg logit contributions | |
�� | -8.955 |
eele | -8.921 |
ogical | -8.591 |
aiman | -8.546 |
nature | -8.351 |
Token | verify |
Token ID | 11767 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
ILLE | +1.452 |
ctions | +1.369 |
ESSION | +1.357 |
lp | +1.298 |
ned | +1.282 |
Neg logit contributions | |
�� | -1.687 |
eele | -1.679 |
ogical | -1.654 |
nature | -1.624 |
Dul | -1.590 |
Token | you |
Token ID | 345 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
ILLE | +2.275 |
ctions | +2.144 |
ESSION | +2.124 |
lp | +2.035 |
ned | +1.996 |
Neg logit contributions | |
�� | -2.900 |
eele | -2.877 |
ogical | -2.835 |
nature | -2.786 |
Dul | -2.726 |
Token | 're |
Token ID | 821 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
eele | +1.319 |
ogical | +1.301 |
nature | +1.291 |
�� | +1.282 |
Dul | +1.253 |
Neg logit contributions | |
ILLE | -1.267 |
ESSION | -1.169 |
ctions | -1.163 |
lp | -1.118 |
atown | -1.098 |
Token | not |
Token ID | 407 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
eele | +0.115 |
ogical | +0.113 |
�� | +0.113 |
nature | +0.110 |
Dul | +0.107 |
Neg logit contributions | |
ILLE | -0.185 |
ESSION | -0.176 |
ctions | -0.175 |
lp | -0.169 |
CLE | -0.166 |
Token | pointed |
Token ID | 6235 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
�� | +0.058 |
eele | +0.058 |
ogical | +0.057 |
nature | +0.056 |
Dul | +0.054 |
Neg logit contributions | |
ILLE | -0.075 |
ctions | -0.071 |
ESSION | -0.071 |
lp | -0.068 |
ned | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
�� | +0.659 |
eele | +0.657 |
ogical | +0.644 |
nature | +0.634 |
Dul | +0.612 |
Neg logit contributions | |
ILLE | -0.821 |
ctions | -0.780 |
ESSION | -0.775 |
lp | -0.747 |
ned | -0.740 |
Token | blame |
Token ID | 8138 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
eele | +0.146 |
�� | +0.146 |
ogical | +0.144 |
nature | +0.141 |
Dul | +0.137 |
Neg logit contributions | |
ILLE | -0.194 |
ESSION | -0.184 |
ctions | -0.183 |
lp | -0.177 |
ned | -0.173 |
Token | towards |
Token ID | 3371 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ILLE | +1.972 |
ctions | +1.898 |
ESSION | +1.862 |
lp | +1.815 |
ned | +1.803 |
Neg logit contributions | |
�� | -1.603 |
eele | -1.572 |
ogical | -1.530 |
nature | -1.509 |
Dul | -1.457 |
Token | the |
Token ID | 262 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
eele | +0.546 |
�� | +0.543 |
ogical | +0.538 |
nature | +0.526 |
Dul | +0.513 |
Neg logit contributions | |
ILLE | -0.762 |
ctions | -0.724 |
ESSION | -0.723 |
lp | -0.696 |
ned | -0.684 |
Token | dis |
Token ID | 595 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ILLE | +0.945 |
ctions | +0.897 |
ESSION | +0.892 |
lp | +0.860 |
ned | +0.846 |
Neg logit contributions | |
�� | -0.777 |
eele | -0.776 |
ogical | -0.763 |
nature | -0.748 |
Dul | -0.726 |
Token | ench |
Token ID | 24421 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ctions | +6.548 |
ILLE | +6.248 |
ESSION | +6.093 |
lp | +6.002 |
ned | +5.968 |
Neg logit contributions | |
�� | -7.352 |
eele | -6.915 |
ogical | -6.614 |
Dul | -6.583 |
Sor | -6.537 |
Token | anted |
Token ID | 4126 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ILLE | +0.184 |
ctions | +0.174 |
ESSION | +0.171 |
lp | +0.160 |
ned | +0.159 |
Neg logit contributions | |
�� | -0.382 |
eele | -0.381 |
ogical | -0.373 |
nature | -0.367 |
Dul | -0.363 |
Token | , |
Token ID | 11 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ILLE | +0.973 |
ctions | +0.924 |
ESSION | +0.917 |
lp | +0.885 |
ned | +0.873 |
Neg logit contributions | |
�� | -0.825 |
eele | -0.822 |
ogical | -0.806 |
nature | -0.792 |
Dul | -0.767 |
Token | j |
Token ID | 474 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
eele | +0.323 |
�� | +0.322 |
ogical | +0.320 |
nature | +0.314 |
Dul | +0.305 |
Neg logit contributions | |
ILLE | -0.386 |
ctions | -0.365 |
ESSION | -0.365 |
lp | -0.350 |
ned | -0.344 |
Token | aded |
Token ID | 5286 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ILLE | +2.031 |
ctions | +1.897 |
ESSION | +1.876 |
lp | +1.798 |
ned | +1.762 |
Neg logit contributions | |
�� | -3.146 |
eele | -3.090 |
ogical | -3.054 |
nature | -3.024 |
Dul | -2.982 |
Token | Pence |
Token ID | 17339 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
�� | +0.310 |
eele | +0.310 |
ogical | +0.304 |
nature | +0.296 |
Dul | +0.285 |
Neg logit contributions | |
ILLE | -0.549 |
ctions | -0.525 |
ESSION | -0.523 |
lp | -0.506 |
ned | -0.500 |
Token | on |
Token ID | 319 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ILLE | +0.437 |
ctions | +0.414 |
ESSION | +0.412 |
lp | +0.396 |
ned | +0.390 |
Neg logit contributions | |
eele | -0.388 |
�� | -0.388 |
ogical | -0.382 |
nature | -0.375 |
Dul | -0.364 |
Token | any |
Token ID | 597 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
�� | +0.412 |
eele | +0.411 |
ogical | +0.403 |
nature | +0.395 |
Dul | +0.381 |
Neg logit contributions | |
ILLE | -0.642 |
ctions | -0.612 |
ESSION | -0.610 |
lp | -0.589 |
ned | -0.582 |
Token | of |
Token ID | 286 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
eele | +0.932 |
�� | +0.923 |
ogical | +0.922 |
nature | +0.898 |
Dul | +0.875 |
Neg logit contributions | |
ILLE | -1.247 |
ESSION | -1.179 |
ctions | -1.177 |
lp | -1.136 |
ned | -1.114 |
Token | his |
Token ID | 465 |
Feature activation | -2.86e-03 |
Pos logit contributions | |
eele | +1.024 |
�� | +1.020 |
ogical | +1.008 |
nature | +0.984 |
Dul | +0.955 |
Neg logit contributions | |
ILLE | -1.614 |
ctions | -1.536 |
ESSION | -1.533 |
lp | -1.481 |
ned | -1.458 |
Token | dis |
Token ID | 595 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
eele | +0.007 |
ogical | +0.007 |
�� | +0.007 |
nature | +0.007 |
Dul | +0.007 |
Neg logit contributions | |
ILLE | -0.008 |
ESSION | -0.008 |
ctions | -0.008 |
lp | -0.007 |
ned | -0.007 |
Token | semb |
Token ID | 4428 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ctions | +6.293 |
ILLE | +6.112 |
ESSION | +5.846 |
lp | +5.780 |
ned | +5.746 |
Neg logit contributions | |
�� | -7.696 |
eele | -6.957 |
Dul | -6.867 |
ogical | -6.812 |
Sor | -6.707 |
Token | ling |
Token ID | 1359 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
ILLE | +4.799 |
ctions | +4.584 |
ESSION | +4.523 |
lp | +4.469 |
ned | +4.316 |
Neg logit contributions | |
�� | -4.431 |
ogical | -4.219 |
eele | -4.180 |
Dul | -4.045 |
nature | -4.024 |
Token | . |
Token ID | 13 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
ILLE | +1.228 |
ctions | +1.161 |
ESSION | +1.155 |
lp | +1.109 |
ned | +1.092 |
Neg logit contributions | |
�� | -1.153 |
eele | -1.150 |
ogical | -1.132 |
nature | -1.112 |
Dul | -1.082 |
Token | � |
Token ID | 564 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
ILLE | +0.018 |
ctions | +0.017 |
ESSION | +0.017 |
lp | +0.017 |
ned | +0.016 |
Neg logit contributions | |
eele | -0.016 |
�� | -0.016 |
ogical | -0.016 |
nature | -0.016 |
Dul | -0.015 |
Token | � |
Token ID | 250 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
eele | +0.048 |
�� | +0.048 |
ogical | +0.048 |
nature | +0.047 |
Dul | +0.046 |
Neg logit contributions | |
ILLE | -0.021 |
ctions | -0.019 |
ESSION | -0.019 |
lp | -0.018 |
ned | -0.017 |
Token | central |
Token ID | 4318 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
eele | +1.181 |
�� | +1.179 |
ogical | +1.160 |
nature | +1.135 |
Dul | +1.099 |
Neg logit contributions | |
ILLE | -1.746 |
ctions | -1.663 |
ESSION | -1.657 |
lp | -1.600 |
ned | -1.576 |
Token | casting |
Token ID | 13092 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
eele | +1.192 |
�� | +1.186 |
ogical | +1.178 |
nature | +1.152 |
Dul | +1.121 |
Neg logit contributions | |
ILLE | -1.462 |
ctions | -1.383 |
ESSION | -1.376 |
lp | -1.324 |
ned | -1.303 |
Token | to |
Token ID | 284 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
eele | +1.231 |
�� | +1.214 |
ogical | +1.205 |
nature | +1.178 |
Dul | +1.152 |
Neg logit contributions | |
ILLE | -1.599 |
ctions | -1.519 |
ESSION | -1.516 |
lp | -1.461 |
ned | -1.431 |
Token | play |
Token ID | 711 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
eele | +0.684 |
�� | +0.682 |
ogical | +0.672 |
nature | +0.659 |
Dul | +0.641 |
Neg logit contributions | |
ILLE | -0.878 |
ctions | -0.834 |
ESSION | -0.831 |
lp | -0.800 |
ned | -0.787 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
eele | +2.864 |
�� | +2.823 |
ogical | +2.820 |
nature | +2.763 |
Dul | +2.718 |
Neg logit contributions | |
ILLE | -3.776 |
ctions | -3.598 |
ESSION | -3.595 |
lp | -3.446 |
ned | -3.363 |
Token | dis |
Token ID | 595 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ILLE | +0.357 |
ctions | +0.338 |
ESSION | +0.335 |
lp | +0.323 |
ned | +0.318 |
Neg logit contributions | |
�� | -0.316 |
eele | -0.315 |
ogical | -0.310 |
nature | -0.304 |
Dul | -0.294 |
Token | arming |
Token ID | 18052 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
ctions | +6.567 |
ILLE | +6.307 |
lp | +6.150 |
ESSION | +6.122 |
ned | +6.112 |
Neg logit contributions | |
�� | -7.267 |
eele | -6.655 |
ogical | -6.484 |
Dul | -6.402 |
Sor | -6.326 |
Token | , |
Token ID | 11 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
eele | +1.221 |
�� | +1.208 |
ogical | +1.208 |
nature | +1.182 |
Dul | +1.159 |
Neg logit contributions | |
ILLE | -1.460 |
ESSION | -1.380 |
ctions | -1.378 |
lp | -1.324 |
ned | -1.293 |
Token | grandfather |
Token ID | 17695 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
eele | +0.455 |
�� | +0.454 |
ogical | +0.449 |
nature | +0.439 |
Dul | +0.429 |
Neg logit contributions | |
ILLE | -0.540 |
ctions | -0.511 |
ESSION | -0.511 |
lp | -0.490 |
ned | -0.481 |
Token | ly |
Token ID | 306 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
ILLE | +0.990 |
ctions | +0.941 |
ESSION | +0.934 |
lp | +0.910 |
ned | +0.898 |
Neg logit contributions | |
�� | -0.778 |
eele | -0.767 |
ogical | -0.744 |
nature | -0.734 |
Dul | -0.710 |
Token | right |
Token ID | 826 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ILLE | +1.166 |
ctions | +1.115 |
ESSION | +1.102 |
lp | +1.067 |
ned | +1.059 |
Neg logit contributions | |
�� | -0.977 |
eele | -0.961 |
ogical | -0.935 |
nature | -0.918 |
aiman | -0.887 |
Token | probe |
Token ID | 12774 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
ILLE | +0.208 |
ctions | +0.198 |
ESSION | +0.197 |
lp | +0.191 |
ned | +0.188 |
Neg logit contributions | |
�� | -0.157 |
eele | -0.155 |
ogical | -0.153 |
nature | -0.150 |
Dul | -0.144 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ILLE | +1.090 |
ctions | +1.034 |
ESSION | +1.030 |
lp | +0.994 |
ned | +0.978 |
Neg logit contributions | |
�� | -0.945 |
eele | -0.939 |
ogical | -0.922 |
nature | -0.909 |
Dul | -0.872 |
Token | Ph |
Token ID | 1380 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ILLE | +0.503 |
ctions | +0.480 |
ESSION | +0.477 |
lp | +0.461 |
ned | +0.453 |
Neg logit contributions | |
�� | -0.392 |
eele | -0.390 |
ogical | -0.382 |
nature | -0.376 |
Dul | -0.361 |
Token | obos |
Token ID | 49878 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
ILLE | +1.059 |
ctions | +1.020 |
ESSION | +1.017 |
lp | +0.991 |
ned | +0.979 |
Neg logit contributions | |
�� | -0.329 |
eele | -0.327 |
ogical | -0.316 |
nature | -0.305 |
Dul | -0.288 |
Token | - |
Token ID | 12 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
ILLE | +0.879 |
ctions | +0.825 |
ESSION | +0.822 |
lp | +0.802 |
ned | +0.786 |
Neg logit contributions | |
�� | -0.874 |
eele | -0.863 |
ogical | -0.850 |
nature | -0.836 |
aiman | -0.804 |
Token | Gr |
Token ID | 8642 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
eele | +0.877 |
�� | +0.872 |
ogical | +0.864 |
nature | +0.851 |
Dul | +0.828 |
Neg logit contributions | |
ILLE | -0.913 |
ctions | -0.862 |
ESSION | -0.860 |
lp | -0.822 |
ned | -0.810 |
Token | unt |
Token ID | 2797 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ctions | +4.412 |
ILLE | +4.373 |
ESSION | +4.149 |
lp | +4.116 |
ned | +3.957 |
Neg logit contributions | |
�� | -9.710 |
eele | -9.128 |
ogical | -9.049 |
Sor | -8.632 |
Mou | -8.600 |
Token | , |
Token ID | 11 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
ILLE | +0.798 |
ctions | +0.755 |
ESSION | +0.750 |
lp | +0.726 |
ned | +0.714 |
Neg logit contributions | |
�� | -0.746 |
eele | -0.739 |
ogical | -0.728 |
nature | -0.714 |
Dul | -0.693 |
Token | last |
Token ID | 938 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ILLE | +0.212 |
ctions | +0.200 |
ESSION | +0.200 |
lp | +0.191 |
ned | +0.188 |
Neg logit contributions | |
eele | -0.183 |
�� | -0.182 |
ogical | -0.180 |
nature | -0.177 |
Dul | -0.172 |
Token | year |
Token ID | 614 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
eele | +0.317 |
�� | +0.316 |
ogical | +0.312 |
nature | +0.305 |
Dul | +0.296 |
Neg logit contributions | |
ILLE | -0.463 |
ctions | -0.440 |
ESSION | -0.439 |
lp | -0.423 |
ned | -0.417 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ILLE | +1.322 |
ctions | +1.245 |
ESSION | +1.228 |
lp | +1.203 |
ned | +1.190 |
Neg logit contributions | |
�� | -1.382 |
eele | -1.372 |
ogical | -1.348 |
nature | -1.327 |
aiman | -1.279 |
Token | mind |
Token ID | 10155 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
ILLE | +0.621 |
ctions | +0.592 |
ESSION | +0.584 |
lp | +0.564 |
ned | +0.557 |
Neg logit contributions | |
�� | -0.645 |
eele | -0.642 |
ogical | -0.631 |
nature | -0.618 |
Dul | -0.607 |
Token | target |
Token ID | 2496 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
ILLE | +2.746 |
ctions | +2.623 |
ESSION | +2.593 |
lp | +2.511 |
ned | +2.504 |
Neg logit contributions | |
�� | -2.508 |
eele | -2.476 |
ogical | -2.443 |
nature | -2.386 |
Dul | -2.326 |
Token | since |
Token ID | 1201 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
ILLE | +1.962 |
ctions | +1.879 |
ESSION | +1.852 |
lp | +1.794 |
ned | +1.790 |
Neg logit contributions | |
�� | -1.795 |
eele | -1.768 |
ogical | -1.748 |
nature | -1.707 |
Dul | -1.665 |
Token | he |
Token ID | 339 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ILLE | +2.169 |
ctions | +2.064 |
ESSION | +2.047 |
lp | +1.979 |
ned | +1.972 |
Neg logit contributions | |
�� | -1.634 |
eele | -1.616 |
ogical | -1.589 |
nature | -1.545 |
Dul | -1.496 |
Token | has |
Token ID | 468 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
ILLE | +0.559 |
ctions | +0.531 |
ESSION | +0.528 |
lp | +0.509 |
ned | +0.501 |
Neg logit contributions | |
�� | -0.454 |
eele | -0.453 |
ogical | -0.446 |
nature | -0.437 |
Dul | -0.425 |
Token | Inv |
Token ID | 10001 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
eele | +0.137 |
�� | +0.136 |
ogical | +0.134 |
nature | +0.132 |
Dul | +0.128 |
Neg logit contributions | |
ILLE | -0.185 |
ctions | -0.176 |
ESSION | -0.176 |
lp | -0.169 |
ned | -0.167 |
Token | ulnerability |
Token ID | 40920 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ILLE | +5.342 |
ESSION | +5.117 |
ctions | +5.040 |
ned | +4.846 |
lp | +4.763 |
Neg logit contributions | |
�� | -8.435 |
eele | -7.901 |
ogical | -7.844 |
nature | -7.642 |
aiman | -7.590 |
Token | and |
Token ID | 290 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
ILLE | +0.473 |
ctions | +0.448 |
ESSION | +0.446 |
lp | +0.429 |
ned | +0.423 |
Neg logit contributions | |
�� | -0.404 |
eele | -0.404 |
ogical | -0.398 |
nature | -0.390 |
Dul | -0.379 |
Token | two |
Token ID | 734 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
eele | +0.123 |
�� | +0.123 |
ogical | +0.121 |
nature | +0.119 |
Dul | +0.115 |
Neg logit contributions | |
ILLE | -0.160 |
ctions | -0.152 |
ESSION | -0.151 |
lp | -0.145 |
ned | -0.143 |
Token | STOP |
Token ID | 44934 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
eele | +1.036 |
�� | +1.024 |
ogical | +1.019 |
nature | +1.005 |
Sor | +0.981 |
Neg logit contributions | |
ILLE | -1.185 |
ESSION | -1.123 |
ctions | -1.115 |
lp | -1.077 |
atown | -1.047 |
Token | clicks |
Token ID | 25785 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
ILLE | +1.022 |
ctions | +0.954 |
ESSION | +0.938 |
lp | +0.889 |
ned | +0.871 |
Neg logit contributions | |
�� | -1.656 |
eele | -1.643 |
ogical | -1.629 |
nature | -1.603 |
Dul | -1.571 |
Token | contain |
Token ID | 3994 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
ILLE | +1.640 |
ctions | +1.568 |
ESSION | +1.535 |
lp | +1.492 |
ned | +1.471 |
Neg logit contributions | |
�� | -1.642 |
eele | -1.627 |
ogical | -1.594 |
nature | -1.580 |
Dul | -1.528 |
Token | the |
Token ID | 262 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
ILLE | +2.004 |
ctions | +1.911 |
ESSION | +1.900 |
lp | +1.836 |
ned | +1.803 |
Neg logit contributions | |
�� | -1.607 |
eele | -1.586 |
ogical | -1.553 |
nature | -1.531 |
Dul | -1.471 |
Token | instructions |
Token ID | 7729 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
ILLE | +1.635 |
ctions | +1.554 |
ESSION | +1.545 |
lp | +1.487 |
ned | +1.457 |
Neg logit contributions | |
�� | -1.480 |
eele | -1.470 |
ogical | -1.443 |
nature | -1.421 |
Dul | -1.372 |
Token | to |
Token ID | 284 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
ILLE | +1.234 |
ctions | +1.171 |
ESSION | +1.165 |
lp | +1.122 |
ned | +1.105 |
Neg logit contributions | |
�� | -1.001 |
eele | -0.999 |
ogical | -0.981 |
nature | -0.963 |
Dul | -0.935 |
Token | create |
Token ID | 2251 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ILLE | +2.095 |
ctions | +1.988 |
ESSION | +1.966 |
lp | +1.892 |
ned | +1.867 |
Neg logit contributions | |
�� | -2.103 |
eele | -2.082 |
ogical | -2.050 |
nature | -2.020 |
Dul | -1.952 |
Token | lambda |
Token ID | 37456 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
ILLE | +3.192 |
ctions | +3.049 |
ESSION | +3.027 |
lp | +2.913 |
ned | +2.872 |
Neg logit contributions | |
�� | -2.710 |
eele | -2.630 |
ogical | -2.563 |
nature | -2.553 |
aiman | -2.433 |
Token | functions |
Token ID | 5499 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ctions | +7.391 |
ILLE | +7.230 |
ESSION | +7.035 |
lp | +6.742 |
ned | +6.656 |
Neg logit contributions | |
�� | -6.397 |
eele | -6.054 |
nature | -5.817 |
ogical | -5.617 |
aiman | -5.604 |
Token | using |
Token ID | 1262 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ILLE | +4.075 |
ctions | +3.938 |
ESSION | +3.858 |
lp | +3.706 |
ned | +3.657 |
Neg logit contributions | |
�� | -4.155 |
eele | -4.045 |
nature | -3.943 |
ogical | -3.935 |
aiman | -3.766 |
Token | the |
Token ID | 262 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ILLE | +0.541 |
ctions | +0.514 |
ESSION | +0.512 |
lp | +0.493 |
ned | +0.486 |
Neg logit contributions | |
�� | -0.422 |
eele | -0.419 |
ogical | -0.412 |
nature | -0.405 |
Dul | -0.391 |
Token | archived |
Token ID | 33962 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ILLE | +0.676 |
ctions | +0.639 |
ESSION | +0.637 |
lp | +0.612 |
ned | +0.601 |
Neg logit contributions | |
eele | -0.609 |
�� | -0.608 |
ogical | -0.599 |
nature | -0.588 |
Dul | -0.573 |
Token | file |
Token ID | 2393 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ILLE | +0.925 |
ctions | +0.872 |
ESSION | +0.868 |
lp | +0.833 |
ned | +0.817 |
Neg logit contributions | |
�� | -0.937 |
eele | -0.934 |
ogical | -0.921 |
nature | -0.906 |
Dul | -0.881 |
Token |
|
Token ID | 198 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
eele | +1.679 |
ogical | +1.672 |
nature | +1.671 |
Sor | +1.616 |
Dul | +1.610 |
Neg logit contributions | |
ILLE | -2.055 |
ESSION | -1.938 |
ctions | -1.912 |
atown | -1.830 |
lp | -1.829 |
Token | Book |
Token ID | 10482 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
eele | +1.033 |
�� | +1.020 |
ogical | +1.020 |
nature | +1.008 |
Dul | +0.976 |
Neg logit contributions | |
ILLE | -0.954 |
ctions | -0.900 |
ESSION | -0.895 |
lp | -0.854 |
ned | -0.837 |
Token | mark |
Token ID | 4102 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
eele | +1.535 |
�� | +1.522 |
ogical | +1.507 |
nature | +1.473 |
Dul | +1.430 |
Neg logit contributions | |
ILLE | -2.278 |
ctions | -2.164 |
ESSION | -2.158 |
lp | -2.085 |
ned | -2.046 |
Token | with |
Token ID | 351 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
eele | +1.410 |
ogical | +1.386 |
�� | +1.385 |
nature | +1.376 |
Dul | +1.338 |
Neg logit contributions | |
ILLE | -1.606 |
ESSION | -1.519 |
ctions | -1.512 |
lp | -1.441 |
atown | -1.413 |
Token | : |
Token ID | 25 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
ILLE | +1.128 |
ctions | +1.082 |
ESSION | +1.061 |
lp | +1.021 |
ned | +1.005 |
Neg logit contributions | |
�� | -1.241 |
eele | -1.209 |
ogical | -1.201 |
nature | -1.180 |
Dul | -1.146 |
Token | Delicious |
Token ID | 39528 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
ILLE | +0.209 |
ESSION | +0.198 |
ctions | +0.198 |
lp | +0.192 |
ned | +0.188 |
Neg logit contributions | |
eele | -0.151 |
ogical | -0.148 |
�� | -0.146 |
nature | -0.145 |
Dul | -0.141 |
Token |
|
Token ID | 198 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
nature | +6.004 |
Dul | +5.863 |
eele | +5.660 |
ogical | +5.647 |
Sor | +5.602 |
Neg logit contributions | |
ILLE | -9.666 |
ESSION | -8.911 |
ctions | -8.803 |
lp | -8.713 |
CLE | -8.353 |
Token |
|
Token ID | 198 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
ILLE | +0.801 |
ctions | +0.755 |
ESSION | +0.752 |
lp | +0.720 |
ned | +0.705 |
Neg logit contributions | |
eele | -0.780 |
�� | -0.772 |
ogical | -0.770 |
nature | -0.759 |
Dul | -0.738 |
Token | D |
Token ID | 35 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ILLE | +2.194 |
ctions | +2.098 |
ESSION | +2.090 |
lp | +2.018 |
ned | +1.997 |
Neg logit contributions | |
�� | -1.854 |
eele | -1.802 |
ogical | -1.760 |
nature | -1.707 |
aiman | -1.678 |
Token | igg |
Token ID | 6950 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
�� | +0.605 |
eele | +0.594 |
ogical | +0.586 |
nature | +0.571 |
Dul | +0.562 |
Neg logit contributions | |
ILLE | -0.356 |
ctions | -0.330 |
ESSION | -0.326 |
lp | -0.311 |
ned | -0.308 |
Token |
|
Token ID | 198 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
eele | +0.426 |
�� | +0.424 |
ogical | +0.421 |
nature | +0.415 |
Dul | +0.406 |
Neg logit contributions | |
ILLE | -0.446 |
ctions | -0.421 |
ESSION | -0.419 |
lp | -0.401 |
ned | -0.394 |
Token | cons |
Token ID | 762 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ILLE | +0.405 |
ctions | +0.385 |
ESSION | +0.383 |
lp | +0.369 |
ned | +0.363 |
Neg logit contributions | |
eele | -0.316 |
�� | -0.316 |
ogical | -0.311 |
nature | -0.305 |
Dul | -0.296 |
Token | cript |
Token ID | 6519 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
eele | +0.519 |
�� | +0.517 |
ogical | +0.515 |
nature | +0.507 |
Dul | +0.492 |
Neg logit contributions | |
ILLE | -0.546 |
ESSION | -0.510 |
ctions | -0.508 |
lp | -0.487 |
CLE | -0.476 |
Token | ed |
Token ID | 276 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
eele | +0.448 |
�� | +0.447 |
ogical | +0.442 |
nature | +0.434 |
Dul | +0.423 |
Neg logit contributions | |
ILLE | -0.439 |
ctions | -0.414 |
ESSION | -0.412 |
lp | -0.395 |
ned | -0.387 |
Token | into |
Token ID | 656 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
eele | +1.336 |
ogical | +1.325 |
�� | +1.321 |
nature | +1.293 |
Dul | +1.270 |
Neg logit contributions | |
ILLE | -1.615 |
ESSION | -1.535 |
ctions | -1.535 |
lp | -1.469 |
CLE | -1.431 |
Token | forced |
Token ID | 4137 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
eele | +0.705 |
�� | +0.704 |
ogical | +0.693 |
nature | +0.678 |
Dul | +0.658 |
Neg logit contributions | |
ILLE | -1.013 |
ctions | -0.964 |
ESSION | -0.960 |
lp | -0.927 |
ned | -0.912 |
Token | labour |
Token ID | 10515 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
eele | +0.413 |
�� | +0.411 |
ogical | +0.404 |
nature | +0.392 |
Dul | +0.376 |
Neg logit contributions | |
ILLE | -0.950 |
ctions | -0.911 |
ESSION | -0.909 |
lp | -0.882 |
ned | -0.871 |
Token | in |
Token ID | 287 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ogical | +6.091 |
Sor | +5.791 |
nature | +5.767 |
Dul | +5.744 |
eele | +5.725 |
Neg logit contributions | |
ILLE | -9.082 |
ESSION | -8.842 |
ctions | -8.655 |
lp | -8.391 |
atown | -8.242 |
Token | Germany |
Token ID | 4486 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
eele | +0.999 |
�� | +0.994 |
ogical | +0.983 |
nature | +0.960 |
Dul | +0.940 |
Neg logit contributions | |
ILLE | -1.455 |
ctions | -1.388 |
ESSION | -1.385 |
lp | -1.334 |
ned | -1.309 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
eele | +2.143 |
ogical | +2.125 |
�� | +2.118 |
nature | +2.078 |
Dul | +2.029 |
Neg logit contributions | |
ILLE | -2.751 |
ESSION | -2.608 |
ctions | -2.595 |
lp | -2.501 |
CLE | -2.442 |
Token | few |
Token ID | 1178 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
eele | +0.253 |
�� | +0.253 |
ogical | +0.249 |
nature | +0.244 |
Dul | +0.236 |
Neg logit contributions | |
ILLE | -0.357 |
ctions | -0.339 |
ESSION | -0.338 |
lp | -0.326 |
ned | -0.321 |
Token | wanted |
Token ID | 2227 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
ILLE | +2.853 |
ctions | +2.707 |
ESSION | +2.677 |
ned | +2.606 |
lp | +2.581 |
Neg logit contributions | |
�� | -2.300 |
eele | -2.268 |
nature | -2.205 |
ogical | -2.203 |
aiman | -2.084 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
ILLE | +0.918 |
ctions | +0.866 |
ESSION | +0.861 |
lp | +0.834 |
ned | +0.821 |
Neg logit contributions | |
�� | -0.810 |
eele | -0.801 |
ogical | -0.794 |
nature | -0.776 |
Dul | -0.750 |
Token | warns |
Token ID | 22145 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ILLE | +0.719 |
ctions | +0.682 |
ESSION | +0.678 |
lp | +0.653 |
ned | +0.643 |
Neg logit contributions | |
�� | -0.613 |
eele | -0.612 |
ogical | -0.602 |
nature | -0.591 |
Dul | -0.574 |
Token | a |
Token ID | 257 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ogical | +3.327 |
eele | +3.322 |
�� | +3.247 |
Dul | +3.220 |
nature | +3.206 |
Neg logit contributions | |
ILLE | -4.594 |
ctions | -4.341 |
ESSION | -4.290 |
lp | -4.127 |
CLE | -4.043 |
Token | room |
Token ID | 2119 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ILLE | +0.592 |
ctions | +0.559 |
ESSION | +0.558 |
lp | +0.535 |
ned | +0.526 |
Neg logit contributions | |
eele | -0.535 |
�� | -0.535 |
ogical | -0.527 |
nature | -0.517 |
Dul | -0.504 |
Token | of |
Token ID | 286 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
ILLE | +0.608 |
ctions | +0.575 |
ESSION | +0.572 |
lp | +0.550 |
ned | +0.541 |
Neg logit contributions | |
eele | -0.569 |
�� | -0.568 |
ogical | -0.560 |
nature | -0.550 |
Dul | -0.535 |
Token | rapt |
Token ID | 38404 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
ILLE | +0.287 |
ctions | +0.272 |
ESSION | +0.271 |
lp | +0.260 |
ned | +0.255 |
Neg logit contributions | |
eele | -0.251 |
�� | -0.250 |
ogical | -0.248 |
nature | -0.242 |
Dul | -0.237 |
Token | students |
Token ID | 2444 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ogical | +6.571 |
eele | +6.352 |
�� | +6.320 |
Dul | +6.234 |
nature | +6.191 |
Neg logit contributions | |
ILLE | -8.438 |
ctions | -8.038 |
ESSION | -7.853 |
lp | -7.680 |
atown | -7.468 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
eele | +2.331 |
ogical | +2.330 |
�� | +2.290 |
nature | +2.258 |
Dul | +2.243 |
Neg logit contributions | |
ILLE | -3.149 |
ESSION | -2.981 |
ctions | -2.975 |
lp | -2.843 |
atown | -2.783 |
Token | be |
Token ID | 307 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ILLE | +0.355 |
ctions | +0.337 |
ESSION | +0.335 |
lp | +0.323 |
ned | +0.318 |
Neg logit contributions | |
�� | -0.292 |
eele | -0.292 |
ogical | -0.287 |
nature | -0.281 |
Dul | -0.273 |
Token | mindful |
Token ID | 33798 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ILLE | +0.352 |
ctions | +0.333 |
ESSION | +0.332 |
lp | +0.318 |
ned | +0.312 |
Neg logit contributions | |
eele | -0.328 |
�� | -0.327 |
ogical | -0.324 |
nature | -0.318 |
Dul | -0.310 |
Token | of |
Token ID | 286 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ILLE | +1.317 |
ctions | +1.259 |
ESSION | +1.252 |
lp | +1.204 |
ned | +1.194 |
Neg logit contributions | |
eele | -1.074 |
�� | -1.074 |
ogical | -1.040 |
nature | -1.026 |
Dul | -0.994 |
Token | and |
Token ID | 290 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
�� | +0.005 |
eele | +0.005 |
ogical | +0.004 |
nature | +0.004 |
Dul | +0.004 |
Neg logit contributions | |
ILLE | -0.006 |
ctions | -0.005 |
ESSION | -0.005 |
lp | -0.005 |
ned | -0.005 |
Token | Strategy |
Token ID | 20561 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
ILLE | +0.295 |
ctions | +0.281 |
ESSION | +0.279 |
lp | +0.269 |
ned | +0.265 |
Neg logit contributions | |
�� | -0.238 |
eele | -0.237 |
ogical | -0.233 |
nature | -0.229 |
Dul | -0.221 |
Token | Justin |
Token ID | 10799 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ILLE | +0.387 |
ctions | +0.370 |
ESSION | +0.367 |
lp | +0.354 |
ned | +0.351 |
Neg logit contributions | |
�� | -0.299 |
eele | -0.296 |
ogical | -0.292 |
nature | -0.286 |
Dul | -0.275 |
Token | Reid |
Token ID | 16095 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
eele | +2.523 |
�� | +2.501 |
ogical | +2.477 |
nature | +2.417 |
Dul | +2.413 |
Neg logit contributions | |
ILLE | -3.496 |
ESSION | -3.331 |
ctions | -3.295 |
lp | -3.183 |
CLE | -3.106 |
Token | was |
Token ID | 373 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
ILLE | +0.144 |
ctions | +0.136 |
ESSION | +0.136 |
lp | +0.131 |
ned | +0.129 |
Neg logit contributions | |
�� | -0.119 |
eele | -0.119 |
ogical | -0.117 |
nature | -0.115 |
Dul | -0.111 |
Token | rapt |
Token ID | 38404 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
eele | +0.147 |
�� | +0.147 |
ogical | +0.145 |
nature | +0.142 |
Dul | +0.139 |
Neg logit contributions | |
ILLE | -0.191 |
ctions | -0.182 |
ESSION | -0.181 |
lp | -0.174 |
ned | -0.171 |
Token | Mc |
Token ID | 1982 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ogical | +6.228 |
eele | +6.045 |
�� | +5.970 |
Dul | +5.860 |
nature | +5.793 |
Neg logit contributions | |
ILLE | -8.609 |
ctions | -8.278 |
ESSION | -8.086 |
lp | -7.818 |
atown | -7.755 |
Token | Govern |
Token ID | 29168 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
ILLE | +3.861 |
ctions | +3.662 |
ESSION | +3.610 |
lp | +3.492 |
ned | +3.458 |
Neg logit contributions | |
�� | -4.649 |
eele | -4.553 |
ogical | -4.519 |
nature | -4.381 |
Dul | -4.272 |
Token | had |
Token ID | 550 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ILLE | +1.197 |
ctions | +1.136 |
ESSION | +1.128 |
lp | +1.089 |
ned | +1.075 |
Neg logit contributions | |
�� | -1.018 |
eele | -1.009 |
ogical | -0.995 |
nature | -0.974 |
Dul | -0.944 |
Token | committed |
Token ID | 5364 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
eele | +0.435 |
�� | +0.433 |
ogical | +0.429 |
nature | +0.419 |
Dul | +0.409 |
Neg logit contributions | |
ILLE | -0.571 |
ctions | -0.542 |
ESSION | -0.541 |
lp | -0.521 |
ned | -0.511 |
Token | to |
Token ID | 284 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
eele | +1.913 |
�� | +1.895 |
ogical | +1.879 |
nature | +1.838 |
Dul | +1.802 |
Neg logit contributions | |
ILLE | -2.577 |
ctions | -2.452 |
ESSION | -2.448 |
lp | -2.359 |
ned | -2.309 |
Token | ouch |
Token ID | 7673 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
eele | +2.145 |
ogical | +2.107 |
�� | +2.083 |
nature | +2.046 |
aiman | +2.000 |
Neg logit contributions | |
ILLE | -2.416 |
ESSION | -2.277 |
ctions | -2.275 |
lp | -2.170 |
CLE | -2.144 |
Token | ard |
Token ID | 446 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
eele | +0.133 |
�� | +0.132 |
ogical | +0.131 |
nature | +0.128 |
Dul | +0.125 |
Neg logit contributions | |
ILLE | -0.150 |
ctions | -0.142 |
ESSION | -0.141 |
lp | -0.135 |
ned | -0.133 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
eele | +1.060 |
�� | +1.052 |
ogical | +1.043 |
nature | +1.022 |
Dul | +0.999 |
Neg logit contributions | |
ILLE | -1.300 |
ESSION | -1.230 |
ctions | -1.228 |
lp | -1.176 |
ned | -1.155 |
Token | a |
Token ID | 257 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
�� | +0.413 |
eele | +0.412 |
ogical | +0.405 |
nature | +0.397 |
Dul | +0.383 |
Neg logit contributions | |
ILLE | -0.578 |
ctions | -0.550 |
ESSION | -0.548 |
lp | -0.529 |
ned | -0.521 |
Token | post |
Token ID | 1281 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
eele | +0.484 |
�� | +0.478 |
ogical | +0.475 |
nature | +0.464 |
Dul | +0.454 |
Neg logit contributions | |
ILLE | -0.688 |
ESSION | -0.655 |
ctions | -0.651 |
lp | -0.627 |
ned | -0.617 |
Token | doctoral |
Token ID | 44064 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
ILLE | +1.123 |
ctions | +1.059 |
ESSION | +1.049 |
lp | +1.010 |
ned | +0.998 |
Neg logit contributions | |
�� | -1.306 |
eele | -1.281 |
ogical | -1.263 |
nature | -1.242 |
aiman | -1.216 |
Token | fellow |
Token ID | 5891 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
ogical | +5.797 |
eele | +5.720 |
Sor | +5.519 |
Mou | +5.510 |
nature | +5.503 |
Neg logit contributions | |
ILLE | -9.080 |
ESSION | -8.505 |
ctions | -8.418 |
atown | -8.170 |
CLE | -8.089 |
Token | in |
Token ID | 287 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
eele | +2.081 |
�� | +2.077 |
ogical | +2.061 |
nature | +2.012 |
Dul | +1.967 |
Neg logit contributions | |
ILLE | -3.040 |
ESSION | -2.875 |
ctions | -2.857 |
lp | -2.757 |
CLE | -2.700 |
Token | Chang |
Token ID | 22597 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
eele | +0.813 |
�� | +0.812 |
ogical | +0.796 |
nature | +0.776 |
Dul | +0.747 |
Neg logit contributions | |
ILLE | -1.513 |
ctions | -1.447 |
ESSION | -1.442 |
lp | -1.397 |
ned | -1.378 |
Token | � |
Token ID | 447 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ILLE | +0.310 |
ctions | +0.297 |
ESSION | +0.292 |
lp | +0.280 |
ned | +0.278 |
Neg logit contributions | |
eele | -0.314 |
�� | -0.313 |
ogical | -0.310 |
nature | -0.303 |
Dul | -0.294 |
Token | � |
Token ID | 247 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
�� | +0.481 |
eele | +0.479 |
ogical | +0.475 |
nature | +0.470 |
Dul | +0.460 |
Neg logit contributions | |
ILLE | -0.234 |
ESSION | -0.214 |
ctions | -0.213 |
lp | -0.198 |
ned | -0.193 |
Token |
|
Token ID | 198 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
nature | +1.425 |
eele | +1.424 |
ogical | +1.423 |
Sor | +1.375 |
Dul | +1.369 |
Neg logit contributions | |
ILLE | -1.734 |
ESSION | -1.638 |
ctions | -1.624 |
lp | -1.550 |
atown | -1.548 |
Token | Book |
Token ID | 10482 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
eele | +0.700 |
ogical | +0.695 |
�� | +0.691 |
nature | +0.689 |
Dul | +0.664 |
Neg logit contributions | |
ILLE | -0.622 |
ctions | -0.589 |
ESSION | -0.585 |
lp | -0.556 |
ned | -0.544 |
Token | mark |
Token ID | 4102 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
eele | +1.764 |
�� | +1.751 |
ogical | +1.742 |
nature | +1.704 |
Dul | +1.659 |
Neg logit contributions | |
ILLE | -2.474 |
ctions | -2.344 |
ESSION | -2.335 |
lp | -2.256 |
ned | -2.206 |
Token | with |
Token ID | 351 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
eele | +1.081 |
�� | +1.069 |
ogical | +1.067 |
nature | +1.058 |
Dul | +1.028 |
Neg logit contributions | |
ILLE | -1.241 |
ESSION | -1.174 |
ctions | -1.168 |
lp | -1.111 |
atown | -1.089 |
Token | : |
Token ID | 25 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ILLE | +1.318 |
ctions | +1.259 |
ESSION | +1.240 |
lp | +1.191 |
ned | +1.170 |
Neg logit contributions | |
�� | -1.406 |
eele | -1.381 |
ogical | -1.365 |
nature | -1.342 |
Dul | -1.306 |
Token | Delicious |
Token ID | 39528 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
ILLE | +0.647 |
ctions | +0.611 |
ESSION | +0.611 |
lp | +0.591 |
ned | +0.580 |
Neg logit contributions | |
eele | -0.477 |
ogical | -0.468 |
�� | -0.467 |
nature | -0.457 |
Dul | -0.446 |
Token |
|
Token ID | 198 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
nature | +5.741 |
Dul | +5.591 |
ogical | +5.470 |
eele | +5.420 |
Sor | +5.368 |
Neg logit contributions | |
ILLE | -9.204 |
ESSION | -8.436 |
ctions | -8.370 |
lp | -8.304 |
atown | -7.943 |
Token |
|
Token ID | 198 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
ILLE | +0.580 |
ctions | +0.546 |
ESSION | +0.545 |
lp | +0.522 |
ned | +0.510 |
Neg logit contributions | |
eele | -0.555 |
ogical | -0.548 |
�� | -0.546 |
nature | -0.541 |
Dul | -0.526 |
Token | D |
Token ID | 35 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ILLE | +1.971 |
ctions | +1.887 |
ESSION | +1.878 |
lp | +1.808 |
ned | +1.796 |
Neg logit contributions | |
�� | -1.669 |
eele | -1.619 |
ogical | -1.581 |
nature | -1.534 |
aiman | -1.509 |
Token | igg |
Token ID | 6950 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
�� | +0.832 |
eele | +0.824 |
ogical | +0.813 |
nature | +0.796 |
Dul | +0.783 |
Neg logit contributions | |
ILLE | -0.525 |
ctions | -0.488 |
ESSION | -0.483 |
lp | -0.459 |
ned | -0.451 |
Token |
|
Token ID | 198 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
eele | +0.583 |
�� | +0.582 |
ogical | +0.576 |
nature | +0.567 |
Dul | +0.554 |
Neg logit contributions | |
ILLE | -0.600 |
ctions | -0.566 |
ESSION | -0.564 |
lp | -0.540 |
ned | -0.530 |
Token | D |
Token ID | 35 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
eele | +0.581 |
nature | +0.579 |
ogical | +0.565 |
�� | +0.558 |
Dul | +0.551 |
Neg logit contributions | |
ILLE | -1.004 |
ctions | -0.964 |
ESSION | -0.941 |
atown | -0.924 |
ned | -0.924 |
Token | rey |
Token ID | 4364 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
eele | +1.017 |
ogical | +1.003 |
nature | +0.974 |
�� | +0.960 |
Mou | +0.950 |
Neg logit contributions | |
ILLE | -1.476 |
ctions | -1.411 |
ESSION | -1.399 |
lp | -1.358 |
CLE | -1.343 |
Token | f |
Token ID | 69 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
ILLE | +1.933 |
ctions | +1.840 |
ESSION | +1.792 |
lp | +1.777 |
ned | +1.732 |
Neg logit contributions | |
�� | -1.756 |
eele | -1.709 |
ogical | -1.683 |
nature | -1.577 |
agine | -1.570 |
Token | us |
Token ID | 385 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
ILLE | +2.328 |
ctions | +2.222 |
ESSION | +2.214 |
lp | +2.140 |
ned | +2.113 |
Neg logit contributions | |
�� | -1.481 |
eele | -1.468 |
ogical | -1.426 |
nature | -1.409 |
Dul | -1.353 |
Token | Ve |
Token ID | 8016 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
eele | +0.077 |
�� | +0.076 |
ogical | +0.075 |
nature | +0.074 |
Dul | +0.072 |
Neg logit contributions | |
ILLE | -0.099 |
ctions | -0.094 |
ESSION | -0.094 |
lp | -0.091 |
ned | -0.089 |
Token | ep |
Token ID | 538 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
ILLE | +0.380 |
ESSION | +0.345 |
ctions | +0.343 |
lp | +0.320 |
ned | +0.310 |
Neg logit contributions | |
eele | -0.879 |
�� | -0.873 |
ogical | -0.872 |
nature | -0.859 |
Dul | -0.848 |
Token | HBO |
Token ID | 18804 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
Mou | +6.218 |
Dul | +6.201 |
eele | +6.173 |
Sor | +6.154 |
nature | +5.940 |
Neg logit contributions | |
ILLE | -8.538 |
ctions | -8.079 |
ESSION | -8.024 |
lp | -7.795 |
atown | -7.529 |
Token | Jim |
Token ID | 5395 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
eele | +2.096 |
ogical | +2.057 |
nature | +2.036 |
Dul | +2.034 |
Sor | +2.028 |
Neg logit contributions | |
ILLE | -2.673 |
ctions | -2.538 |
ESSION | -2.525 |
lp | -2.430 |
ned | -2.368 |
Token | Parsons |
Token ID | 35925 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ILLE | +2.039 |
ctions | +1.951 |
ESSION | +1.935 |
lp | +1.870 |
ned | +1.845 |
Neg logit contributions | |
�� | -1.505 |
eele | -1.474 |
ogical | -1.449 |
nature | -1.414 |
aiman | -1.357 |
Token | The |
Token ID | 383 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
eele | +2.387 |
ogical | +2.304 |
Dul | +2.303 |
Mou | +2.301 |
nature | +2.292 |
Neg logit contributions | |
ILLE | -3.105 |
ctions | -2.930 |
ESSION | -2.913 |
lp | -2.820 |
atown | -2.731 |
Token | Big |
Token ID | 4403 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ILLE | +0.929 |
ctions | +0.885 |
ESSION | +0.881 |
lp | +0.850 |
ned | +0.837 |
Neg logit contributions | |
�� | -0.720 |
eele | -0.714 |
ogical | -0.704 |
nature | -0.690 |
Dul | -0.665 |
Token | , |
Token ID | 11 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
�� | +1.522 |
eele | +1.521 |
ogical | +1.502 |
nature | +1.471 |
Dul | +1.436 |
Neg logit contributions | |
ILLE | -1.936 |
ctions | -1.835 |
ESSION | -1.832 |
lp | -1.765 |
ned | -1.731 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ILLE | +0.215 |
ctions | +0.205 |
ESSION | +0.204 |
lp | +0.196 |
ned | +0.194 |
Neg logit contributions | |
�� | -0.157 |
eele | -0.157 |
ogical | -0.154 |
nature | -0.150 |
Dul | -0.145 |
Token | life |
Token ID | 1204 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
eele | +0.027 |
�� | +0.027 |
ogical | +0.026 |
nature | +0.026 |
Dul | +0.025 |
Neg logit contributions | |
ILLE | -0.033 |
ctions | -0.032 |
ESSION | -0.032 |
lp | -0.030 |
ned | -0.030 |
Token | could |
Token ID | 714 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
eele | +0.619 |
�� | +0.618 |
ogical | +0.609 |
nature | +0.597 |
Dul | +0.580 |
Neg logit contributions | |
ILLE | -0.821 |
ctions | -0.780 |
ESSION | -0.777 |
lp | -0.749 |
ned | -0.737 |
Token | never |
Token ID | 1239 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
eele | +1.475 |
�� | +1.468 |
ogical | +1.462 |
nature | +1.430 |
Dul | +1.380 |
Neg logit contributions | |
ILLE | -2.168 |
ESSION | -2.061 |
ctions | -2.048 |
lp | -1.972 |
CLE | -1.927 |
Token | quite |
Token ID | 2407 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
eele | +0.233 |
�� | +0.233 |
ogical | +0.229 |
nature | +0.225 |
Dul | +0.219 |
Neg logit contributions | |
ILLE | -0.286 |
ctions | -0.271 |
ESSION | -0.270 |
lp | -0.260 |
ned | -0.256 |
Token | match |
Token ID | 2872 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ogical | +5.797 |
eele | +5.742 |
nature | +5.618 |
Dul | +5.617 |
Tolkien | +5.527 |
Neg logit contributions | |
ILLE | -8.540 |
ESSION | -8.186 |
ctions | -7.834 |
lp | -7.499 |
INST | -7.395 |
Token | the |
Token ID | 262 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
eele | +2.687 |
ogical | +2.668 |
�� | +2.649 |
nature | +2.647 |
Dul | +2.584 |
Neg logit contributions | |
ILLE | -4.319 |
ctions | -4.110 |
ESSION | -4.096 |
lp | -3.969 |
CLE | -3.880 |
Token | intensity |
Token ID | 12245 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
eele | +0.548 |
�� | +0.544 |
ogical | +0.540 |
nature | +0.529 |
Dul | +0.516 |
Neg logit contributions | |
ILLE | -0.760 |
ctions | -0.722 |
ESSION | -0.722 |
lp | -0.695 |
ned | -0.683 |
Token | of |
Token ID | 286 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
ILLE | +0.737 |
ctions | +0.698 |
ESSION | +0.693 |
lp | +0.668 |
ned | +0.663 |
Neg logit contributions | |
eele | -0.610 |
�� | -0.610 |
ogical | -0.596 |
nature | -0.586 |
Dul | -0.566 |
Token | the |
Token ID | 262 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
eele | +0.078 |
�� | +0.078 |
ogical | +0.077 |
nature | +0.075 |
Dul | +0.073 |
Neg logit contributions | |
ILLE | -0.118 |
ctions | -0.113 |
ESSION | -0.112 |
lp | -0.109 |
ned | -0.107 |
Token | pi |
Token ID | 31028 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
eele | +2.745 |
ogical | +2.721 |
�� | +2.705 |
nature | +2.657 |
Dul | +2.607 |
Neg logit contributions | |
ILLE | -2.921 |
ESSION | -2.793 |
ctions | -2.748 |
lp | -2.585 |
CLE | -2.572 |
Token | ha |
Token ID | 3099 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
eele | +1.197 |
�� | +1.187 |
ogical | +1.183 |
nature | +1.153 |
Dul | +1.132 |
Neg logit contributions | |
ILLE | -1.319 |
ESSION | -1.242 |
ctions | -1.238 |
lp | -1.181 |
ned | -1.161 |
Token | a |
Token ID | 257 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
eele | +0.842 |
�� | +0.836 |
ogical | +0.832 |
nature | +0.814 |
Dul | +0.799 |
Neg logit contributions | |
ILLE | -0.889 |
ESSION | -0.840 |
ctions | -0.839 |
lp | -0.797 |
ned | -0.784 |
Token | i |
Token ID | 72 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
eele | +1.274 |
�� | +1.267 |
ogical | +1.258 |
nature | +1.234 |
Dul | +1.213 |
Neg logit contributions | |
ILLE | -1.310 |
ESSION | -1.243 |
ctions | -1.234 |
lp | -1.169 |
CLE | -1.149 |
Token | Ka |
Token ID | 11611 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
eele | +1.092 |
�� | +1.081 |
ogical | +1.078 |
nature | +1.055 |
Dul | +1.039 |
Neg logit contributions | |
ILLE | -1.160 |
ESSION | -1.096 |
ctions | -1.093 |
lp | -1.040 |
ned | -1.020 |
Token | Pap |
Token ID | 14185 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
eele | +3.243 |
ogical | +3.242 |
�� | +3.217 |
nature | +3.121 |
Dul | +3.113 |
Neg logit contributions | |
ILLE | -3.190 |
ESSION | -3.027 |
ctions | -3.017 |
lp | -2.815 |
CLE | -2.774 |
Token | ah |
Token ID | 993 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ogical | +6.708 |
eele | +6.695 |
�� | +6.519 |
nature | +6.485 |
aiman | +6.453 |
Neg logit contributions | |
ILLE | -7.022 |
ESSION | -6.682 |
ctions | -6.572 |
CLE | -6.154 |
IDENT | -6.004 |
Token | ana |
Token ID | 2271 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ILLE | +0.808 |
ctions | +0.764 |
ESSION | +0.761 |
lp | +0.733 |
ned | +0.721 |
Neg logit contributions | |
�� | -0.711 |
eele | -0.710 |
ogical | -0.699 |
nature | -0.687 |
Dul | -0.667 |
Token | Kai |
Token ID | 22091 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
ILLE | +2.934 |
ctions | +2.779 |
ESSION | +2.742 |
lp | +2.690 |
ned | +2.646 |
Neg logit contributions | |
�� | -2.681 |
eele | -2.649 |
ogical | -2.592 |
nature | -2.563 |
aiman | -2.456 |
Token | ap |
Token ID | 499 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
eele | +2.639 |
�� | +2.627 |
ogical | +2.622 |
nature | +2.568 |
Dul | +2.537 |
Neg logit contributions | |
ILLE | -1.792 |
ESSION | -1.663 |
ctions | -1.654 |
lp | -1.535 |
ned | -1.522 |
Token | uni |
Token ID | 35657 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
eele | +1.306 |
�� | +1.296 |
ogical | +1.289 |
nature | +1.261 |
Dul | +1.224 |
Neg logit contributions | |
ILLE | -1.788 |
ESSION | -1.696 |
ctions | -1.690 |
lp | -1.620 |
CLE | -1.596 |
Token | . |
Token ID | 13 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
eele | +1.008 |
ogical | +1.000 |
�� | +0.996 |
nature | +0.977 |
Dul | +0.959 |
Neg logit contributions | |
ILLE | -1.274 |
ctions | -1.205 |
ESSION | -1.202 |
lp | -1.153 |
CLE | -1.125 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ILLE | +0.130 |
ctions | +0.122 |
ESSION | +0.122 |
lp | +0.117 |
ned | +0.115 |
Neg logit contributions | |
eele | -0.118 |
�� | -0.117 |
ogical | -0.116 |
nature | -0.114 |
Dul | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
eele | +0.447 |
ogical | +0.444 |
nature | +0.439 |
�� | +0.433 |
Dul | +0.425 |
Neg logit contributions | |
ILLE | -0.495 |
ESSION | -0.465 |
ctions | -0.463 |
lp | -0.442 |
atown | -0.435 |
Token | I |
Token ID | 40 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
ILLE | +0.436 |
ctions | +0.409 |
ESSION | +0.406 |
lp | +0.387 |
ned | +0.379 |
Neg logit contributions | |
eele | -0.524 |
�� | -0.522 |
ogical | -0.518 |
nature | -0.511 |
Dul | -0.498 |
Token | van |
Token ID | 10438 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
ILLE | +1.907 |
ctions | +1.812 |
ESSION | +1.797 |
lp | +1.739 |
ned | +1.718 |
Neg logit contributions | |
�� | -1.779 |
eele | -1.758 |
ogical | -1.722 |
nature | -1.683 |
Dul | -1.635 |
Token | Nep |
Token ID | 15310 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ILLE | +2.227 |
ctions | +2.138 |
ESSION | +2.107 |
lp | +2.043 |
ned | +2.034 |
Neg logit contributions | |
�� | -1.616 |
eele | -1.599 |
ogical | -1.551 |
nature | -1.532 |
Dul | -1.450 |
Token | om |
Token ID | 296 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
eele | +6.901 |
ogical | +6.724 |
aiman | +6.655 |
agine | +6.598 |
nature | +6.564 |
Neg logit contributions | |
ILLE | -7.054 |
ESSION | -6.616 |
ctions | -6.167 |
CLE | -5.968 |
IDENT | -5.933 |
Token | ny |
Token ID | 3281 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
eele | +1.228 |
ogical | +1.217 |
�� | +1.206 |
nature | +1.200 |
Dul | +1.168 |
Neg logit contributions | |
ILLE | -1.050 |
ESSION | -0.980 |
ctions | -0.962 |
lp | -0.906 |
CLE | -0.895 |
Token | ash |
Token ID | 1077 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ILLE | +1.030 |
ctions | +0.979 |
ESSION | +0.965 |
lp | +0.940 |
ned | +0.922 |
Neg logit contributions | |
�� | -0.974 |
eele | -0.962 |
ogical | -0.947 |
nature | -0.930 |
Dul | -0.902 |
Token | ch |
Token ID | 354 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
ILLE | +0.537 |
ctions | +0.509 |
ESSION | +0.504 |
lp | +0.486 |
ned | +0.478 |
Neg logit contributions | |
�� | -0.534 |
eele | -0.532 |
ogical | -0.524 |
nature | -0.514 |
Dul | -0.502 |
Token | ikh |
Token ID | 13848 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
ILLE | +1.476 |
ctions | +1.405 |
ESSION | +1.389 |
lp | +1.344 |
ned | +1.327 |
Neg logit contributions | |
�� | -1.378 |
eele | -1.364 |
ogical | -1.340 |
nature | -1.310 |
Dul | -1.282 |
Token | . |
Token ID | 13 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
ILLE | +0.159 |
ctions | +0.151 |
ESSION | +0.150 |
lp | +0.144 |
ned | +0.142 |
Neg logit contributions | |
eele | -0.138 |
�� | -0.138 |
ogical | -0.136 |
nature | -0.134 |
Dul | -0.130 |
Token | It |
Token ID | 632 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ILLE | +0.211 |
ctions | +0.200 |
ESSION | +0.199 |
lp | +0.191 |
ned | +0.187 |
Neg logit contributions | |
eele | -0.195 |
�� | -0.194 |
ogical | -0.192 |
nature | -0.189 |
Dul | -0.185 |
Token | reminds |
Token ID | 17603 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
eele | +0.312 |
�� | +0.310 |
ogical | +0.308 |
nature | +0.303 |
Dul | +0.294 |
Neg logit contributions | |
ILLE | -0.365 |
ESSION | -0.345 |
ctions | -0.344 |
lp | -0.329 |
ned | -0.323 |
Token | us |
Token ID | 514 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
eele | +1.876 |
�� | +1.868 |
ogical | +1.858 |
nature | +1.829 |
Dul | +1.773 |
Neg logit contributions | |
ILLE | -2.420 |
ctions | -2.295 |
ESSION | -2.290 |
lp | -2.199 |
ned | -2.153 |
Token | how |
Token ID | 703 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ILLE | +0.812 |
ctions | +0.771 |
ESSION | +0.765 |
lp | +0.740 |
ned | +0.733 |
Neg logit contributions | |
�� | -0.672 |
eele | -0.670 |
ogical | -0.657 |
nature | -0.643 |
Dul | -0.622 |
Token | precious |
Token ID | 14186 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ILLE | +0.701 |
ctions | +0.666 |
ESSION | +0.662 |
lp | +0.640 |
ned | +0.632 |
Neg logit contributions | |
�� | -0.542 |
eele | -0.538 |
ogical | -0.525 |
nature | -0.515 |
Dul | -0.499 |
Token | this |
Token ID | 428 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ogical | +5.449 |
nature | +5.418 |
eele | +5.144 |
Sor | +5.137 |
Dul | +5.133 |
Neg logit contributions | |
ILLE | -8.358 |
ctions | -7.797 |
ESSION | -7.725 |
lp | -7.378 |
atown | -7.331 |
Token | resource |
Token ID | 8271 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ogical | +2.572 |
eele | +2.557 |
nature | +2.502 |
�� | +2.501 |
Dul | +2.448 |
Neg logit contributions | |
ILLE | -3.530 |
ESSION | -3.332 |
ctions | -3.321 |
lp | -3.187 |
ned | -3.135 |
Token | is |
Token ID | 318 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
�� | +0.445 |
eele | +0.443 |
ogical | +0.432 |
nature | +0.425 |
Dul | +0.412 |
Neg logit contributions | |
ILLE | -0.553 |
ctions | -0.526 |
ESSION | -0.525 |
lp | -0.505 |
ned | -0.500 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
eele | +1.225 |
ogical | +1.218 |
�� | +1.216 |
nature | +1.194 |
Dul | +1.156 |
Neg logit contributions | |
ILLE | -1.486 |
ctions | -1.400 |
ESSION | -1.398 |
lp | -1.344 |
ned | -1.313 |
Token | and |
Token ID | 290 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
eele | +0.269 |
�� | +0.269 |
ogical | +0.266 |
nature | +0.261 |
Dul | +0.253 |
Neg logit contributions | |
ILLE | -0.311 |
ctions | -0.294 |
ESSION | -0.293 |
lp | -0.281 |
ned | -0.277 |
Token | igraph |
Token ID | 45920 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
eele | +3.279 |
�� | +3.265 |
ogical | +3.261 |
nature | +3.168 |
Dul | +3.076 |
Neg logit contributions | |
ILLE | -4.696 |
ESSION | -4.442 |
ctions | -4.409 |
lp | -4.241 |
ned | -4.173 |
Token | from |
Token ID | 422 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ogical | +1.512 |
eele | +1.511 |
�� | +1.502 |
nature | +1.460 |
Dul | +1.427 |
Neg logit contributions | |
ILLE | -1.882 |
ESSION | -1.772 |
ctions | -1.763 |
lp | -1.702 |
ned | -1.666 |
Token | the |
Token ID | 262 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
�� | +0.736 |
eele | +0.734 |
ogical | +0.720 |
nature | +0.704 |
Dul | +0.679 |
Neg logit contributions | |
ILLE | -1.165 |
ctions | -1.112 |
ESSION | -1.107 |
lp | -1.071 |
ned | -1.056 |
Token | Greek |
Token ID | 8312 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
eele | +0.465 |
�� | +0.464 |
ogical | +0.457 |
nature | +0.448 |
Dul | +0.435 |
Neg logit contributions | |
ILLE | -0.631 |
ctions | -0.599 |
ESSION | -0.597 |
lp | -0.576 |
ned | -0.567 |
Token | historian |
Token ID | 18026 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
ogical | +2.684 |
eele | +2.682 |
�� | +2.639 |
nature | +2.608 |
Dul | +2.565 |
Neg logit contributions | |
ILLE | -3.748 |
ESSION | -3.520 |
ctions | -3.514 |
lp | -3.394 |
CLE | -3.307 |
Token | Herod |
Token ID | 48084 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
eele | +1.074 |
�� | +1.069 |
ogical | +1.062 |
nature | +1.039 |
Dul | +1.011 |
Neg logit contributions | |
ILLE | -1.579 |
ctions | -1.500 |
ESSION | -1.496 |
lp | -1.443 |
ned | -1.422 |
Token | ot |
Token ID | 313 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
ogical | +4.961 |
eele | +4.762 |
Sor | +4.743 |
nature | +4.694 |
Dul | +4.691 |
Neg logit contributions | |
ILLE | -8.806 |
ctions | -8.277 |
ESSION | -8.138 |
lp | -7.867 |
CLE | -7.770 |
Token | us |
Token ID | 385 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ILLE | +1.224 |
ctions | +1.169 |
ESSION | +1.164 |
lp | +1.133 |
ned | +1.115 |
Neg logit contributions | |
�� | -0.796 |
eele | -0.777 |
ogical | -0.763 |
nature | -0.746 |
Dul | -0.720 |
Token | begins |
Token ID | 6140 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
eele | +2.400 |
ogical | +2.383 |
�� | +2.338 |
nature | +2.315 |
Dul | +2.295 |
Neg logit contributions | |
ILLE | -3.098 |
ESSION | -2.930 |
ctions | -2.899 |
lp | -2.791 |
ned | -2.736 |
Token | the |
Token ID | 262 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ILLE | +0.795 |
ctions | +0.757 |
ESSION | +0.753 |
lp | +0.726 |
ned | +0.721 |
Neg logit contributions | |
�� | -0.669 |
eele | -0.668 |
ogical | -0.651 |
nature | -0.645 |
Dul | -0.616 |
Token | Australian |
Token ID | 6638 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
ILLE | +1.322 |
ctions | +1.258 |
ESSION | +1.246 |
lp | +1.204 |
ned | +1.194 |
Neg logit contributions | |
�� | -1.038 |
eele | -1.033 |
ogical | -1.012 |
nature | -0.997 |
Dul | -0.960 |
Token | bon |
Token ID | 5351 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
ILLE | +0.206 |
ESSION | +0.196 |
ctions | +0.196 |
lp | +0.188 |
ned | +0.186 |
Neg logit contributions | |
eele | -0.143 |
�� | -0.143 |
ogical | -0.141 |
nature | -0.138 |
Dul | -0.134 |
Token | o |
Token ID | 78 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
eele | +2.415 |
�� | +2.406 |
ogical | +2.379 |
nature | +2.333 |
Dul | +2.267 |
Neg logit contributions | |
ILLE | -2.942 |
ctions | -2.785 |
ESSION | -2.782 |
lp | -2.673 |
ned | -2.628 |
Token | : |
Token ID | 25 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
eele | +1.893 |
ogical | +1.891 |
�� | +1.854 |
nature | +1.829 |
Dul | +1.797 |
Neg logit contributions | |
ILLE | -2.137 |
ESSION | -2.035 |
ctions | -2.002 |
lp | -1.948 |
CLE | -1.892 |
Token | to |
Token ID | 284 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
ILLE | +0.062 |
ctions | +0.058 |
ESSION | +0.058 |
lp | +0.056 |
ned | +0.055 |
Neg logit contributions | |
�� | -0.055 |
eele | -0.055 |
ogical | -0.054 |
nature | -0.053 |
Dul | -0.051 |
Token | whose |
Token ID | 3025 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
ILLE | +0.237 |
ctions | +0.225 |
ESSION | +0.224 |
lp | +0.216 |
ned | +0.212 |
Neg logit contributions | |
eele | -0.183 |
�� | -0.183 |
ogical | -0.180 |
nature | -0.176 |
Dul | -0.171 |
Token | benefit |
Token ID | 4414 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
ILLE | +0.874 |
ctions | +0.835 |
ESSION | +0.829 |
lp | +0.802 |
ned | +0.792 |
Neg logit contributions | |
�� | -0.593 |
eele | -0.592 |
ogical | -0.580 |
nature | -0.568 |
Dul | -0.548 |
Token | ? |
Token ID | 30 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Dul | +4.927 |
ogical | +4.880 |
Sor | +4.824 |
nature | +4.706 |
eele | +4.703 |
Neg logit contributions | |
ILLE | -8.512 |
ESSION | -7.990 |
ctions | -7.944 |
lp | -7.613 |
atown | -7.609 |
Token |
|
Token ID | 198 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
ogical | +2.675 |
eele | +2.662 |
Dul | +2.642 |
nature | +2.637 |
Sor | +2.620 |
Neg logit contributions | |
ILLE | -3.250 |
ESSION | -3.052 |
ctions | -3.036 |
lp | -2.900 |
atown | -2.855 |
Token |
|
Token ID | 198 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
eele | +1.082 |
ogical | +1.080 |
nature | +1.075 |
Sor | +1.043 |
Dul | +1.040 |
Neg logit contributions | |
ILLE | -1.291 |
ESSION | -1.219 |
ctions | -1.210 |
lp | -1.153 |
atown | -1.150 |
Token | Here |
Token ID | 4342 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ILLE | +0.424 |
ctions | +0.399 |
ESSION | +0.396 |
lp | +0.377 |
ned | +0.369 |
Neg logit contributions | |
eele | -0.514 |
�� | -0.509 |
ogical | -0.508 |
nature | -0.502 |
Dul | -0.488 |
Token | are |
Token ID | 389 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
ILLE | +3.400 |
ctions | +3.261 |
ESSION | +3.176 |
lp | +3.097 |
ned | +3.015 |
Neg logit contributions | |
�� | -3.428 |
eele | -3.318 |
ogical | -3.307 |
nature | -3.155 |
aiman | -3.125 |
Token | payment |
Token ID | 37301 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ogical | +2.893 |
eele | +2.881 |
nature | +2.876 |
�� | +2.826 |
aiman | +2.730 |
Neg logit contributions | |
ILLE | -3.366 |
ctions | -3.171 |
ESSION | -3.171 |
lp | -3.039 |
ned | -3.000 |
Token | of |
Token ID | 286 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
eele | +2.648 |
ogical | +2.646 |
�� | +2.600 |
nature | +2.548 |
Dul | +2.524 |
Neg logit contributions | |
ILLE | -3.986 |
ESSION | -3.820 |
ctions | -3.742 |
lp | -3.632 |
ned | -3.557 |
Token | hours |
Token ID | 2250 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
ILLE | +0.110 |
ctions | +0.104 |
ESSION | +0.104 |
lp | +0.100 |
ned | +0.099 |
Neg logit contributions | |
eele | -0.074 |
�� | -0.074 |
ogical | -0.073 |
nature | -0.072 |
Dul | -0.069 |
Token | have |
Token ID | 423 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
�� | +0.227 |
eele | +0.226 |
ogical | +0.222 |
nature | +0.218 |
Dul | +0.211 |
Neg logit contributions | |
ILLE | -0.279 |
ctions | -0.265 |
ESSION | -0.263 |
lp | -0.254 |
ned | -0.250 |
Token | finally |
Token ID | 3443 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
eele | +0.712 |
�� | +0.708 |
ogical | +0.704 |
nature | +0.688 |
Dul | +0.672 |
Neg logit contributions | |
ILLE | -0.926 |
ESSION | -0.877 |
ctions | -0.876 |
lp | -0.843 |
ned | -0.823 |
Token | tipped |
Token ID | 28395 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
eele | +0.842 |
ogical | +0.841 |
�� | +0.836 |
nature | +0.817 |
Dul | +0.802 |
Neg logit contributions | |
ILLE | -1.084 |
ESSION | -1.025 |
ctions | -1.017 |
lp | -0.983 |
CLE | -0.954 |
Token | the |
Token ID | 262 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
ogical | +5.448 |
eele | +5.213 |
Dul | +5.183 |
Sor | +5.169 |
Mou | +5.134 |
Neg logit contributions | |
ILLE | -8.172 |
ctions | -7.713 |
ESSION | -7.622 |
lp | -7.472 |
CLE | -7.225 |
Token | Irish |
Token ID | 8685 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
�� | +0.165 |
eele | +0.164 |
ogical | +0.161 |
nature | +0.158 |
Dul | +0.152 |
Neg logit contributions | |
ILLE | -0.258 |
ctions | -0.246 |
ESSION | -0.245 |
lp | -0.237 |
ned | -0.234 |
Token | health |
Token ID | 1535 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
eele | +1.247 |
�� | +1.235 |
ogical | +1.233 |
nature | +1.206 |
Dul | +1.171 |
Neg logit contributions | |
ILLE | -1.668 |
ctions | -1.576 |
ESSION | -1.576 |
lp | -1.520 |
ned | -1.492 |
Token | service |
Token ID | 2139 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
eele | +1.549 |
ogical | +1.545 |
�� | +1.539 |
nature | +1.498 |
Dul | +1.449 |
Neg logit contributions | |
ILLE | -2.430 |
ESSION | -2.311 |
ctions | -2.310 |
lp | -2.228 |
ned | -2.190 |
Token | to |
Token ID | 284 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
eele | +0.317 |
�� | +0.315 |
ogical | +0.313 |
nature | +0.307 |
Dul | +0.300 |
Neg logit contributions | |
ILLE | -0.325 |
ctions | -0.306 |
ESSION | -0.306 |
lp | -0.293 |
ned | -0.287 |
Token | ica |
Token ID | 3970 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ogical | +1.700 |
eele | +1.700 |
�� | +1.674 |
nature | +1.667 |
Dul | +1.619 |
Neg logit contributions | |
ILLE | -1.273 |
ESSION | -1.190 |
ctions | -1.173 |
lp | -1.107 |
ned | -1.088 |
Token | / |
Token ID | 1220 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ILLE | +0.519 |
ctions | +0.491 |
ESSION | +0.487 |
lp | +0.469 |
ned | +0.462 |
Neg logit contributions | |
�� | -0.482 |
eele | -0.480 |
ogical | -0.472 |
nature | -0.462 |
Dul | -0.449 |
Token |
|
Token ID | 198 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ILLE | +1.286 |
ctions | +1.221 |
ESSION | +1.213 |
lp | +1.173 |
ned | +1.158 |
Neg logit contributions | |
�� | -0.956 |
eele | -0.953 |
ogical | -0.933 |
nature | -0.908 |
Dul | -0.882 |
Token |
|
Token ID | 198 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
eele | +0.522 |
ogical | +0.518 |
nature | +0.517 |
�� | +0.503 |
Dul | +0.498 |
Neg logit contributions | |
ILLE | -0.580 |
ctions | -0.550 |
ESSION | -0.549 |
lp | -0.524 |
atown | -0.516 |
Token | Local |
Token ID | 14565 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ILLE | +1.628 |
ctions | +1.517 |
ESSION | +1.511 |
lp | +1.453 |
ned | +1.427 |
Neg logit contributions | |
�� | -1.836 |
eele | -1.818 |
ogical | -1.782 |
nature | -1.733 |
Dul | -1.716 |
Token | tourist |
Token ID | 18473 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
eele | +0.389 |
ogical | +0.386 |
�� | +0.383 |
nature | +0.378 |
Dul | +0.368 |
Neg logit contributions | |
ILLE | -0.479 |
ESSION | -0.452 |
ctions | -0.452 |
lp | -0.435 |
ned | -0.426 |
Token | site |
Token ID | 2524 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ogical | +5.878 |
eele | +5.849 |
Sor | +5.822 |
Mou | +5.770 |
Dul | +5.747 |
Neg logit contributions | |
ILLE | -7.444 |
ESSION | -7.081 |
ctions | -7.053 |
lp | -6.847 |
atown | -6.670 |
Token | Fort |
Token ID | 6401 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
eele | +1.384 |
�� | +1.372 |
ogical | +1.364 |
nature | +1.340 |
Dul | +1.315 |
Neg logit contributions | |
ILLE | -1.700 |
ctions | -1.612 |
ESSION | -1.611 |
lp | -1.547 |
ned | -1.516 |
Token | de |
Token ID | 390 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
eele | +0.328 |
�� | +0.328 |
ogical | +0.323 |
nature | +0.317 |
Dul | +0.309 |
Neg logit contributions | |
ILLE | -0.384 |
ctions | -0.363 |
ESSION | -0.362 |
lp | -0.348 |
ned | -0.342 |
Token | Bre |
Token ID | 3719 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
eele | +2.355 |
�� | +2.328 |
ogical | +2.326 |
nature | +2.288 |
Dul | +2.261 |
Neg logit contributions | |
ILLE | -2.879 |
ESSION | -2.736 |
ctions | -2.721 |
lp | -2.609 |
ned | -2.552 |
Token | gan |
Token ID | 1030 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
�� | +0.887 |
eele | +0.879 |
ogical | +0.868 |
nature | +0.848 |
Dul | +0.826 |
Neg logit contributions | |
ILLE | -1.051 |
ctions | -0.999 |
ESSION | -0.990 |
lp | -0.959 |
ned | -0.943 |
Token | 2 |
Token ID | 362 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
ILLE | +1.452 |
ctions | +1.368 |
ESSION | +1.365 |
lp | +1.311 |
ned | +1.285 |
Neg logit contributions | |
�� | -1.455 |
eele | -1.451 |
ogical | -1.431 |
nature | -1.404 |
Dul | -1.360 |
Token | Million |
Token ID | 23425 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
eele | +1.424 |
�� | +1.414 |
ogical | +1.413 |
nature | +1.383 |
Dul | +1.358 |
Neg logit contributions | |
ILLE | -1.237 |
ctions | -1.160 |
ESSION | -1.158 |
lp | -1.101 |
CLE | -1.080 |
Token | Pack |
Token ID | 6400 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
ILLE | +0.666 |
ctions | +0.630 |
ESSION | +0.628 |
lp | +0.603 |
ned | +0.593 |
Neg logit contributions | |
eele | -0.593 |
�� | -0.593 |
ogical | -0.584 |
nature | -0.573 |
Dul | -0.558 |
Token | ets |
Token ID | 1039 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
�� | +0.882 |
eele | +0.877 |
ogical | +0.866 |
nature | +0.853 |
Dul | +0.833 |
Neg logit contributions | |
ILLE | -0.681 |
ctions | -0.640 |
ESSION | -0.636 |
lp | -0.607 |
ned | -0.594 |
Token | Per |
Token ID | 2448 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ILLE | +0.665 |
ctions | +0.630 |
ESSION | +0.628 |
lp | +0.605 |
ned | +0.596 |
Neg logit contributions | |
�� | -0.553 |
eele | -0.551 |
ogical | -0.542 |
nature | -0.533 |
Dul | -0.516 |
Token | Second |
Token ID | 5498 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ILLE | +0.359 |
ctions | +0.339 |
ESSION | +0.337 |
lp | +0.323 |
ned | +0.317 |
Neg logit contributions | |
eele | -0.374 |
�� | -0.374 |
ogical | -0.369 |
nature | -0.363 |
Dul | -0.354 |
Token | on |
Token ID | 319 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ogical | +5.629 |
eele | +5.568 |
Sor | +5.559 |
Dul | +5.504 |
Mou | +5.424 |
Neg logit contributions | |
ILLE | -7.359 |
ctions | -7.142 |
ESSION | -6.959 |
atown | -6.706 |
CLE | -6.657 |
Token | a |
Token ID | 257 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
eele | +0.602 |
�� | +0.599 |
ogical | +0.593 |
nature | +0.581 |
Dul | +0.567 |
Neg logit contributions | |
ILLE | -0.771 |
ctions | -0.731 |
ESSION | -0.728 |
lp | -0.700 |
ned | -0.689 |
Token | Public |
Token ID | 5094 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
eele | +0.420 |
�� | +0.419 |
ogical | +0.415 |
nature | +0.407 |
Dul | +0.398 |
Neg logit contributions | |
ILLE | -0.475 |
ctions | -0.449 |
ESSION | -0.448 |
lp | -0.429 |
ned | -0.423 |
Token | Cloud |
Token ID | 10130 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
ILLE | +0.800 |
ctions | +0.756 |
ESSION | +0.753 |
lp | +0.724 |
ned | +0.711 |
Neg logit contributions | |
�� | -0.753 |
eele | -0.749 |
ogical | -0.736 |
nature | -0.724 |
Dul | -0.702 |
Token | Inst |
Token ID | 2262 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
eele | +1.824 |
ogical | +1.803 |
�� | +1.798 |
nature | +1.763 |
Dul | +1.732 |
Neg logit contributions | |
ILLE | -2.089 |
ctions | -1.987 |
ESSION | -1.967 |
lp | -1.888 |
CLE | -1.856 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ILLE | +0.104 |
ctions | +0.099 |
ESSION | +0.098 |
lp | +0.095 |
ned | +0.094 |
Neg logit contributions | |
eele | -0.073 |
�� | -0.073 |
ogical | -0.071 |
nature | -0.070 |
Dul | -0.067 |
Token | Brune |
Token ID | 46070 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
ILLE | +0.397 |
ctions | +0.379 |
ESSION | +0.376 |
lp | +0.363 |
ned | +0.359 |
Neg logit contributions | |
�� | -0.279 |
eele | -0.279 |
ogical | -0.274 |
nature | -0.268 |
Dul | -0.259 |
Token | i |
Token ID | 72 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
ogical | +1.712 |
eele | +1.710 |
�� | +1.687 |
nature | +1.681 |
Sor | +1.635 |
Neg logit contributions | |
ILLE | -1.273 |
ESSION | -1.199 |
ctions | -1.172 |
lp | -1.103 |
CLE | -1.099 |
Token | Currency |
Token ID | 20113 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
ILLE | +0.356 |
ctions | +0.339 |
ESSION | +0.337 |
lp | +0.325 |
ned | +0.321 |
Neg logit contributions | |
�� | -0.257 |
eele | -0.257 |
ogical | -0.251 |
nature | -0.246 |
Dul | -0.238 |
Token | and |
Token ID | 290 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
eele | +1.545 |
�� | +1.538 |
ogical | +1.527 |
nature | +1.483 |
Dul | +1.441 |
Neg logit contributions | |
ILLE | -2.322 |
ESSION | -2.207 |
ctions | -2.204 |
lp | -2.133 |
ned | -2.092 |
Token | Monetary |
Token ID | 34112 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
eele | +1.169 |
�� | +1.167 |
ogical | +1.151 |
nature | +1.124 |
Dul | +1.093 |
Neg logit contributions | |
ILLE | -1.716 |
ctions | -1.631 |
ESSION | -1.627 |
lp | -1.572 |
ned | -1.546 |
Token | Board |
Token ID | 5926 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ogical | +6.152 |
eele | +5.976 |
Sor | +5.959 |
�� | +5.888 |
nature | +5.860 |
Neg logit contributions | |
ILLE | -7.318 |
ESSION | -6.885 |
ctions | -6.645 |
lp | -6.604 |
atown | -6.508 |
Token | .[ |
Token ID | 3693 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
�� | +0.634 |
eele | +0.634 |
ogical | +0.623 |
nature | +0.612 |
Dul | +0.594 |
Neg logit contributions | |
ILLE | -0.758 |
ctions | -0.719 |
ESSION | -0.716 |
lp | -0.689 |
ned | -0.678 |
Token | 18 |
Token ID | 1507 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
eele | +0.784 |
�� | +0.784 |
ogical | +0.770 |
nature | +0.754 |
Dul | +0.734 |
Neg logit contributions | |
ILLE | -0.981 |
ctions | -0.931 |
ESSION | -0.927 |
lp | -0.894 |
ned | -0.880 |
Token | ] |
Token ID | 60 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
eele | +1.561 |
�� | +1.560 |
ogical | +1.538 |
nature | +1.506 |
Dul | +1.461 |
Neg logit contributions | |
ILLE | -2.013 |
ctions | -1.910 |
ESSION | -1.904 |
lp | -1.831 |
ned | -1.803 |
Token |
|
Token ID | 198 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
ILLE | +2.261 |
ctions | +2.142 |
ESSION | +2.116 |
lp | +2.023 |
ned | +2.018 |
Neg logit contributions | |
�� | -2.469 |
eele | -2.434 |
ogical | -2.389 |
nature | -2.353 |
agine | -2.279 |
Token | & |
Token ID | 1222 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
eele | +1.615 |
�� | +1.612 |
ogical | +1.591 |
nature | +1.554 |
Dul | +1.521 |
Neg logit contributions | |
ILLE | -2.076 |
ctions | -1.967 |
ESSION | -1.962 |
lp | -1.889 |
ned | -1.859 |
Token | George |
Token ID | 4502 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
ILLE | +1.317 |
ctions | +1.252 |
ESSION | +1.247 |
lp | +1.204 |
ned | +1.184 |
Neg logit contributions | |
�� | -0.990 |
eele | -0.986 |
ogical | -0.969 |
nature | -0.949 |
aiman | -0.913 |
Token | - |
Token ID | 12 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
eele | +0.966 |
�� | +0.965 |
ogical | +0.951 |
nature | +0.933 |
Dul | +0.908 |
Neg logit contributions | |
ILLE | -1.141 |
ctions | -1.080 |
ESSION | -1.078 |
lp | -1.035 |
ned | -1.018 |
Token | 8 |
Token ID | 23 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
eele | +1.079 |
�� | +1.068 |
ogical | +1.068 |
nature | +1.057 |
Dul | +1.029 |
Neg logit contributions | |
ILLE | -1.016 |
ctions | -0.964 |
ESSION | -0.953 |
lp | -0.911 |
ned | -0.895 |
Token | Track |
Token ID | 17762 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
eele | +1.335 |
�� | +1.323 |
ogical | +1.318 |
nature | +1.288 |
Dul | +1.259 |
Neg logit contributions | |
ILLE | -1.629 |
ctions | -1.534 |
ESSION | -1.532 |
lp | -1.469 |
ned | -1.446 |
Token | Porn |
Token ID | 29629 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
eele | +0.553 |
�� | +0.551 |
ogical | +0.546 |
nature | +0.535 |
Dul | +0.520 |
Neg logit contributions | |
ILLE | -0.673 |
ctions | -0.635 |
ESSION | -0.635 |
lp | -0.608 |
ned | -0.598 |
Token | Pt |
Token ID | 34352 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ogical | +6.012 |
eele | +5.859 |
Sor | +5.809 |
�� | +5.784 |
nature | +5.756 |
Neg logit contributions | |
ILLE | -7.088 |
ESSION | -6.677 |
ctions | -6.555 |
CLE | -6.369 |
lp | -6.273 |
Token | 4 |
Token ID | 604 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
eele | +2.537 |
�� | +2.529 |
ogical | +2.502 |
nature | +2.459 |
Sor | +2.395 |
Neg logit contributions | |
ILLE | -3.408 |
ESSION | -3.205 |
ctions | -3.186 |
lp | -3.064 |
CLE | -3.018 |
Token | - |
Token ID | 12 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
�� | +2.265 |
eele | +2.262 |
ogical | +2.234 |
nature | +2.189 |
Dul | +2.144 |
Neg logit contributions | |
ILLE | -2.712 |
ctions | -2.571 |
ESSION | -2.570 |
lp | -2.451 |
ned | -2.418 |
Token | Ott |
Token ID | 49092 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
eele | +0.586 |
�� | +0.582 |
ogical | +0.579 |
nature | +0.571 |
Dul | +0.556 |
Neg logit contributions | |
ILLE | -0.555 |
ctions | -0.525 |
ESSION | -0.520 |
lp | -0.498 |
ned | -0.489 |
Token | os |
Token ID | 418 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
eele | +1.835 |
�� | +1.829 |
ogical | +1.813 |
nature | +1.771 |
Dul | +1.724 |
Neg logit contributions | |
ILLE | -2.251 |
ESSION | -2.124 |
ctions | -2.115 |
lp | -2.032 |
ned | -1.991 |
Token | pieces |
Token ID | 5207 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
eele | +1.818 |
ogical | +1.798 |
�� | +1.791 |
nature | +1.763 |
Sor | +1.728 |
Neg logit contributions | |
ILLE | -2.032 |
ESSION | -1.903 |
ctions | -1.892 |
lp | -1.818 |
ned | -1.787 |
Token | : |
Token ID | 1058 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
eele | +2.308 |
�� | +2.289 |
ogical | +2.278 |
nature | +2.231 |
Dul | +2.155 |
Neg logit contributions | |
ILLE | -2.930 |
ctions | -2.743 |
ESSION | -2.739 |
lp | -2.642 |
ned | -2.595 |
Token | [ |
Token ID | 685 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ILLE | +1.791 |
ctions | +1.725 |
ESSION | +1.688 |
lp | +1.644 |
ned | +1.624 |
Neg logit contributions | |
�� | -1.618 |
eele | -1.572 |
ogical | -1.565 |
nature | -1.532 |
aiman | -1.486 |
Token | Option |
Token ID | 16018 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
eele | +0.635 |
�� | +0.633 |
ogical | +0.624 |
nature | +0.613 |
Dul | +0.596 |
Neg logit contributions | |
ILLE | -0.749 |
ctions | -0.709 |
ESSION | -0.706 |
lp | -0.679 |
ned | -0.668 |
Token | < |
Token ID | 1279 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
eele | +4.019 |
�� | +3.947 |
ogical | +3.946 |
nature | +3.867 |
Sor | +3.796 |
Neg logit contributions | |
ILLE | -4.827 |
ctions | -4.554 |
ESSION | -4.551 |
lp | -4.346 |
atown | -4.231 |
Token | Piece |
Token ID | 27053 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
eele | +1.166 |
�� | +1.157 |
ogical | +1.145 |
nature | +1.128 |
Sor | +1.100 |
Neg logit contributions | |
ILLE | -1.325 |
ctions | -1.253 |
ESSION | -1.251 |
lp | -1.198 |
ned | -1.176 |
Token | > |
Token ID | 1875 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
ogical | +6.030 |
eele | +6.015 |
Sor | +5.923 |
nature | +5.874 |
Mou | +5.783 |
Neg logit contributions | |
ILLE | -6.840 |
ctions | -6.376 |
ESSION | -6.362 |
lp | -6.081 |
atown | -5.882 |
Token | ; |
Token ID | 2162 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ILLE | +1.392 |
ctions | +1.322 |
ESSION | +1.311 |
lp | +1.275 |
ned | +1.257 |
Neg logit contributions | |
�� | -1.102 |
eele | -1.080 |
ogical | -1.068 |
nature | -1.047 |
Dul | -1.013 |
Token | 64 |
Token ID | 5598 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
eele | +1.042 |
�� | +1.039 |
ogical | +1.026 |
nature | +1.008 |
Dul | +0.984 |
Neg logit contributions | |
ILLE | -1.050 |
ctions | -0.989 |
ESSION | -0.986 |
lp | -0.944 |
ned | -0.927 |
Token | ], |
Token ID | 16589 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
eele | +0.748 |
�� | +0.745 |
ogical | +0.736 |
nature | +0.722 |
Dul | +0.702 |
Neg logit contributions | |
ILLE | -0.868 |
ctions | -0.821 |
ESSION | -0.818 |
lp | -0.786 |
ned | -0.773 |
Token | // |
Token ID | 3373 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
ILLE | +4.498 |
ctions | +4.388 |
ESSION | +4.215 |
lp | +4.145 |
ned | +4.085 |
Neg logit contributions | |
�� | -5.537 |
eele | -5.327 |
ogical | -5.315 |
nature | -5.223 |
aiman | -5.102 |
Token | is |
Token ID | 318 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ILLE | +0.198 |
ESSION | +0.187 |
ctions | +0.186 |
lp | +0.179 |
ned | +0.175 |
Neg logit contributions | |
eele | -0.165 |
�� | -0.164 |
ogical | -0.164 |
nature | -0.160 |
Dul | -0.156 |
Token | losing |
Token ID | 6078 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
ILLE | +0.430 |
ctions | +0.407 |
ESSION | +0.406 |
lp | +0.390 |
ned | +0.383 |
Neg logit contributions | |
eele | -0.373 |
�� | -0.372 |
ogical | -0.370 |
nature | -0.361 |
Dul | -0.353 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ILLE | +0.944 |
ctions | +0.897 |
ESSION | +0.892 |
ned | +0.856 |
lp | +0.856 |
Neg logit contributions | |
�� | -0.876 |
eele | -0.868 |
ogical | -0.838 |
nature | -0.835 |
Dul | -0.798 |
Token | ( |
Token ID | 357 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ILLE | +0.591 |
ctions | +0.560 |
ESSION | +0.558 |
lp | +0.536 |
ned | +0.528 |
Neg logit contributions | |
eele | -0.498 |
�� | -0.498 |
ogical | -0.491 |
nature | -0.481 |
Dul | -0.468 |
Token | The |
Token ID | 464 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
ILLE | +0.736 |
ctions | +0.690 |
ESSION | +0.687 |
lp | +0.656 |
ned | +0.643 |
Neg logit contributions | |
eele | -0.868 |
�� | -0.868 |
ogical | -0.857 |
nature | -0.843 |
Dul | -0.823 |
Token | third |
Token ID | 2368 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
eele | +1.121 |
ogical | +1.116 |
�� | +1.111 |
nature | +1.089 |
Dul | +1.074 |
Neg logit contributions | |
ILLE | -1.237 |
ESSION | -1.168 |
ctions | -1.164 |
lp | -1.119 |
CLE | -1.097 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
ogical | +5.120 |
Sor | +5.043 |
Dul | +4.999 |
eele | +4.938 |
Mou | +4.938 |
Neg logit contributions | |
ILLE | -7.745 |
ESSION | -7.477 |
ctions | -7.305 |
atown | -7.073 |
lp | -7.011 |
Token | ironically |
Token ID | 32532 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
eele | +0.739 |
�� | +0.736 |
ogical | +0.734 |
nature | +0.717 |
Dul | +0.705 |
Neg logit contributions | |
ILLE | -0.969 |
ctions | -0.915 |
ESSION | -0.914 |
lp | -0.881 |
ned | -0.865 |
Token | , |
Token ID | 11 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ILLE | +0.789 |
ctions | +0.751 |
ESSION | +0.735 |
lp | +0.713 |
ned | +0.712 |
Neg logit contributions | |
�� | -0.749 |
eele | -0.744 |
ogical | -0.721 |
nature | -0.715 |
agine | -0.688 |
Token | is |
Token ID | 318 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
eele | +0.747 |
�� | +0.742 |
ogical | +0.737 |
nature | +0.721 |
Dul | +0.705 |
Neg logit contributions | |
ILLE | -0.978 |
ESSION | -0.928 |
ctions | -0.926 |
lp | -0.890 |
ned | -0.873 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
eele | +0.291 |
�� | +0.291 |
ogical | +0.288 |
nature | +0.281 |
Dul | +0.274 |
Neg logit contributions | |
ILLE | -0.369 |
ctions | -0.350 |
ESSION | -0.349 |
lp | -0.336 |
ned | -0.330 |
Token | alph |
Token ID | 17307 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
eele | +1.680 |
ogical | +1.657 |
�� | +1.625 |
nature | +1.603 |
aiman | +1.567 |
Neg logit contributions | |
ILLE | -1.769 |
ctions | -1.676 |
ESSION | -1.662 |
lp | -1.600 |
ned | -1.560 |
Token | � |
Token ID | 447 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
eele | +1.936 |
ogical | +1.928 |
�� | +1.926 |
nature | +1.865 |
Dul | +1.850 |
Neg logit contributions | |
ILLE | -2.457 |
ctions | -2.335 |
ESSION | -2.324 |
lp | -2.242 |
ned | -2.210 |
Token | � |
Token ID | 251 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ILLE | +0.602 |
ctions | +0.559 |
ESSION | +0.552 |
lp | +0.524 |
ned | +0.510 |
Neg logit contributions | |
eele | -0.987 |
�� | -0.979 |
ogical | -0.976 |
nature | -0.962 |
Dul | -0.944 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
ILLE | +3.626 |
ctions | +3.423 |
ESSION | +3.398 |
lp | +3.294 |
ned | +3.279 |
Neg logit contributions | |
�� | -3.024 |
eele | -2.995 |
ogical | -2.945 |
nature | -2.885 |
aiman | -2.791 |
Token | the |
Token ID | 262 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
ILLE | +0.715 |
ctions | +0.679 |
ESSION | +0.675 |
lp | +0.651 |
ned | +0.641 |
Neg logit contributions | |
eele | -0.566 |
�� | -0.565 |
ogical | -0.556 |
nature | -0.544 |
Dul | -0.527 |
Token | name |
Token ID | 1438 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ILLE | +0.065 |
ctions | +0.062 |
ESSION | +0.062 |
lp | +0.059 |
ned | +0.058 |
Neg logit contributions | |
eele | -0.052 |
�� | -0.052 |
ogical | -0.052 |
nature | -0.051 |
Dul | -0.049 |
Token | a |
Token ID | 257 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ILLE | +4.931 |
ctions | +4.726 |
ESSION | +4.670 |
ned | +4.560 |
lp | +4.486 |
Neg logit contributions | |
�� | -4.638 |
eele | -4.465 |
nature | -4.334 |
ogical | -4.329 |
agine | -4.186 |
Token | teenage |
Token ID | 16330 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
eele | +0.387 |
�� | +0.382 |
ogical | +0.379 |
nature | +0.371 |
Dul | +0.364 |
Neg logit contributions | |
ILLE | -0.477 |
ESSION | -0.453 |
ctions | -0.449 |
lp | -0.433 |
CLE | -0.423 |
Token | boy |
Token ID | 2933 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
eele | +0.136 |
�� | +0.135 |
ogical | +0.133 |
nature | +0.130 |
Dul | +0.127 |
Neg logit contributions | |
ILLE | -0.184 |
ctions | -0.175 |
ESSION | -0.174 |
lp | -0.168 |
ned | -0.165 |
Token | memor |
Token ID | 16181 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
ILLE | +2.514 |
ctions | +2.392 |
ESSION | +2.375 |
lp | +2.292 |
ned | +2.269 |
Neg logit contributions | |
�� | -2.209 |
eele | -2.185 |
ogical | -2.139 |
nature | -2.106 |
Dul | -2.031 |
Token | ably |
Token ID | 1346 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ILLE | +2.141 |
ctions | +2.115 |
ESSION | +2.064 |
lp | +2.019 |
ned | +2.015 |
Neg logit contributions | |
�� | -1.176 |
eele | -1.139 |
ogical | -1.099 |
nature | -1.067 |
Dul | -1.037 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ILLE | +1.939 |
ctions | +1.832 |
ESSION | +1.812 |
lp | +1.749 |
ned | +1.730 |
Neg logit contributions | |
�� | -2.134 |
eele | -2.093 |
ogical | -2.053 |
nature | -2.007 |
Dul | -1.963 |
Token | Share |
Token ID | 11649 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ILLE | +3.757 |
ESSION | +3.454 |
ctions | +3.426 |
lp | +3.336 |
CLE | +3.291 |
Neg logit contributions | |
�� | -4.787 |
eele | -4.682 |
ogical | -4.565 |
nature | -4.435 |
Dul | -4.425 |
Token | this |
Token ID | 428 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
ILLE | +3.185 |
ctions | +3.042 |
ESSION | +2.980 |
lp | +2.911 |
ned | +2.898 |
Neg logit contributions | |
�� | -2.772 |
eele | -2.727 |
ogical | -2.690 |
nature | -2.624 |
Dul | -2.525 |
Token | post |
Token ID | 1281 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
ILLE | +0.172 |
ctions | +0.163 |
ESSION | +0.162 |
lp | +0.156 |
ned | +0.153 |
Neg logit contributions | |
eele | -0.145 |
�� | -0.144 |
ogical | -0.143 |
nature | -0.140 |
Dul | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ILLE | +2.576 |
ctions | +2.446 |
ESSION | +2.418 |
lp | +2.325 |
ned | +2.298 |
Neg logit contributions | |
�� | -2.643 |
eele | -2.640 |
ogical | -2.602 |
nature | -2.554 |
Dul | -2.475 |
Token |
|
Token ID | 198 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ILLE | +3.880 |
ctions | +3.716 |
ESSION | +3.596 |
ned | +3.586 |
lp | +3.538 |
Neg logit contributions | |
�� | -5.508 |
eele | -5.166 |
ogical | -5.013 |
aiman | -4.859 |
nature | -4.842 |
Token | J |
Token ID | 41 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ILLE | +4.818 |
ctions | +4.422 |
ESSION | +4.383 |
lp | +4.321 |
CLE | +4.250 |
Neg logit contributions | |
�� | -5.789 |
eele | -5.635 |
ogical | -5.454 |
Dul | -5.341 |
Sor | -5.302 |
Token | olla |
Token ID | 33011 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ILLE | +3.487 |
ESSION | +3.289 |
ctions | +3.271 |
lp | +3.163 |
ned | +3.101 |
Neg logit contributions | |
�� | -3.416 |
eele | -3.315 |
ogical | -3.249 |
nature | -3.239 |
Dul | -3.161 |
Token | boss |
Token ID | 6478 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ILLE | +3.224 |
ctions | +3.045 |
ESSION | +3.009 |
lp | +2.928 |
ned | +2.890 |
Neg logit contributions | |
�� | -2.966 |
eele | -2.912 |
ogical | -2.848 |
nature | -2.815 |
Dul | -2.702 |
Token | promises |
Token ID | 10497 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ogical | +2.424 |
eele | +2.384 |
�� | +2.344 |
Sor | +2.334 |
Dul | +2.331 |
Neg logit contributions | |
ILLE | -3.390 |
ESSION | -3.217 |
ctions | -3.188 |
lp | -3.058 |
atown | -3.025 |
Token | : |
Token ID | 25 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
ILLE | +0.342 |
ctions | +0.324 |
ESSION | +0.323 |
lp | +0.310 |
ned | +0.306 |
Neg logit contributions | |
�� | -0.290 |
eele | -0.290 |
ogical | -0.286 |
nature | -0.280 |
Dul | -0.272 |
Token | protest |
Token ID | 5402 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
eele | +1.042 |
�� | +1.037 |
ogical | +1.031 |
nature | +0.997 |
Dul | +0.973 |
Neg logit contributions | |
ILLE | -2.020 |
ESSION | -1.936 |
ctions | -1.929 |
lp | -1.865 |
ned | -1.833 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
eele | +1.061 |
�� | +1.050 |
ogical | +1.047 |
nature | +1.023 |
Dul | +0.998 |
Neg logit contributions | |
ILLE | -1.293 |
ctions | -1.220 |
ESSION | -1.220 |
lp | -1.175 |
ned | -1.150 |
Token | � |
Token ID | 447 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
ILLE | +2.836 |
ctions | +2.715 |
ESSION | +2.659 |
lp | +2.561 |
ned | +2.537 |
Neg logit contributions | |
�� | -2.902 |
eele | -2.820 |
ogical | -2.752 |
nature | -2.707 |
Dul | -2.639 |
Token | � |
Token ID | 247 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ILLE | +0.557 |
ctions | +0.506 |
ESSION | +0.503 |
lp | +0.468 |
ned | +0.454 |
Neg logit contributions | |
�� | -1.211 |
eele | -1.211 |
ogical | -1.198 |
nature | -1.183 |
Dul | -1.161 |
Token | s |
Token ID | 82 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
eele | +0.758 |
�� | +0.751 |
ogical | +0.751 |
nature | +0.739 |
Dul | +0.719 |
Neg logit contributions | |
ILLE | -0.624 |
ESSION | -0.581 |
ctions | -0.580 |
lp | -0.552 |
ned | -0.539 |
Token | presidency |
Token ID | 12112 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ILLE | +1.181 |
ctions | +1.131 |
ESSION | +1.125 |
lp | +1.090 |
ned | +1.078 |
Neg logit contributions | |
�� | -0.622 |
eele | -0.621 |
ogical | -0.606 |
nature | -0.591 |
Dul | -0.568 |
Token | . |
Token ID | 13 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
ILLE | +4.522 |
ctions | +4.393 |
ESSION | +4.290 |
lp | +4.104 |
ned | +4.095 |
Neg logit contributions | |
�� | -5.103 |
eele | -4.966 |
ogical | -4.811 |
nature | -4.723 |
aiman | -4.661 |
Token | Spons |
Token ID | 43522 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
eele | +0.018 |
�� | +0.017 |
ogical | +0.017 |
nature | +0.017 |
Dul | +0.017 |
Neg logit contributions | |
ILLE | -0.017 |
ctions | -0.016 |
ESSION | -0.016 |
lp | -0.015 |
ned | -0.015 |
Token | ored |
Token ID | 1850 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ILLE | +1.183 |
ctions | +1.121 |
ESSION | +1.115 |
lp | +1.072 |
ned | +1.055 |
Neg logit contributions | |
eele | -1.053 |
�� | -1.052 |
ogical | -1.037 |
nature | -1.018 |
Dul | -0.991 |
Token | by |
Token ID | 416 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ILLE | +0.377 |
ctions | +0.356 |
ESSION | +0.354 |
lp | +0.340 |
ned | +0.334 |
Neg logit contributions | |
eele | -0.349 |
�� | -0.349 |
ogical | -0.344 |
nature | -0.337 |
Dul | -0.329 |
Token | Democrats |
Token ID | 4956 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
eele | +1.196 |
�� | +1.185 |
ogical | +1.180 |
nature | +1.159 |
Dul | +1.136 |
Neg logit contributions | |
ILLE | -1.418 |
ctions | -1.339 |
ESSION | -1.333 |
lp | -1.282 |
ned | -1.256 |
Token | white |
Token ID | 2330 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
ILLE | +2.466 |
ctions | +2.346 |
ESSION | +2.319 |
lp | +2.241 |
ned | +2.227 |
Neg logit contributions | |
�� | -2.290 |
eele | -2.251 |
ogical | -2.200 |
nature | -2.166 |
aiman | -2.101 |
Token | powder |
Token ID | 11913 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
ILLE | +1.144 |
ctions | +1.082 |
ESSION | +1.076 |
lp | +1.035 |
ned | +1.022 |
Neg logit contributions | |
�� | -1.088 |
eele | -1.086 |
ogical | -1.067 |
nature | -1.049 |
Dul | -1.018 |
Token | is |
Token ID | 318 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ILLE | +2.009 |
ctions | +1.913 |
ESSION | +1.898 |
lp | +1.838 |
ned | +1.826 |
Neg logit contributions | |
�� | -1.824 |
eele | -1.785 |
ogical | -1.748 |
nature | -1.725 |
aiman | -1.659 |
Token | actually |
Token ID | 1682 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
ILLE | +0.310 |
ctions | +0.294 |
ESSION | +0.293 |
lp | +0.282 |
ned | +0.277 |
Neg logit contributions | |
eele | -0.253 |
�� | -0.251 |
ogical | -0.249 |
nature | -0.245 |
Dul | -0.239 |
Token | a |
Token ID | 257 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
eele | +0.099 |
�� | +0.099 |
ogical | +0.098 |
nature | +0.096 |
Dul | +0.093 |
Neg logit contributions | |
ILLE | -0.126 |
ctions | -0.120 |
ESSION | -0.119 |
lp | -0.115 |
ned | -0.113 |
Token | processed |
Token ID | 13686 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ILLE | +1.369 |
ctions | +1.299 |
ESSION | +1.288 |
lp | +1.244 |
ned | +1.228 |
Neg logit contributions | |
�� | -1.184 |
eele | -1.179 |
ogical | -1.159 |
nature | -1.134 |
Dul | -1.094 |
Token | flour |
Token ID | 10601 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
ILLE | +5.256 |
ctions | +5.000 |
ESSION | +4.898 |
ned | +4.882 |
lp | +4.788 |
Neg logit contributions | |
�� | -5.231 |
eele | -5.152 |
ogical | -4.990 |
nature | -4.878 |
aiman | -4.768 |
Token | / |
Token ID | 14 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ILLE | +0.929 |
ctions | +0.879 |
ESSION | +0.876 |
lp | +0.842 |
ned | +0.830 |
Neg logit contributions | |
�� | -0.816 |
eele | -0.815 |
ogical | -0.802 |
nature | -0.787 |
Dul | -0.764 |
Token | st |
Token ID | 301 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ILLE | +1.458 |
ctions | +1.377 |
ESSION | +1.368 |
lp | +1.329 |
ned | +1.313 |
Neg logit contributions | |
�� | -1.390 |
eele | -1.375 |
ogical | -1.351 |
nature | -1.306 |
Dul | -1.287 |
Token | arch |
Token ID | 998 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ILLE | +0.422 |
ctions | +0.401 |
ESSION | +0.400 |
lp | +0.385 |
ned | +0.379 |
Neg logit contributions | |
eele | -0.297 |
�� | -0.295 |
ogical | -0.292 |
nature | -0.285 |
Dul | -0.276 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
eele | +0.367 |
�� | +0.363 |
ogical | +0.362 |
nature | +0.354 |
Dul | +0.346 |
Neg logit contributions | |
ILLE | -0.431 |
ctions | -0.408 |
ESSION | -0.408 |
lp | -0.391 |
ned | -0.381 |
Token | Justin |
Token ID | 33229 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
ILLE | +2.106 |
ESSION | +1.970 |
ctions | +1.968 |
lp | +1.893 |
ned | +1.860 |
Neg logit contributions | |
�� | -2.142 |
eele | -2.115 |
ogical | -2.074 |
nature | -2.018 |
Dul | -1.975 |
Token | Sullivan |
Token ID | 18501 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
�� | +0.923 |
eele | +0.923 |
ogical | +0.906 |
nature | +0.882 |
Dul | +0.854 |
Neg logit contributions | |
ILLE | -1.777 |
ctions | -1.696 |
ESSION | -1.695 |
lp | -1.640 |
ned | -1.615 |
Token | / |
Token ID | 14 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ILLE | +0.375 |
ctions | +0.349 |
ESSION | +0.343 |
lp | +0.331 |
ned | +0.323 |
Neg logit contributions | |
�� | -0.519 |
eele | -0.516 |
ogical | -0.509 |
nature | -0.500 |
Dul | -0.488 |
Token | Getty |
Token ID | 6633 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
eele | +0.282 |
�� | +0.279 |
ogical | +0.275 |
nature | +0.275 |
Sor | +0.260 |
Neg logit contributions | |
ILLE | -0.473 |
ESSION | -0.457 |
ctions | -0.456 |
lp | -0.438 |
ned | -0.433 |
Token | Images |
Token ID | 5382 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
eele | +0.369 |
�� | +0.364 |
ogical | +0.352 |
nature | +0.332 |
Dul | +0.309 |
Neg logit contributions | |
ILLE | -1.610 |
ctions | -1.555 |
ESSION | -1.542 |
lp | -1.509 |
ned | -1.496 |
Token | ) |
Token ID | 8 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ILLE | +0.032 |
ctions | +0.030 |
ESSION | +0.030 |
lp | +0.029 |
ned | +0.029 |
Neg logit contributions | |
�� | -0.030 |
eele | -0.030 |
ogical | -0.030 |
nature | -0.029 |
aiman | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ILLE | +4.337 |
ctions | +4.020 |
ESSION | +3.912 |
CLE | +3.824 |
lp | +3.758 |
Neg logit contributions | |
eele | -5.659 |
�� | -5.520 |
ogical | -5.503 |
aiman | -5.374 |
nature | -5.370 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ILLE | +2.599 |
ctions | +2.456 |
ESSION | +2.421 |
lp | +2.342 |
ned | +2.326 |
Neg logit contributions | |
�� | -3.021 |
eele | -2.940 |
ogical | -2.872 |
nature | -2.796 |
aiman | -2.757 |
Token | SAN |
Token ID | 36753 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ILLE | +3.077 |
ESSION | +2.800 |
ctions | +2.791 |
CLE | +2.680 |
lp | +2.671 |
Neg logit contributions | |
�� | -4.511 |
eele | -4.407 |
ogical | -4.311 |
Dul | -4.196 |
nature | -4.187 |
Token | FR |
Token ID | 8782 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ILLE | +6.292 |
ctions | +5.993 |
ESSION | +5.874 |
ned | +5.642 |
CLE | +5.543 |
Neg logit contributions | |
�� | -5.520 |
eele | -5.189 |
ogical | -5.006 |
nature | -4.980 |
agine | -4.750 |
Token | ANC |
Token ID | 20940 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
ILLE | +2.114 |
ESSION | +1.903 |
ctions | +1.761 |
CLE | +1.606 |
IDENT | +1.573 |
Neg logit contributions | |
�� | -5.128 |
eele | -5.040 |
ogical | -4.979 |
nature | -4.845 |
agine | -4.784 |
Token | M |
Token ID | 337 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ILLE | +1.190 |
ctions | +1.132 |
ESSION | +1.129 |
ned | +1.085 |
lp | +1.082 |
Neg logit contributions | |
�� | -0.854 |
eele | -0.841 |
ogical | -0.821 |
nature | -0.817 |
agine | -0.779 |
Token | ook |
Token ID | 566 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
ILLE | +0.419 |
ESSION | +0.399 |
ctions | +0.398 |
lp | +0.382 |
CLE | +0.375 |
Neg logit contributions | |
eele | -0.268 |
ogical | -0.262 |
�� | -0.258 |
nature | -0.255 |
Dul | -0.245 |
Token | said |
Token ID | 531 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
eele | +1.335 |
ogical | +1.326 |
�� | +1.323 |
nature | +1.289 |
Dul | +1.264 |
Neg logit contributions | |
ILLE | -1.695 |
ESSION | -1.599 |
ctions | -1.596 |
lp | -1.532 |
CLE | -1.491 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
ILLE | +1.345 |
ctions | +1.269 |
ESSION | +1.263 |
lp | +1.216 |
ned | +1.212 |
Neg logit contributions | |
�� | -1.295 |
eele | -1.282 |
ogical | -1.256 |
nature | -1.240 |
agine | -1.197 |
Token | ' |
Token ID | 705 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ILLE | +0.960 |
ctions | +0.912 |
ESSION | +0.901 |
lp | +0.873 |
ned | +0.861 |
Neg logit contributions | |
�� | -0.851 |
eele | -0.847 |
ogical | -0.835 |
nature | -0.820 |
agine | -0.795 |
Token | I |
Token ID | 40 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
ILLE | +0.041 |
ctions | +0.038 |
ESSION | +0.038 |
lp | +0.036 |
atown | +0.035 |
Neg logit contributions | |
ogical | -0.051 |
eele | -0.051 |
nature | -0.050 |
�� | -0.050 |
Dul | -0.049 |
Token | am |
Token ID | 716 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
ILLE | +1.196 |
ctions | +1.134 |
ESSION | +1.126 |
lp | +1.085 |
ned | +1.068 |
Neg logit contributions | |
�� | -1.124 |
eele | -1.118 |
ogical | -1.096 |
nature | -1.076 |
Dul | -1.048 |
Token | simply |
Token ID | 2391 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
ILLE | +2.636 |
ctions | +2.503 |
ESSION | +2.481 |
lp | +2.396 |
ned | +2.362 |
Neg logit contributions | |
�� | -2.208 |
eele | -2.192 |
ogical | -2.137 |
nature | -2.107 |
Dul | -2.037 |
Token | going |
Token ID | 1016 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ILLE | +1.549 |
ctions | +1.466 |
ESSION | +1.460 |
lp | +1.404 |
ned | +1.381 |
Neg logit contributions | |
eele | -1.348 |
�� | -1.347 |
ogical | -1.326 |
nature | -1.301 |
Dul | -1.266 |
Token | off |
Token ID | 572 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ILLE | +0.373 |
ctions | +0.354 |
ESSION | +0.351 |
lp | +0.337 |
ned | +0.334 |
Neg logit contributions | |
eele | -0.334 |
�� | -0.333 |
ogical | -0.324 |
nature | -0.319 |
Dul | -0.310 |
Token | what |
Token ID | 644 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
eele | +0.556 |
�� | +0.553 |
ogical | +0.552 |
nature | +0.539 |
Dul | +0.522 |
Neg logit contributions | |
ILLE | -0.760 |
ctions | -0.721 |
ESSION | -0.716 |
lp | -0.692 |
ned | -0.679 |
Token | the |
Token ID | 262 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
eele | +1.296 |
ogical | +1.282 |
�� | +1.278 |
nature | +1.249 |
Dul | +1.226 |
Neg logit contributions | |
ILLE | -2.050 |
ctions | -1.946 |
ESSION | -1.943 |
lp | -1.873 |
ned | -1.845 |
Token | Canary |
Token ID | 50206 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
�� | +0.898 |
eele | +0.896 |
ogical | +0.879 |
nature | +0.861 |
Dul | +0.831 |
Neg logit contributions | |
ILLE | -1.290 |
ctions | -1.229 |
ESSION | -1.223 |
lp | -1.182 |
ned | -1.164 |
Token | Islands |
Token ID | 12010 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
�� | +0.601 |
eele | +0.597 |
ogical | +0.588 |
nature | +0.576 |
Dul | +0.559 |
Neg logit contributions | |
ILLE | -0.742 |
ctions | -0.704 |
ESSION | -0.701 |
lp | -0.675 |
ned | -0.665 |
Token | and |
Token ID | 290 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
�� | +1.999 |
eele | +1.998 |
ogical | +1.966 |
nature | +1.930 |
Dul | +1.874 |
Neg logit contributions | |
ILLE | -2.277 |
ctions | -2.157 |
ESSION | -2.145 |
lp | -2.064 |
ned | -2.031 |
Token | Catalonia |
Token ID | 33859 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
�� | +0.530 |
eele | +0.529 |
ogical | +0.519 |
nature | +0.508 |
Dul | +0.490 |
Neg logit contributions | |
ILLE | -0.834 |
ctions | -0.795 |
ESSION | -0.792 |
lp | -0.766 |
ned | -0.755 |
Token | — |
Token ID | 851 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
�� | +0.803 |
eele | +0.795 |
ogical | +0.785 |
nature | +0.772 |
Dul | +0.747 |
Neg logit contributions | |
ILLE | -0.733 |
ctions | -0.691 |
ESSION | -0.684 |
lp | -0.658 |
ned | -0.647 |
Token | have |
Token ID | 423 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ILLE | +0.711 |
ctions | +0.676 |
ESSION | +0.671 |
lp | +0.650 |
ned | +0.639 |
Neg logit contributions | |
�� | -0.555 |
eele | -0.550 |
ogical | -0.541 |
nature | -0.530 |
Dul | -0.513 |
Token | said |
Token ID | 531 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
eele | +1.223 |
ogical | +1.214 |
�� | +1.210 |
nature | +1.186 |
Dul | +1.168 |
Neg logit contributions | |
ILLE | -1.193 |
ESSION | -1.129 |
ctions | -1.124 |
lp | -1.074 |
CLE | -1.048 |
Token | that |
Token ID | 326 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
eele | +0.471 |
�� | +0.468 |
ogical | +0.465 |
nature | +0.455 |
Dul | +0.445 |
Neg logit contributions | |
ILLE | -0.543 |
ctions | -0.514 |
ESSION | -0.513 |
lp | -0.492 |
ned | -0.483 |
Token | they |
Token ID | 484 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
eele | +1.279 |
ogical | +1.265 |
�� | +1.262 |
nature | +1.236 |
Dul | +1.210 |
Neg logit contributions | |
ILLE | -1.514 |
ctions | -1.432 |
ESSION | -1.432 |
lp | -1.377 |
ned | -1.348 |
Token | will |
Token ID | 481 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
eele | +0.328 |
�� | +0.324 |
ogical | +0.324 |
nature | +0.317 |
Dul | +0.308 |
Neg logit contributions | |
ILLE | -0.468 |
ESSION | -0.444 |
ctions | -0.443 |
lp | -0.427 |
ned | -0.420 |
Token | president |
Token ID | 1893 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
ILLE | +1.631 |
ctions | +1.539 |
ESSION | +1.528 |
lp | +1.469 |
ned | +1.455 |
Neg logit contributions | |
�� | -1.692 |
eele | -1.672 |
ogical | -1.639 |
nature | -1.637 |
aiman | -1.558 |
Token | , |
Token ID | 11 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ILLE | +2.608 |
ctions | +2.450 |
ESSION | +2.444 |
ned | +2.362 |
lp | +2.352 |
Neg logit contributions | |
�� | -2.613 |
eele | -2.595 |
nature | -2.557 |
ogical | -2.551 |
agine | -2.410 |
Token | Dean |
Token ID | 11325 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
eele | +0.887 |
�� | +0.887 |
ogical | +0.872 |
nature | +0.855 |
Dul | +0.829 |
Neg logit contributions | |
ILLE | -1.169 |
ctions | -1.111 |
ESSION | -1.107 |
lp | -1.067 |
ned | -1.050 |
Token | also |
Token ID | 635 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ILLE | +0.878 |
ctions | +0.832 |
ESSION | +0.827 |
lp | +0.796 |
ned | +0.783 |
Neg logit contributions | |
�� | -0.788 |
eele | -0.788 |
ogical | -0.775 |
nature | -0.761 |
Dul | -0.740 |
Token | was |
Token ID | 373 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
eele | +0.750 |
ogical | +0.745 |
�� | +0.741 |
nature | +0.725 |
Dul | +0.715 |
Neg logit contributions | |
ILLE | -0.866 |
ESSION | -0.811 |
ctions | -0.806 |
lp | -0.771 |
CLE | -0.754 |
Token | not |
Token ID | 407 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
ILLE | +0.197 |
ctions | +0.187 |
ESSION | +0.186 |
lp | +0.179 |
ned | +0.176 |
Neg logit contributions | |
eele | -0.161 |
�� | -0.161 |
ogical | -0.159 |
nature | -0.155 |
Dul | -0.151 |
Token | particularly |
Token ID | 3573 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
ILLE | +1.818 |
ctions | +1.727 |
ESSION | +1.716 |
lp | +1.654 |
ned | +1.633 |
Neg logit contributions | |
�� | -1.610 |
eele | -1.602 |
ogical | -1.569 |
nature | -1.545 |
Dul | -1.501 |
Token | tech |
Token ID | 7261 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
ogical | +1.570 |
eele | +1.566 |
�� | +1.524 |
nature | +1.521 |
Dul | +1.496 |
Neg logit contributions | |
ILLE | -1.769 |
ESSION | -1.676 |
ctions | -1.655 |
lp | -1.580 |
atown | -1.550 |
Token | - |
Token ID | 12 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ILLE | +1.691 |
ctions | +1.571 |
ESSION | +1.559 |
lp | +1.488 |
ned | +1.462 |
Neg logit contributions | |
�� | -2.829 |
eele | -2.821 |
ogical | -2.768 |
nature | -2.736 |
Dul | -2.690 |
Token | sav |
Token ID | 39308 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ILLE | +0.184 |
ctions | +0.164 |
ESSION | +0.163 |
lp | +0.148 |
ned | +0.142 |
Neg logit contributions | |
eele | -0.484 |
�� | -0.482 |
ogical | -0.480 |
nature | -0.475 |
Dul | -0.465 |
Token | vy |
Token ID | 7670 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
ILLE | +2.909 |
ctions | +2.690 |
lp | +2.654 |
ned | +2.600 |
ESSION | +2.586 |
Neg logit contributions | |
�� | -6.669 |
eele | -6.402 |
ogical | -6.338 |
Dul | -6.205 |
nature | -6.168 |
Token | Arkansas |
Token ID | 14538 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
�� | +0.041 |
eele | +0.041 |
ogical | +0.041 |
nature | +0.040 |
Dul | +0.039 |
Neg logit contributions | |
ILLE | -0.057 |
ctions | -0.054 |
ESSION | -0.054 |
lp | -0.052 |
ned | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
eele | +0.960 |
�� | +0.953 |
ogical | +0.949 |
nature | +0.929 |
Dul | +0.911 |
Neg logit contributions | |
ILLE | -1.163 |
ctions | -1.102 |
ESSION | -1.098 |
lp | -1.056 |
ned | -1.033 |
Token | and |
Token ID | 290 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
eele | +0.319 |
�� | +0.317 |
ogical | +0.315 |
nature | +0.308 |
Dul | +0.301 |
Neg logit contributions | |
ILLE | -0.397 |
ctions | -0.376 |
ESSION | -0.375 |
lp | -0.361 |
ned | -0.355 |
Token | as |
Token ID | 355 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ILLE | +0.155 |
ctions | +0.147 |
ESSION | +0.147 |
lp | +0.141 |
ned | +0.139 |
Neg logit contributions | |
eele | -0.118 |
�� | -0.118 |
ogical | -0.116 |
nature | -0.113 |
Dul | -0.110 |
Token | a |
Token ID | 257 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ILLE | +0.987 |
ctions | +0.937 |
ESSION | +0.932 |
lp | +0.902 |
ned | +0.893 |
Neg logit contributions | |
�� | -0.695 |
eele | -0.686 |
ogical | -0.674 |
nature | -0.661 |
Dul | -0.633 |
Token | consequence |
Token ID | 12921 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
eele | +0.375 |
�� | +0.374 |
ogical | +0.369 |
nature | +0.361 |
Dul | +0.351 |
Neg logit contributions | |
ILLE | -0.531 |
ctions | -0.505 |
ESSION | -0.505 |
lp | -0.486 |
ned | -0.478 |
Token | was |
Token ID | 373 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ILLE | +3.218 |
ctions | +3.022 |
ESSION | +2.982 |
ned | +2.947 |
lp | +2.909 |
Neg logit contributions | |
�� | -2.762 |
eele | -2.702 |
ogical | -2.621 |
nature | -2.578 |
aiman | -2.475 |
Token | hanged |
Token ID | 40597 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
eele | +0.859 |
ogical | +0.855 |
�� | +0.848 |
nature | +0.836 |
Dul | +0.820 |
Neg logit contributions | |
ILLE | -1.094 |
ESSION | -1.049 |
ctions | -1.040 |
lp | -0.998 |
CLE | -0.974 |
Token | as |
Token ID | 355 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
ILLE | +1.837 |
ctions | +1.737 |
ESSION | +1.726 |
lp | +1.667 |
ned | +1.646 |
Neg logit contributions | |
�� | -1.621 |
eele | -1.614 |
ogical | -1.583 |
nature | -1.555 |
Dul | -1.507 |
Token | a |
Token ID | 257 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
ILLE | +0.141 |
ctions | +0.135 |
ESSION | +0.134 |
lp | +0.130 |
ned | +0.128 |
Neg logit contributions | |
eele | -0.095 |
�� | -0.095 |
ogical | -0.093 |
nature | -0.091 |
Dul | -0.088 |
Token | spy |
Token ID | 13997 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
eele | +0.088 |
�� | +0.087 |
ogical | +0.086 |
nature | +0.085 |
Dul | +0.083 |
Neg logit contributions | |
ILLE | -0.106 |
ESSION | -0.101 |
ctions | -0.100 |
lp | -0.096 |
ned | -0.094 |
Token | not |
Token ID | 407 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
ILLE | +0.277 |
ctions | +0.264 |
ESSION | +0.262 |
lp | +0.253 |
ned | +0.251 |
Neg logit contributions | |
�� | -0.193 |
eele | -0.193 |
ogical | -0.189 |
nature | -0.185 |
Dul | -0.179 |
Token | all |
Token ID | 477 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ILLE | +1.075 |
ctions | +1.020 |
ESSION | +1.016 |
lp | +0.980 |
ned | +0.970 |
Neg logit contributions | |
eele | -0.804 |
�� | -0.802 |
ogical | -0.789 |
nature | -0.771 |
Dul | -0.742 |
Token | of |
Token ID | 286 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ILLE | +0.501 |
ctions | +0.479 |
ESSION | +0.473 |
lp | +0.455 |
ned | +0.454 |
Neg logit contributions | |
eele | -0.383 |
�� | -0.382 |
ogical | -0.375 |
nature | -0.367 |
Dul | -0.351 |
Token | them |
Token ID | 606 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
ILLE | +0.614 |
ctions | +0.584 |
ESSION | +0.583 |
lp | +0.561 |
ned | +0.557 |
Neg logit contributions | |
eele | -0.408 |
�� | -0.407 |
ogical | -0.397 |
nature | -0.387 |
aiman | -0.371 |
Token | are |
Token ID | 389 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ILLE | +1.297 |
ctions | +1.235 |
ESSION | +1.221 |
lp | +1.179 |
ned | +1.169 |
Neg logit contributions | |
�� | -1.132 |
eele | -1.125 |
ogical | -1.108 |
nature | -1.084 |
Dul | -1.045 |
Token | C |
Token ID | 327 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
ILLE | +0.352 |
ctions | +0.335 |
ESSION | +0.333 |
lp | +0.321 |
ned | +0.318 |
Neg logit contributions | |
�� | -0.272 |
eele | -0.271 |
ogical | -0.266 |
nature | -0.261 |
Dul | -0.252 |
Token | eph |
Token ID | 27446 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
ILLE | +0.975 |
ctions | +0.922 |
ESSION | +0.917 |
lp | +0.884 |
ned | +0.873 |
Neg logit contributions | |
�� | -0.881 |
eele | -0.865 |
ogical | -0.852 |
nature | -0.841 |
Dul | -0.821 |
Token | aly |
Token ID | 3400 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
eele | +0.671 |
�� | +0.671 |
ogical | +0.661 |
nature | +0.649 |
Dul | +0.631 |
Neg logit contributions | |
ILLE | -0.759 |
ctions | -0.718 |
ESSION | -0.715 |
lp | -0.687 |
ned | -0.676 |
Token | x |
Token ID | 87 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
�� | +0.015 |
eele | +0.015 |
ogical | +0.015 |
nature | +0.014 |
Dul | +0.014 |
Neg logit contributions | |
ILLE | -0.011 |
ctions | -0.010 |
ESSION | -0.010 |
lp | -0.009 |
ned | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
ILLE | +0.765 |
ctions | +0.728 |
ESSION | +0.721 |
lp | +0.695 |
ned | +0.690 |
Neg logit contributions | |
�� | -0.634 |
eele | -0.630 |
ogical | -0.621 |
nature | -0.607 |
Dul | -0.588 |
Token | their |
Token ID | 511 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ILLE | +0.137 |
ctions | +0.131 |
ESSION | +0.130 |
lp | +0.126 |
ned | +0.124 |
Neg logit contributions | |
eele | -0.092 |
�� | -0.092 |
ogical | -0.091 |
nature | -0.089 |
Dul | -0.085 |
Token | someone |
Token ID | 2130 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
eele | +2.420 |
ogical | +2.400 |
�� | +2.369 |
nature | +2.368 |
Dul | +2.311 |
Neg logit contributions | |
ILLE | -3.237 |
ESSION | -3.088 |
ctions | -3.080 |
lp | -2.965 |
CLE | -2.910 |
Token | � |
Token ID | 447 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
ILLE | +0.775 |
ctions | +0.733 |
ESSION | +0.729 |
lp | +0.701 |
ned | +0.689 |
Neg logit contributions | |
�� | -0.709 |
eele | -0.709 |
ogical | -0.699 |
nature | -0.686 |
Dul | -0.668 |
Token | � |
Token ID | 247 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
�� | +2.013 |
eele | +1.964 |
ogical | +1.957 |
nature | +1.946 |
Dul | +1.903 |
Neg logit contributions | |
ILLE | -1.098 |
ESSION | -1.019 |
ctions | -1.004 |
lp | -0.934 |
ned | -0.926 |
Token | s |
Token ID | 82 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
eele | +2.829 |
ogical | +2.827 |
nature | +2.805 |
�� | +2.779 |
Dul | +2.679 |
Neg logit contributions | |
ILLE | -2.646 |
ESSION | -2.471 |
ctions | -2.418 |
lp | -2.318 |
CLE | -2.304 |
Token | work |
Token ID | 670 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
eele | +0.555 |
�� | +0.553 |
ogical | +0.549 |
nature | +0.538 |
Dul | +0.524 |
Neg logit contributions | |
ILLE | -0.702 |
ctions | -0.665 |
ESSION | -0.664 |
lp | -0.638 |
ned | -0.625 |
Token | , |
Token ID | 11 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
eele | +2.088 |
�� | +2.078 |
ogical | +2.073 |
nature | +2.032 |
Dul | +1.971 |
Neg logit contributions | |
ILLE | -2.498 |
ESSION | -2.343 |
ctions | -2.343 |
lp | -2.256 |
ned | -2.205 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
eele | +1.054 |
ogical | +1.052 |
�� | +1.050 |
nature | +1.032 |
Dul | +1.001 |
Neg logit contributions | |
ILLE | -1.223 |
ESSION | -1.152 |
ctions | -1.151 |
lp | -1.107 |
ned | -1.085 |
Token | your |
Token ID | 534 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
eele | +0.286 |
�� | +0.285 |
ogical | +0.283 |
nature | +0.278 |
Dul | +0.270 |
Neg logit contributions | |
ILLE | -0.314 |
ctions | -0.297 |
ESSION | -0.296 |
lp | -0.284 |
ned | -0.279 |
Token | jaw |
Token ID | 19218 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
eele | +1.637 |
ogical | +1.635 |
�� | +1.616 |
nature | +1.605 |
Dul | +1.554 |
Neg logit contributions | |
ILLE | -1.912 |
ESSION | -1.809 |
ctions | -1.803 |
lp | -1.729 |
ned | -1.694 |
Token | drops |
Token ID | 10532 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ILLE | +0.010 |
ctions | +0.010 |
ESSION | +0.010 |
lp | +0.009 |
ned | +0.009 |
Neg logit contributions | |
eele | -0.009 |
�� | -0.009 |
ogical | -0.009 |
nature | -0.008 |
Dul | -0.008 |
Token | open |
Token ID | 1280 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
eele | +3.339 |
ogical | +3.309 |
nature | +3.222 |
�� | +3.189 |
Sor | +3.155 |
Neg logit contributions | |
ILLE | -4.452 |
ESSION | -4.188 |
ctions | -4.136 |
lp | -4.005 |
CLE | -3.973 |
Token | � |
Token ID | 246 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
ILLE | +0.391 |
ctions | +0.365 |
ESSION | +0.362 |
lp | +0.345 |
ned | +0.338 |
Neg logit contributions | |
eele | -0.523 |
ogical | -0.517 |
�� | -0.514 |
nature | -0.506 |
Dul | -0.498 |
Token | getting |
Token ID | 37210 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
eele | +1.497 |
�� | +1.488 |
ogical | +1.477 |
nature | +1.474 |
Dul | +1.419 |
Neg logit contributions | |
ILLE | -1.240 |
ctions | -1.175 |
ESSION | -1.165 |
lp | -1.111 |
ned | -1.089 |
Token | back |
Token ID | 736 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
ILLE | +0.742 |
ctions | +0.695 |
ESSION | +0.691 |
lp | +0.659 |
ned | +0.646 |
Neg logit contributions | |
eele | -0.909 |
�� | -0.909 |
ogical | -0.897 |
nature | -0.883 |
Dul | -0.862 |
Token | � |
Token ID | 447 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
eele | +0.218 |
�� | +0.217 |
ogical | +0.216 |
nature | +0.211 |
Dul | +0.206 |
Neg logit contributions | |
ILLE | -0.253 |
ctions | -0.240 |
ESSION | -0.239 |
lp | -0.230 |
ned | -0.225 |
Token | � |
Token ID | 247 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
�� | +0.284 |
eele | +0.283 |
ogical | +0.280 |
nature | +0.276 |
Dul | +0.271 |
Neg logit contributions | |
ILLE | -0.140 |
ctions | -0.128 |
ESSION | -0.127 |
lp | -0.119 |
ned | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +9.81e-03 |
Pos logit contributions | |
eele | +0.060 |
�� | +0.060 |
ogical | +0.060 |
nature | +0.059 |
Dul | +0.057 |
Neg logit contributions | |
ILLE | -0.067 |
ctions | -0.063 |
ESSION | -0.063 |
lp | -0.060 |
ned | -0.059 |
Token | � |
Token ID | 564 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
ILLE | +0.028 |
ctions | +0.026 |
ESSION | +0.026 |
lp | +0.025 |
ned | +0.025 |
Neg logit contributions | |
eele | -0.025 |
�� | -0.025 |
ogical | -0.025 |
nature | -0.024 |
Dul | -0.024 |
Token | � |
Token ID | 246 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
�� | +0.814 |
eele | +0.811 |
ogical | +0.801 |
nature | +0.789 |
Dul | +0.771 |
Neg logit contributions | |
ILLE | -0.657 |
ctions | -0.615 |
ESSION | -0.613 |
lp | -0.584 |
ned | -0.572 |
Token | W |
Token ID | 54 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
nature | +2.604 |
eele | +2.600 |
ogical | +2.597 |
�� | +2.560 |
Dul | +2.496 |
Neg logit contributions | |
ILLE | -2.090 |
ctions | -2.004 |
ESSION | -1.983 |
lp | -1.872 |
atown | -1.848 |
Token | inger |
Token ID | 3889 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
eele | +1.918 |
ogical | +1.876 |
�� | +1.856 |
nature | +1.840 |
aiman | +1.804 |
Neg logit contributions | |
ILLE | -1.510 |
ctions | -1.443 |
ESSION | -1.429 |
lp | -1.352 |
ned | -1.340 |
Token | � |
Token ID | 447 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
eele | +0.888 |
�� | +0.881 |
ogical | +0.878 |
nature | +0.860 |
Dul | +0.840 |
Neg logit contributions | |
ILLE | -1.035 |
ctions | -0.980 |
ESSION | -0.978 |
lp | -0.942 |
ned | -0.920 |
Token | seconds |
Token ID | 4201 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ILLE | +3.755 |
ctions | +3.541 |
ESSION | +3.487 |
lp | +3.391 |
ned | +3.378 |
Neg logit contributions | |
�� | -4.145 |
eele | -4.029 |
ogical | -3.929 |
nature | -3.851 |
agine | -3.746 |
Token | after |
Token ID | 706 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
eele | +0.775 |
�� | +0.773 |
ogical | +0.768 |
nature | +0.754 |
Dul | +0.734 |
Neg logit contributions | |
ILLE | -0.918 |
ctions | -0.869 |
ESSION | -0.864 |
lp | -0.833 |
ned | -0.815 |
Token | the |
Token ID | 262 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ILLE | +2.465 |
ctions | +2.349 |
ESSION | +2.347 |
lp | +2.250 |
ned | +2.238 |
Neg logit contributions | |
�� | -1.869 |
eele | -1.833 |
ogical | -1.777 |
nature | -1.738 |
aiman | -1.699 |
Token | validation |
Token ID | 21201 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
ILLE | +0.622 |
ctions | +0.594 |
ESSION | +0.590 |
lp | +0.570 |
ned | +0.562 |
Neg logit contributions | |
�� | -0.424 |
eele | -0.423 |
ogical | -0.413 |
nature | -0.404 |
Dul | -0.390 |
Token | of |
Token ID | 286 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
ILLE | +1.317 |
ctions | +1.259 |
ESSION | +1.249 |
lp | +1.201 |
ned | +1.189 |
Neg logit contributions | |
�� | -1.067 |
eele | -1.053 |
ogical | -1.018 |
nature | -1.011 |
aiman | -0.980 |
Token | the |
Token ID | 262 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
eele | +1.072 |
�� | +1.061 |
ogical | +1.056 |
nature | +1.032 |
Dul | +1.004 |
Neg logit contributions | |
ILLE | -1.647 |
ctions | -1.563 |
ESSION | -1.562 |
lp | -1.510 |
ned | -1.484 |
Token | results |
Token ID | 2482 |
Feature activation | +5.80e-05 |
Pos logit contributions | |
eele | +0.647 |
�� | +0.642 |
ogical | +0.638 |
nature | +0.624 |
Dul | +0.606 |
Neg logit contributions | |
ILLE | -0.955 |
ESSION | -0.907 |
ctions | -0.907 |
lp | -0.875 |
ned | -0.861 |
Token | produced |
Token ID | 4635 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
ILLE | +0.000 |
ctions | +0.000 |
ESSION | +0.000 |
lp | +0.000 |
ned | +0.000 |
Neg logit contributions | |
�� | -0.000 |
eele | -0.000 |
ogical | -0.000 |
nature | -0.000 |
Dul | -0.000 |
Token | in |
Token ID | 287 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
ILLE | +1.620 |
ctions | +1.531 |
ESSION | +1.521 |
lp | +1.464 |
ned | +1.441 |
Neg logit contributions | |
�� | -1.710 |
eele | -1.690 |
ogical | -1.658 |
nature | -1.642 |
Dul | -1.584 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
�� | +0.040 |
eele | +0.040 |
ogical | +0.039 |
nature | +0.038 |
Dul | +0.037 |
Neg logit contributions | |
ILLE | -0.054 |
ctions | -0.052 |
ESSION | -0.052 |
lp | -0.050 |
ned | -0.049 |
Token | unconstitutional |
Token ID | 20727 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
ILLE | +0.603 |
ctions | +0.577 |
ESSION | +0.574 |
lp | +0.554 |
ned | +0.546 |
Neg logit contributions | |
eele | -0.406 |
�� | -0.405 |
ogical | -0.395 |
nature | -0.388 |
Dul | -0.372 |
Token | decades |
Token ID | 4647 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
ILLE | +1.191 |
ctions | +1.126 |
ESSION | +1.109 |
lp | +1.071 |
ned | +1.058 |
Neg logit contributions | |
�� | -1.282 |
eele | -1.267 |
ogical | -1.239 |
nature | -1.230 |
aiman | -1.187 |
Token | . |
Token ID | 13 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
ILLE | +2.018 |
ctions | +1.923 |
ESSION | +1.903 |
lp | +1.830 |
ned | +1.811 |
Neg logit contributions | |
�� | -1.951 |
eele | -1.935 |
ogical | -1.882 |
nature | -1.855 |
Dul | -1.804 |
Token | We |
Token ID | 775 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
eele | +0.111 |
�� | +0.110 |
ogical | +0.110 |
nature | +0.108 |
Dul | +0.105 |
Neg logit contributions | |
ILLE | -0.123 |
ctions | -0.116 |
ESSION | -0.116 |
lp | -0.111 |
ned | -0.109 |
Token | have |
Token ID | 423 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
eele | +0.324 |
�� | +0.324 |
ogical | +0.319 |
nature | +0.313 |
Dul | +0.303 |
Neg logit contributions | |
ILLE | -0.437 |
ctions | -0.415 |
ESSION | -0.414 |
lp | -0.398 |
ned | -0.392 |
Token | to |
Token ID | 284 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ILLE | +0.369 |
ctions | +0.351 |
ESSION | +0.348 |
lp | +0.336 |
ned | +0.332 |
Neg logit contributions | |
�� | -0.289 |
eele | -0.288 |
ogical | -0.282 |
nature | -0.277 |
Dul | -0.268 |
Token | utterly |
Token ID | 15950 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ILLE | +1.464 |
ctions | +1.396 |
ESSION | +1.381 |
lp | +1.335 |
ned | +1.322 |
Neg logit contributions | |
�� | -1.274 |
eele | -1.262 |
ogical | -1.235 |
nature | -1.216 |
Dul | -1.174 |
Token | destroy |
Token ID | 4117 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ogical | +2.730 |
eele | +2.709 |
nature | +2.639 |
Dul | +2.621 |
�� | +2.604 |
Neg logit contributions | |
ILLE | -3.521 |
ESSION | -3.370 |
ctions | -3.345 |
lp | -3.194 |
ned | -3.101 |
Token | the |
Token ID | 262 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
eele | +0.750 |
�� | +0.747 |
ogical | +0.738 |
nature | +0.721 |
Dul | +0.699 |
Neg logit contributions | |
ILLE | -1.194 |
ctions | -1.138 |
ESSION | -1.134 |
lp | -1.096 |
ned | -1.078 |
Token | capitalist |
Token ID | 15098 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
eele | +0.614 |
�� | +0.610 |
ogical | +0.606 |
nature | +0.592 |
Dul | +0.577 |
Neg logit contributions | |
ILLE | -0.870 |
ctions | -0.827 |
ESSION | -0.826 |
lp | -0.795 |
ned | -0.782 |
Token | world |
Token ID | 995 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ILLE | +0.471 |
ctions | +0.449 |
ESSION | +0.446 |
lp | +0.430 |
ned | +0.425 |
Neg logit contributions | |
�� | -0.350 |
eele | -0.348 |
ogical | -0.341 |
nature | -0.335 |
Dul | -0.324 |
Token | order |
Token ID | 1502 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
ILLE | +0.532 |
ctions | +0.512 |
ESSION | +0.509 |
lp | +0.494 |
ned | +0.490 |
Neg logit contributions | |
�� | -0.237 |
eele | -0.234 |
ogical | -0.228 |
nature | -0.221 |
Dul | -0.211 |
Token | writer |
Token ID | 6260 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
eele | +1.848 |
�� | +1.821 |
ogical | +1.812 |
nature | +1.777 |
Dul | +1.750 |
Neg logit contributions | |
ILLE | -2.531 |
ctions | -2.406 |
ESSION | -2.405 |
lp | -2.305 |
CLE | -2.256 |
Token | could |
Token ID | 714 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
ILLE | +0.979 |
ctions | +0.935 |
ESSION | +0.925 |
lp | +0.897 |
ned | +0.891 |
Neg logit contributions | |
�� | -0.708 |
eele | -0.701 |
ogical | -0.686 |
nature | -0.671 |
Dul | -0.645 |
Token | pay |
Token ID | 1414 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
�� | +0.737 |
eele | +0.733 |
ogical | +0.719 |
nature | +0.703 |
Dul | +0.682 |
Neg logit contributions | |
ILLE | -1.108 |
ctions | -1.056 |
ESSION | -1.050 |
lp | -1.017 |
ned | -1.004 |
Token | would |
Token ID | 561 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
eele | +2.631 |
�� | +2.600 |
ogical | +2.594 |
nature | +2.519 |
Dul | +2.489 |
Neg logit contributions | |
ILLE | -3.798 |
ctions | -3.630 |
ESSION | -3.602 |
lp | -3.480 |
CLE | -3.401 |
Token | be |
Token ID | 307 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
eele | +0.894 |
�� | +0.890 |
ogical | +0.880 |
nature | +0.868 |
Dul | +0.844 |
Neg logit contributions | |
ILLE | -0.906 |
ctions | -0.859 |
ESSION | -0.849 |
lp | -0.818 |
ned | -0.808 |
Token | to |
Token ID | 284 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
�� | +0.749 |
eele | +0.746 |
ogical | +0.734 |
nature | +0.722 |
Dul | +0.698 |
Neg logit contributions | |
ILLE | -0.925 |
ctions | -0.875 |
ESSION | -0.871 |
lp | -0.839 |
ned | -0.828 |
Token | ur |
Token ID | 2956 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
�� | +0.057 |
eele | +0.057 |
ogical | +0.056 |
nature | +0.055 |
Dul | +0.052 |
Neg logit contributions | |
ILLE | -0.079 |
ctions | -0.075 |
ESSION | -0.075 |
lp | -0.072 |
ned | -0.071 |
Token | inate |
Token ID | 4559 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
eele | +3.865 |
ogical | +3.853 |
�� | +3.840 |
nature | +3.787 |
Dul | +3.729 |
Neg logit contributions | |
ILLE | -2.550 |
ESSION | -2.419 |
ctions | -2.360 |
ned | -2.187 |
lp | -2.167 |
Token | on |
Token ID | 319 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
eele | +0.437 |
�� | +0.437 |
ogical | +0.433 |
nature | +0.424 |
Dul | +0.414 |
Neg logit contributions | |
ILLE | -0.464 |
ctions | -0.438 |
ESSION | -0.437 |
lp | -0.418 |
ned | -0.411 |
Token | his |
Token ID | 465 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
eele | +1.321 |
�� | +1.317 |
ogical | +1.302 |
nature | +1.271 |
Dul | +1.234 |
Neg logit contributions | |
ILLE | -2.124 |
ctions | -2.028 |
ESSION | -2.018 |
lp | -1.950 |
ned | -1.919 |
Token | tomb |
Token ID | 22234 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
eele | +0.777 |
�� | +0.773 |
ogical | +0.767 |
nature | +0.752 |
Dul | +0.738 |
Neg logit contributions | |
ILLE | -0.977 |
ctions | -0.926 |
ESSION | -0.925 |
lp | -0.887 |
ned | -0.871 |
Token | m |
Token ID | 285 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
ILLE | +0.854 |
ctions | +0.807 |
ESSION | +0.800 |
lp | +0.776 |
ned | +0.762 |
Neg logit contributions | |
�� | -0.801 |
eele | -0.797 |
ogical | -0.784 |
nature | -0.771 |
Dul | -0.746 |
Token | ai |
Token ID | 1872 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
eele | +0.738 |
�� | +0.730 |
ogical | +0.727 |
nature | +0.712 |
Dul | +0.692 |
Neg logit contributions | |
ILLE | -0.868 |
ESSION | -0.820 |
ctions | -0.820 |
lp | -0.777 |
CLE | -0.767 |
Token | ana |
Token ID | 44763 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ILLE | +1.162 |
ctions | +1.100 |
ESSION | +1.088 |
lp | +1.057 |
ned | +1.037 |
Neg logit contributions | |
�� | -1.102 |
eele | -1.095 |
ogical | -1.078 |
nature | -1.059 |
Dul | -1.026 |
Token | . |
Token ID | 13 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
eele | +3.853 |
ogical | +3.833 |
�� | +3.786 |
nature | +3.718 |
Dul | +3.707 |
Neg logit contributions | |
ILLE | -4.303 |
ESSION | -4.115 |
ctions | -4.042 |
lp | -3.814 |
CLE | -3.772 |
Token | E |
Token ID | 412 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
eele | +1.203 |
�� | +1.197 |
ogical | +1.185 |
nature | +1.163 |
Dul | +1.140 |
Neg logit contributions | |
ILLE | -1.573 |
ctions | -1.491 |
ESSION | -1.489 |
lp | -1.427 |
ned | -1.403 |
Token | p |
Token ID | 279 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
eele | +4.222 |
ogical | +4.158 |
�� | +4.109 |
nature | +4.060 |
Dul | +4.060 |
Neg logit contributions | |
ILLE | -4.623 |
ESSION | -4.447 |
ctions | -4.360 |
lp | -4.080 |
CLE | -4.078 |
Token | au |
Token ID | 559 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
eele | +5.576 |
ogical | +5.540 |
aiman | +5.315 |
agine | +5.311 |
nature | +5.311 |
Neg logit contributions | |
ILLE | -6.117 |
ESSION | -5.785 |
ctions | -5.700 |
CLE | -5.440 |
lp | -5.259 |
Token | ka |
Token ID | 38387 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
eele | +2.780 |
ogical | +2.762 |
�� | +2.733 |
nature | +2.688 |
Dul | +2.658 |
Neg logit contributions | |
ILLE | -2.957 |
ESSION | -2.828 |
ctions | -2.769 |
CLE | -2.615 |
lp | -2.599 |
Token | p |
Token ID | 279 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
eele | +2.997 |
�� | +2.963 |
ogical | +2.955 |
nature | +2.886 |
Dul | +2.882 |
Neg logit contributions | |
ILLE | -3.233 |
ESSION | -3.088 |
ctions | -3.060 |
lp | -2.876 |
CLE | -2.844 |
Token | ā |
Token ID | 10235 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
eele | +4.405 |
ogical | +4.343 |
�� | +4.261 |
nature | +4.200 |
aiman | +4.160 |
Neg logit contributions | |
ILLE | -5.058 |
ESSION | -4.829 |
ctions | -4.778 |
CLE | -4.534 |
lp | -4.426 |
Token | h |
Token ID | 71 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
ILLE | +0.664 |
ctions | +0.628 |
ESSION | +0.622 |
lp | +0.603 |
ned | +0.590 |
Neg logit contributions | |
�� | -0.636 |
eele | -0.635 |
ogical | -0.626 |
nature | -0.614 |
Dul | -0.598 |
Token | H |
Token ID | 367 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ILLE | +2.177 |
ctions | +2.096 |
ESSION | +2.065 |
lp | +2.015 |
ned | +2.000 |
Neg logit contributions | |
�� | -1.598 |
eele | -1.577 |
ogical | -1.529 |
nature | -1.501 |
aiman | -1.428 |
Token | ü |
Token ID | 9116 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
ILLE | +0.694 |
ctions | +0.658 |
ESSION | +0.655 |
lp | +0.631 |
ned | +0.621 |
Neg logit contributions | |
�� | -0.580 |
eele | -0.579 |
ogical | -0.570 |
nature | -0.560 |
Dul | -0.544 |
Token | leg |
Token ID | 1455 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
ILLE | +2.156 |
ctions | +2.051 |
ESSION | +2.002 |
lp | +1.989 |
ned | +1.957 |
Neg logit contributions | |
�� | -2.162 |
eele | -2.149 |
ogical | -2.108 |
nature | -2.055 |
Dul | -2.009 |
Token | ü |
Token ID | 9116 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
ILLE | +2.044 |
ctions | +1.948 |
ESSION | +1.925 |
lp | +1.882 |
ned | +1.861 |
Neg logit contributions | |
�� | -1.751 |
eele | -1.729 |
ogical | -1.690 |
nature | -1.662 |
Dul | -1.601 |
Token | .[ |
Token ID | 3693 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
ILLE | +0.733 |
ctions | +0.693 |
ESSION | +0.685 |
lp | +0.665 |
ned | +0.654 |
Neg logit contributions | |
�� | -0.723 |
eele | -0.720 |
ogical | -0.707 |
nature | -0.695 |
Dul | -0.675 |
Token | 6 |
Token ID | 21 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
eele | +2.012 |
�� | +2.002 |
ogical | +1.987 |
nature | +1.960 |
Dul | +1.899 |
Neg logit contributions | |
ILLE | -2.212 |
ctions | -2.097 |
ESSION | -2.084 |
lp | -1.996 |
ned | -1.957 |
Token | ] |
Token ID | 60 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
eele | +4.230 |
�� | +4.201 |
ogical | +4.189 |
nature | +4.062 |
Dul | +3.944 |
Neg logit contributions | |
ILLE | -6.521 |
ESSION | -6.174 |
ctions | -6.160 |
lp | -5.881 |
ned | -5.823 |
Token |
|
Token ID | 198 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ILLE | +1.884 |
ctions | +1.790 |
ESSION | +1.772 |
lp | +1.711 |
ned | +1.686 |
Neg logit contributions | |
�� | -1.919 |
eele | -1.889 |
ogical | -1.847 |
nature | -1.817 |
agine | -1.758 |
Token |
|
Token ID | 198 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
eele | +0.602 |
ogical | +0.598 |
nature | +0.591 |
�� | +0.581 |
Dul | +0.573 |
Neg logit contributions | |
ILLE | -0.672 |
ESSION | -0.633 |
ctions | -0.630 |
lp | -0.601 |
atown | -0.591 |
Token | From |
Token ID | 4863 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
ILLE | +0.617 |
ctions | +0.579 |
ESSION | +0.576 |
lp | +0.551 |
ned | +0.540 |
Neg logit contributions | |
�� | -0.711 |
eele | -0.710 |
ogical | -0.699 |
nature | -0.687 |
Dul | -0.672 |
Token | the |
Token ID | 262 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
ILLE | +2.812 |
ctions | +2.692 |
ESSION | +2.684 |
lp | +2.587 |
ned | +2.545 |
Neg logit contributions | |
�� | -2.216 |
eele | -2.174 |
ogical | -2.115 |
nature | -2.085 |
aiman | -2.003 |
Token | population |
Token ID | 3265 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
eele | +2.266 |
ogical | +2.255 |
nature | +2.213 |
Dul | +2.183 |
�� | +2.180 |
Neg logit contributions | |
ILLE | -2.360 |
ESSION | -2.226 |
ctions | -2.171 |
lp | -2.134 |
atown | -2.070 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ILLE | +0.109 |
ctions | +0.103 |
ESSION | +0.102 |
lp | +0.099 |
ned | +0.097 |
Neg logit contributions | |
eele | -0.096 |
�� | -0.096 |
ogical | -0.095 |
nature | -0.093 |
Dul | -0.090 |
Token | � |
Token ID | 447 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
eele | +0.633 |
�� | +0.627 |
ogical | +0.623 |
nature | +0.613 |
Dul | +0.599 |
Neg logit contributions | |
ILLE | -0.719 |
ctions | -0.679 |
ESSION | -0.678 |
lp | -0.651 |
ned | -0.640 |
Token | � |
Token ID | 251 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
�� | +1.112 |
eele | +1.110 |
ogical | +1.098 |
nature | +1.082 |
Dul | +1.060 |
Neg logit contributions | |
ILLE | -0.665 |
ctions | -0.614 |
ESSION | -0.611 |
lp | -0.576 |
ned | -0.562 |
Token | [ |
Token ID | 58 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
ILLE | +1.295 |
ctions | +1.226 |
ESSION | +1.219 |
lp | +1.170 |
ned | +1.154 |
Neg logit contributions | |
�� | -1.180 |
eele | -1.173 |
ogical | -1.152 |
nature | -1.131 |
aiman | -1.095 |
Token | 8 |
Token ID | 23 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
eele | +2.129 |
nature | +2.121 |
ogical | +2.102 |
Dul | +2.035 |
Sor | +2.007 |
Neg logit contributions | |
ILLE | -1.968 |
ctions | -1.885 |
ESSION | -1.859 |
atown | -1.755 |
lp | -1.755 |
Token | ] |
Token ID | 60 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
ogical | +2.893 |
eele | +2.858 |
nature | +2.838 |
Sor | +2.759 |
Dul | +2.757 |
Neg logit contributions | |
ILLE | -5.617 |
ESSION | -5.316 |
ctions | -5.187 |
atown | -5.023 |
lp | -4.969 |
Token | Chevron |
Token ID | 50083 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
ILLE | +2.357 |
ctions | +2.234 |
ESSION | +2.209 |
lp | +2.132 |
ned | +2.088 |
Neg logit contributions | |
�� | -2.450 |
eele | -2.406 |
ogical | -2.371 |
nature | -2.320 |
aiman | -2.255 |
Token | eventually |
Token ID | 4191 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
ILLE | +2.360 |
ctions | +2.242 |
ESSION | +2.200 |
lp | +2.129 |
ned | +2.112 |
Neg logit contributions | |
�� | -2.091 |
eele | -2.060 |
ogical | -2.019 |
nature | -1.983 |
Dul | -1.918 |
Token | signed |
Token ID | 4488 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ILLE | +1.759 |
ctions | +1.676 |
ESSION | +1.659 |
lp | +1.604 |
ned | +1.588 |
Neg logit contributions | |
�� | -1.391 |
eele | -1.383 |
ogical | -1.352 |
nature | -1.329 |
Dul | -1.285 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
eele | +0.850 |
�� | +0.847 |
ogical | +0.835 |
nature | +0.818 |
Dul | +0.794 |
Neg logit contributions | |
ILLE | -1.211 |
ctions | -1.152 |
ESSION | -1.149 |
lp | -1.107 |
ned | -1.089 |
Token | .[ |
Token ID | 3693 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
ILLE | +2.399 |
ctions | +2.286 |
ESSION | +2.275 |
lp | +2.203 |
ned | +2.182 |
Neg logit contributions | |
�� | -2.375 |
eele | -2.355 |
ogical | -2.285 |
nature | -2.248 |
aiman | -2.170 |
Token | 31 |
Token ID | 3132 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
eele | +1.219 |
�� | +1.213 |
ogical | +1.199 |
nature | +1.181 |
Dul | +1.146 |
Neg logit contributions | |
ILLE | -1.486 |
ctions | -1.408 |
ESSION | -1.402 |
lp | -1.347 |
ned | -1.323 |
Token | ][ |
Token ID | 7131 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
eele | +2.120 |
�� | +2.117 |
ogical | +2.087 |
nature | +2.042 |
Dul | +1.981 |
Neg logit contributions | |
ILLE | -2.830 |
ctions | -2.685 |
ESSION | -2.678 |
lp | -2.574 |
ned | -2.536 |
Token | 32 |
Token ID | 2624 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
�� | +1.326 |
eele | +1.324 |
ogical | +1.307 |
nature | +1.284 |
Dul | +1.257 |
Neg logit contributions | |
ILLE | -1.091 |
ctions | -1.021 |
ESSION | -1.017 |
lp | -0.971 |
ned | -0.951 |
Token | ][ |
Token ID | 7131 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
�� | +3.637 |
eele | +3.637 |
ogical | +3.605 |
nature | +3.499 |
Dul | +3.396 |
Neg logit contributions | |
ILLE | -5.105 |
ESSION | -4.830 |
ctions | -4.817 |
lp | -4.598 |
ned | -4.532 |
Token | 33 |
Token ID | 2091 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
�� | +1.228 |
eele | +1.226 |
ogical | +1.208 |
nature | +1.184 |
Dul | +1.155 |
Neg logit contributions | |
ILLE | -1.298 |
ctions | -1.226 |
ESSION | -1.220 |
lp | -1.174 |
ned | -1.153 |
Token | ] |
Token ID | 60 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
�� | +3.590 |
eele | +3.587 |
ogical | +3.538 |
nature | +3.462 |
Dul | +3.363 |
Neg logit contributions | |
ILLE | -4.770 |
ESSION | -4.513 |
ctions | -4.503 |
lp | -4.300 |
ned | -4.239 |
Token |
|
Token ID | 198 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ILLE | +2.367 |
ctions | +2.240 |
ESSION | +2.214 |
lp | +2.139 |
ned | +2.111 |
Neg logit contributions | |
�� | -2.599 |
eele | -2.550 |
ogical | -2.513 |
nature | -2.469 |
aiman | -2.407 |
Token |
|
Token ID | 198 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
eele | +0.858 |
ogical | +0.853 |
nature | +0.844 |
Sor | +0.818 |
�� | +0.818 |
Neg logit contributions | |
ILLE | -0.984 |
ESSION | -0.928 |
ctions | -0.921 |
lp | -0.879 |
atown | -0.870 |
Token | On |
Token ID | 2202 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ILLE | +0.204 |
ctions | +0.192 |
ESSION | +0.191 |
lp | +0.182 |
ned | +0.178 |
Neg logit contributions | |
eele | -0.245 |
�� | -0.245 |
ogical | -0.242 |
nature | -0.238 |
Dul | -0.233 |
Token | 29 |
Token ID | 2808 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
eele | +0.370 |
�� | +0.369 |
ogical | +0.364 |
nature | +0.356 |
Dul | +0.345 |
Neg logit contributions | |
ILLE | -0.526 |
ctions | -0.501 |
ESSION | -0.499 |
lp | -0.481 |
ned | -0.474 |
Token | making |
Token ID | 1642 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
ILLE | +1.192 |
ctions | +1.133 |
ESSION | +1.124 |
lp | +1.084 |
ned | +1.068 |
Neg logit contributions | |
�� | -1.044 |
eele | -1.042 |
ogical | -1.018 |
nature | -1.002 |
Dul | -0.972 |
Token | bilingual |
Token ID | 48116 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ILLE | +0.196 |
ctions | +0.186 |
ESSION | +0.185 |
lp | +0.178 |
ned | +0.175 |
Neg logit contributions | |
eele | -0.171 |
�� | -0.170 |
ogical | -0.168 |
nature | -0.165 |
Dul | -0.161 |
Token | ism |
Token ID | 1042 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
ILLE | +5.082 |
ctions | +4.918 |
ESSION | +4.845 |
ned | +4.677 |
lp | +4.633 |
Neg logit contributions | |
�� | -4.251 |
eele | -4.152 |
nature | -3.968 |
ogical | -3.941 |
aiman | -3.850 |
Token | for |
Token ID | 329 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ILLE | +1.354 |
ctions | +1.285 |
ESSION | +1.282 |
lp | +1.235 |
ned | +1.214 |
Neg logit contributions | |
eele | -1.012 |
�� | -1.009 |
ogical | -0.997 |
nature | -0.976 |
Dul | -0.948 |
Token | all |
Token ID | 477 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
ILLE | +1.031 |
ctions | +0.978 |
ESSION | +0.974 |
lp | +0.937 |
ned | +0.927 |
Neg logit contributions | |
�� | -0.788 |
eele | -0.786 |
ogical | -0.771 |
nature | -0.757 |
Dul | -0.731 |
Token | positions |
Token ID | 6116 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ogical | +1.458 |
eele | +1.456 |
�� | +1.448 |
nature | +1.411 |
Dul | +1.391 |
Neg logit contributions | |
ILLE | -2.064 |
ctions | -1.952 |
ESSION | -1.950 |
lp | -1.896 |
atown | -1.844 |
Token | unnecessary |
Token ID | 13114 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ogical | +3.545 |
eele | +3.478 |
nature | +3.391 |
Sor | +3.380 |
�� | +3.376 |
Neg logit contributions | |
ILLE | -4.551 |
ESSION | -4.407 |
ctions | -4.278 |
lp | -4.155 |
atown | -4.045 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ILLE | +0.587 |
ctions | +0.556 |
ESSION | +0.552 |
lp | +0.531 |
ned | +0.523 |
Neg logit contributions | |
�� | -0.538 |
eele | -0.536 |
ogical | -0.527 |
nature | -0.518 |
Dul | -0.503 |
Token | ( |
Token ID | 357 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
ILLE | +0.430 |
ctions | +0.408 |
ESSION | +0.405 |
lp | +0.390 |
ned | +0.383 |
Neg logit contributions | |
�� | -0.385 |
eele | -0.384 |
ogical | -0.378 |
nature | -0.371 |
Dul | -0.359 |
Token | CBC |
Token ID | 29208 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ILLE | +1.328 |
ESSION | +1.254 |
ctions | +1.251 |
lp | +1.203 |
ned | +1.184 |
Neg logit contributions | |
�� | -1.146 |
eele | -1.142 |
ogical | -1.121 |
nature | -1.092 |
aiman | -1.065 |
Token | ) |
Token ID | 8 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
�� | +1.066 |
eele | +1.064 |
ogical | +1.047 |
nature | +1.025 |
Dul | +0.997 |
Neg logit contributions | |
ILLE | -1.220 |
ctions | -1.155 |
ESSION | -1.148 |
lp | -1.106 |
ned | -1.087 |