Token | — |
Token ID | 851 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
entary | +0.537 |
itary | +0.512 |
itialized | +0.496 |
FIG | +0.479 |
Feder | +0.477 |
Neg logit contributions | |
Harding | -0.503 |
Typhoon | -0.502 |
Anth | -0.485 |
Deng | -0.480 |
+. | -0.471 |
Token | Dan |
Token ID | 6035 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
entary | +1.559 |
itary | +1.485 |
itialized | +1.448 |
Feder | +1.406 |
FIG | +1.379 |
Neg logit contributions | |
Harding | -1.425 |
Typhoon | -1.424 |
Anth | -1.386 |
Deng | -1.351 |
ype | -1.345 |
Token | Mer |
Token ID | 4638 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Feder | +4.124 |
entary | +4.035 |
itary | +3.763 |
itialized | +3.290 |
igned | +3.192 |
Neg logit contributions | |
Typhoon | -12.696 |
Harding | -12.400 |
+. | -12.375 |
Anth | -12.167 |
vu | -11.956 |
Token | ica |
Token ID | 3970 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
Harding | +0.160 |
Typhoon | +0.159 |
Anth | +0.155 |
Deng | +0.153 |
+. | +0.152 |
Neg logit contributions | |
entary | -0.109 |
itary | -0.102 |
itialized | -0.098 |
FIG | -0.093 |
Feder | -0.093 |
Token | (@ |
Token ID | 4275 |
Feature activation | +2.17e+01 |
Pos logit contributions | |
entary | +2.317 |
itary | +2.214 |
Feder | +2.133 |
itialized | +2.089 |
FIG | +2.075 |
Neg logit contributions | |
Typhoon | -3.054 |
Harding | -3.045 |
Anth | -2.957 |
Deng | -2.907 |
+. | -2.882 |
Token | dan |
Token ID | 25604 |
Feature activation | +2.88e+01 |
Pos logit contributions | |
rek | +3.194 |
ilan | +3.136 |
entary | +3.091 |
itary | +2.607 |
lis | +2.509 |
Neg logit contributions | |
Typhoon | -23.614 |
Harding | -22.602 |
Hut | -22.162 |
Booth | -21.375 |
Thro | -21.360 |
Token | meric |
Token ID | 946 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
itary | +8.132 |
entary | +7.768 |
meric | +7.564 |
ilan | +7.109 |
ear | +6.672 |
Neg logit contributions | |
Typhoon | -26.610 |
Harding | -25.090 |
Hut | -24.028 |
Deng | -23.665 |
Booth | -23.357 |
Token | a |
Token ID | 64 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
Harding | +0.478 |
Typhoon | +0.475 |
Anth | +0.460 |
Deng | +0.455 |
ype | +0.448 |
Neg logit contributions | |
entary | -0.550 |
itary | -0.523 |
itialized | -0.511 |
FIG | -0.490 |
Feder | -0.489 |
Token | CNN |
Token ID | 18474 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
FIG | +6.286 |
Feder | +5.370 |
entary | +5.324 |
Coin | +5.172 |
SIGN | +5.148 |
Neg logit contributions | |
Typhoon | -13.978 |
Harding | -13.468 |
+. | -12.727 |
Zeal | -12.636 |
Avery | -12.615 |
Token | ) |
Token ID | 8 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
FIG | +5.587 |
Feder | +5.434 |
entary | +5.392 |
itary | +5.323 |
igned | +5.046 |
Neg logit contributions | |
Typhoon | -12.988 |
Harding | -12.983 |
vertisement | -12.625 |
Anth | -12.625 |
exha | -12.620 |
Token | October |
Token ID | 3267 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
Harding | +0.426 |
Typhoon | +0.425 |
Anth | +0.410 |
Deng | +0.406 |
+. | +0.400 |
Neg logit contributions | |
entary | -0.436 |
itary | -0.414 |
itialized | -0.403 |
FIG | -0.386 |
Feder | -0.385 |
Token | the |
Token ID | 262 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
entary | +6.357 |
itary | +6.073 |
Feder | +6.009 |
wastes | +5.709 |
itialized | +5.685 |
Neg logit contributions | |
Anth | -7.040 |
Typhoon | -7.033 |
Harding | -6.850 |
+. | -6.702 |
ype | -6.613 |
Token | Sessions |
Token ID | 15184 |
Feature activation | +2.09e+01 |
Pos logit contributions | |
entary | +8.793 |
Feder | +8.555 |
itary | +8.383 |
wastes | +8.293 |
mockery | +8.169 |
Neg logit contributions | |
Anth | -8.627 |
Typhoon | -8.594 |
Harding | -8.177 |
ype | -8.097 |
+. | -8.092 |
Token | - |
Token ID | 12 |
Feature activation | +2.25e+01 |
Pos logit contributions | |
entary | +12.208 |
itary | +11.446 |
Feder | +11.375 |
wastes | +11.261 |
igned | +11.183 |
Neg logit contributions | |
Typhoon | -12.812 |
Anth | -12.273 |
Harding | -12.111 |
Deng | -11.726 |
~~~~ | -11.650 |
Token | R |
Token ID | 49 |
Feature activation | +1.65e+01 |
Pos logit contributions | |
FIG | +11.503 |
ear | +11.387 |
itary | +11.131 |
entary | +11.108 |
IRC | +10.925 |
Neg logit contributions | |
Typhoon | -15.675 |
Deng | -13.778 |
Harding | -13.597 |
Horizon | -13.568 |
TT | -13.364 |
Token | osen |
Token ID | 5233 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
ear | +3.382 |
entary | +3.018 |
itary | +2.884 |
igned | +2.715 |
lis | +2.049 |
Neg logit contributions | |
Typhoon | -20.075 |
Harding | -18.244 |
Anth | -18.227 |
Deng | -18.154 |
psi | -17.716 |
Token | stein |
Token ID | 5714 |
Feature activation | +2.86e+01 |
Pos logit contributions | |
itary | +6.326 |
entary | +6.259 |
igned | +5.929 |
itialized | +5.850 |
FIG | +5.848 |
Neg logit contributions | |
Typhoon | -6.129 |
Anth | -5.864 |
Harding | -5.811 |
ype | -5.508 |
Deng | -5.466 |
Token | recommendation |
Token ID | 15602 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
entary | +14.824 |
Feder | +14.619 |
wastes | +14.296 |
mockery | +14.196 |
itary | +14.114 |
Neg logit contributions | |
Typhoon | -15.286 |
Anth | -14.537 |
Harding | -13.544 |
atus | -13.489 |
vu | -13.477 |
Token | to |
Token ID | 284 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
entary | +3.955 |
itary | +3.807 |
Feder | +3.626 |
wastes | +3.554 |
itialized | +3.547 |
Neg logit contributions | |
Typhoon | -3.737 |
Harding | -3.713 |
Anth | -3.690 |
ype | -3.535 |
Deng | -3.507 |
Token | explain |
Token ID | 4727 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
entary | +4.588 |
itary | +4.397 |
Feder | +4.286 |
itialized | +4.203 |
FIG | +4.112 |
Neg logit contributions | |
Typhoon | -4.325 |
Harding | -4.229 |
Anth | -4.206 |
+. | -4.090 |
ype | -4.049 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
entary | +4.416 |
itary | +4.226 |
Feder | +4.069 |
itialized | +3.945 |
wastes | +3.900 |
Neg logit contributions | |
Typhoon | -4.797 |
Anth | -4.708 |
Harding | -4.665 |
ype | -4.490 |
Deng | -4.472 |
Token | decision |
Token ID | 2551 |
Feature activation | +7.75e+00 |
Pos logit contributions | |
entary | +7.650 |
itary | +7.434 |
Feder | +7.395 |
wastes | +7.256 |
mockery | +7.146 |
Neg logit contributions | |
Typhoon | -8.131 |
Anth | -7.932 |
Harding | -7.668 |
ype | -7.635 |
+. | -7.589 |
Token | to |
Token ID | 284 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
entary | +5.501 |
itary | +5.195 |
Feder | +5.023 |
itialized | +4.899 |
FIG | +4.886 |
Neg logit contributions | |
Typhoon | -5.966 |
Anth | -5.959 |
Harding | -5.884 |
ype | -5.614 |
Deng | -5.612 |
Token | power |
Token ID | 1176 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
entary | +7.779 |
itary | +7.262 |
FIG | +7.228 |
Feder | +7.158 |
itialized | +7.135 |
Neg logit contributions | |
Anth | -8.574 |
Harding | -8.491 |
Typhoon | -8.384 |
Deng | -8.010 |
ype | -7.892 |
Token | management |
Token ID | 4542 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
entary | +2.111 |
itary | +2.004 |
itialized | +1.959 |
FIG | +1.886 |
Feder | +1.881 |
Neg logit contributions | |
Harding | -2.065 |
Typhoon | -2.056 |
Anth | -2.017 |
Deng | -1.965 |
ype | -1.929 |
Token | . |
Token ID | 13 |
Feature activation | +8.25e+00 |
Pos logit contributions | |
entary | +0.824 |
itary | +0.784 |
itialized | +0.760 |
Feder | +0.736 |
FIG | +0.735 |
Neg logit contributions | |
Harding | -0.706 |
Typhoon | -0.705 |
Anth | -0.684 |
Deng | -0.672 |
ype | -0.658 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
entary | +5.690 |
itary | +5.296 |
itialized | +5.165 |
Feder | +5.136 |
FIG | +5.074 |
Neg logit contributions | |
Harding | -5.851 |
Anth | -5.849 |
Typhoon | -5.833 |
Deng | -5.562 |
ype | -5.478 |
Token |
|
Token ID | 198 |
Feature activation | +2.73e+01 |
Pos logit contributions | |
entary | +1.527 |
itary | +1.469 |
itialized | +1.403 |
FIG | +1.384 |
Feder | +1.378 |
Neg logit contributions | |
Harding | -1.501 |
Typhoon | -1.495 |
Anth | -1.446 |
Deng | -1.424 |
ype | -1.392 |
Token | sudo |
Token ID | 24032 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
FIG | +16.564 |
entary | +16.474 |
itary | +15.709 |
lis | +15.294 |
igned | +14.917 |
Neg logit contributions | |
Harding | -14.181 |
Typhoon | -13.939 |
Deng | -13.708 |
Kass | -12.525 |
Anth | -12.397 |
Token | i |
Token ID | 1312 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
entary | +8.002 |
itary | +7.357 |
Feder | +7.094 |
itialized | +7.068 |
wastes | +7.049 |
Neg logit contributions | |
Anth | -8.119 |
Harding | -8.102 |
Typhoon | -8.063 |
Deng | -7.679 |
ype | -7.415 |
Token | w |
Token ID | 86 |
Feature activation | +7.53e+00 |
Pos logit contributions | |
entary | +7.008 |
itary | +6.423 |
itialized | +5.776 |
ilan | +5.774 |
FIG | +5.745 |
Neg logit contributions | |
Typhoon | -12.946 |
Anth | -12.870 |
Harding | -12.642 |
Deng | -12.295 |
Avery | -11.616 |
Token | config |
Token ID | 11250 |
Feature activation | +9.98e+00 |
Pos logit contributions | |
entary | +4.208 |
itary | +3.938 |
itialized | +3.759 |
FIG | +3.632 |
Feder | +3.603 |
Neg logit contributions | |
Harding | -6.515 |
Typhoon | -6.462 |
Anth | -6.400 |
Deng | -6.221 |
+. | -6.030 |
Token | w |
Token ID | 266 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
entary | +7.178 |
itary | +6.656 |
itialized | +6.559 |
FIG | +6.513 |
Feder | +6.479 |
Neg logit contributions | |
Harding | -6.709 |
Anth | -6.676 |
Typhoon | -6.574 |
Deng | -6.316 |
ype | -6.015 |
Token | centre |
Token ID | 7372 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
entary | +3.478 |
itary | +3.322 |
itialized | +3.203 |
Feder | +3.171 |
wastes | +3.106 |
Neg logit contributions | |
Harding | -3.706 |
Typhoon | -3.698 |
Anth | -3.652 |
+. | -3.542 |
Deng | -3.526 |
Token | of |
Token ID | 286 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Harding | +0.978 |
Typhoon | +0.976 |
Anth | +0.945 |
Deng | +0.938 |
+. | +0.926 |
Neg logit contributions | |
entary | -0.814 |
itary | -0.772 |
itialized | -0.744 |
FIG | -0.710 |
Feder | -0.708 |
Token | the |
Token ID | 262 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Typhoon | +1.663 |
Harding | +1.659 |
Deng | +1.591 |
Anth | +1.572 |
+. | +1.541 |
Neg logit contributions | |
entary | -1.758 |
itary | -1.680 |
itialized | -1.626 |
FIG | -1.574 |
Feder | -1.537 |
Token | debate |
Token ID | 4384 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
Typhoon | +2.144 |
Harding | +2.128 |
Deng | +2.044 |
Anth | +2.016 |
+. | +1.985 |
Neg logit contributions | |
entary | -2.310 |
itary | -2.210 |
itialized | -2.129 |
FIG | -2.069 |
Feder | -2.006 |
Token | , |
Token ID | 11 |
Feature activation | +7.90e+00 |
Pos logit contributions | |
entary | +2.934 |
itary | +2.807 |
Feder | +2.657 |
itialized | +2.654 |
wastes | +2.651 |
Neg logit contributions | |
Harding | -2.730 |
Typhoon | -2.730 |
Anth | -2.707 |
Deng | -2.608 |
ype | -2.604 |
Token | seems |
Token ID | 2331 |
Feature activation | +2.70e+01 |
Pos logit contributions | |
entary | +5.219 |
itary | +4.940 |
wastes | +4.910 |
Feder | +4.768 |
itialized | +4.697 |
Neg logit contributions | |
Anth | -5.725 |
Typhoon | -5.629 |
Harding | -5.623 |
+. | -5.481 |
ype | -5.425 |
Token | to |
Token ID | 284 |
Feature activation | +1.89e+01 |
Pos logit contributions | |
wastes | +13.303 |
entary | +12.806 |
itary | +12.502 |
igned | +11.999 |
mockery | +11.921 |
Neg logit contributions | |
Anth | -16.647 |
Typhoon | -16.221 |
ackets | -15.874 |
Harding | -15.797 |
ype | -15.775 |
Token | me |
Token ID | 502 |
Feature activation | +1.86e+01 |
Pos logit contributions | |
entary | +9.637 |
itary | +9.167 |
wastes | +8.718 |
Feder | +8.402 |
igned | +8.390 |
Neg logit contributions | |
Typhoon | -13.278 |
Anth | -13.266 |
Harding | -13.148 |
ype | -12.962 |
atus | -12.925 |
Token | like |
Token ID | 588 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
entary | +9.808 |
wastes | +9.768 |
itary | +9.478 |
igned | +9.309 |
Feder | +8.899 |
Neg logit contributions | |
Anth | -12.994 |
Typhoon | -12.796 |
Harding | -12.744 |
ype | -12.327 |
Deng | -12.270 |
Token | an |
Token ID | 281 |
Feature activation | +2.27e+01 |
Pos logit contributions | |
entary | +9.858 |
wastes | +9.433 |
itary | +9.432 |
Feder | +8.833 |
igned | +8.829 |
Neg logit contributions | |
Anth | -13.627 |
Harding | -13.083 |
Typhoon | -12.902 |
ype | -12.679 |
Deng | -12.651 |
Token | unnecessary |
Token ID | 13114 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
entary | +10.739 |
wastes | +10.189 |
igned | +9.973 |
itary | +9.887 |
Feder | +9.265 |
Neg logit contributions | |
Anth | -16.024 |
Typhoon | -16.014 |
Harding | -15.478 |
+. | -15.367 |
ype | -15.093 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e+01 |
Pos logit contributions | |
entary | +9.207 |
itary | +9.043 |
Feder | +9.015 |
wastes | +8.709 |
igned | +8.411 |
Neg logit contributions | |
Typhoon | -10.609 |
Anth | -10.486 |
ype | -10.301 |
+. | -10.209 |
~~~~ | -10.184 |
Token | copper |
Token ID | 15317 |
Feature activation | +2.23e+01 |
Pos logit contributions | |
entary | +9.892 |
Feder | +9.675 |
itary | +9.646 |
Mint | +9.273 |
wastes | +9.269 |
Neg logit contributions | |
Typhoon | -10.504 |
Anth | -10.458 |
ype | -10.010 |
~~~~ | -9.994 |
+. | -9.952 |
Token | - |
Token ID | 12 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
itary | +12.691 |
entary | +12.520 |
wastes | +12.014 |
igned | +12.012 |
Feder | +11.898 |
Neg logit contributions | |
Typhoon | -13.291 |
Harding | -12.519 |
Anth | -12.505 |
ype | -12.354 |
~~~~ | -12.320 |
Token | nic |
Token ID | 6988 |
Feature activation | +9.21e+00 |
Pos logit contributions | |
entary | +6.348 |
itary | +6.112 |
FIG | +5.728 |
itialized | +5.539 |
igned | +5.538 |
Neg logit contributions | |
Typhoon | -9.378 |
Harding | -9.082 |
Deng | -8.741 |
~~~~ | -8.614 |
Anth | -8.419 |
Token | kel |
Token ID | 7750 |
Feature activation | +2.13e+01 |
Pos logit contributions | |
entary | +2.496 |
itary | +2.276 |
igned | +1.965 |
itialized | +1.910 |
FIG | +1.799 |
Neg logit contributions | |
Typhoon | -10.568 |
Harding | -10.540 |
Anth | -10.303 |
Deng | -10.207 |
~~~~ | -9.922 |
Token | cent |
Token ID | 1247 |
Feature activation | +2.70e+01 |
Pos logit contributions | |
itary | +12.513 |
entary | +12.383 |
Feder | +12.125 |
wastes | +11.962 |
igned | +11.863 |
Neg logit contributions | |
Typhoon | -12.255 |
~~~~ | -11.922 |
Anth | -11.762 |
ype | -11.674 |
Harding | -11.611 |
Token | be |
Token ID | 307 |
Feature activation | +1.77e+01 |
Pos logit contributions | |
entary | +15.694 |
itary | +15.480 |
FIG | +14.228 |
wastes | +14.144 |
Feder | +14.136 |
Neg logit contributions | |
Typhoon | -14.201 |
Harding | -13.461 |
Deng | -13.159 |
meier | -13.127 |
+. | -12.986 |
Token | replaced |
Token ID | 6928 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
entary | +10.170 |
igned | +10.154 |
itary | +9.846 |
itialized | +9.610 |
Feder | +9.601 |
Neg logit contributions | |
Typhoon | -11.833 |
Anth | -11.446 |
Harding | -11.344 |
+. | -11.126 |
ype | -11.052 |
Token | with |
Token ID | 351 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
entary | +3.617 |
itary | +3.442 |
itialized | +3.299 |
Feder | +3.270 |
wastes | +3.220 |
Neg logit contributions | |
Typhoon | -2.958 |
Harding | -2.940 |
Anth | -2.843 |
Deng | -2.767 |
ype | -2.727 |
Token | a |
Token ID | 257 |
Feature activation | +7.26e+00 |
Pos logit contributions | |
entary | +7.190 |
itary | +6.955 |
Feder | +6.865 |
wastes | +6.446 |
igned | +6.317 |
Neg logit contributions | |
Anth | -9.013 |
Typhoon | -8.972 |
ype | -8.784 |
+. | -8.773 |
Harding | -8.736 |
Token | bronze |
Token ID | 22101 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
entary | +4.950 |
itary | +4.726 |
Feder | +4.599 |
itialized | +4.453 |
igned | +4.356 |
Neg logit contributions | |
Typhoon | -5.156 |
Harding | -5.105 |
Anth | -5.094 |
Deng | -4.967 |
ype | -4.955 |
Token | run |
Token ID | 1057 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
entary | +4.451 |
itary | +4.185 |
FIG | +4.029 |
itialized | +4.021 |
Feder | +4.012 |
Neg logit contributions | |
Harding | -4.660 |
Anth | -4.635 |
Typhoon | -4.573 |
Deng | -4.408 |
ype | -4.308 |
Token | at |
Token ID | 379 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
entary | +8.520 |
itary | +7.894 |
FIG | +7.612 |
itialized | +7.416 |
Feder | +7.318 |
Neg logit contributions | |
Anth | -9.589 |
Harding | -9.233 |
Typhoon | -9.185 |
Deng | -8.726 |
ype | -8.439 |
Token | start |
Token ID | 923 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
entary | +2.098 |
itary | +1.982 |
itialized | +1.930 |
FIG | +1.884 |
Feder | +1.854 |
Neg logit contributions | |
Harding | -2.159 |
Typhoon | -2.148 |
Anth | -2.115 |
Deng | -2.057 |
+. | -2.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
Harding | +0.259 |
Typhoon | +0.258 |
Anth | +0.248 |
Deng | +0.246 |
+. | +0.242 |
Neg logit contributions | |
entary | -0.300 |
itary | -0.286 |
itialized | -0.278 |
FIG | -0.267 |
Feder | -0.267 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
entary | +6.846 |
itary | +6.392 |
Feder | +6.214 |
itialized | +6.179 |
FIG | +6.138 |
Neg logit contributions | |
Anth | -7.175 |
Harding | -7.057 |
Typhoon | -7.022 |
Deng | -6.756 |
ype | -6.620 |
Token |
|
Token ID | 198 |
Feature activation | +2.65e+01 |
Pos logit contributions | |
entary | +1.080 |
itary | +1.036 |
itialized | +0.996 |
FIG | +0.974 |
Feder | +0.971 |
Neg logit contributions | |
Harding | -1.022 |
Typhoon | -1.018 |
Anth | -0.984 |
Deng | -0.970 |
ype | -0.949 |
Token | After |
Token ID | 3260 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
FIG | +16.348 |
entary | +16.128 |
itary | +15.610 |
lis | +14.677 |
igned | +14.618 |
Neg logit contributions | |
Harding | -13.844 |
Typhoon | -13.641 |
Deng | -13.399 |
Anth | -12.306 |
Kass | -12.025 |
Token | saving |
Token ID | 8914 |
Feature activation | +9.89e+00 |
Pos logit contributions | |
entary | +7.174 |
itary | +6.831 |
itialized | +6.747 |
Feder | +6.437 |
FIG | +6.341 |
Neg logit contributions | |
Anth | -7.987 |
Harding | -7.982 |
Typhoon | -7.874 |
Deng | -7.626 |
+. | -7.350 |
Token | this |
Token ID | 428 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
entary | +6.467 |
itary | +5.913 |
itialized | +5.752 |
FIG | +5.625 |
Feder | +5.593 |
Neg logit contributions | |
Anth | -7.581 |
Harding | -7.464 |
Typhoon | -7.398 |
Deng | -7.006 |
+. | -6.896 |
Token | file |
Token ID | 2393 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
entary | +3.665 |
itary | +3.419 |
itialized | +3.323 |
Feder | +3.252 |
FIG | +3.232 |
Neg logit contributions | |
Harding | -4.015 |
Typhoon | -3.993 |
Anth | -3.946 |
Deng | -3.801 |
+. | -3.718 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
entary | +3.786 |
itary | +3.557 |
itialized | +3.443 |
Feder | +3.365 |
FIG | +3.339 |
Neg logit contributions | |
Harding | -3.768 |
Typhoon | -3.761 |
Anth | -3.731 |
Deng | -3.555 |
+. | -3.485 |
Token | more |
Token ID | 517 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
entary | +5.606 |
itary | +5.404 |
Feder | +5.242 |
wastes | +5.033 |
itialized | +5.030 |
Neg logit contributions | |
Anth | -5.742 |
Harding | -5.719 |
Typhoon | -5.632 |
ype | -5.512 |
+. | -5.459 |
Token | than |
Token ID | 621 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
entary | +8.502 |
itary | +8.028 |
Feder | +7.867 |
igned | +7.575 |
wastes | +7.555 |
Neg logit contributions | |
Anth | -9.241 |
Harding | -9.089 |
Typhoon | -8.779 |
~~~~ | -8.515 |
ype | -8.462 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
entary | +3.586 |
itary | +3.441 |
itialized | +3.268 |
Feder | +3.249 |
wastes | +3.181 |
Neg logit contributions | |
Harding | -3.737 |
Anth | -3.701 |
Typhoon | -3.664 |
Deng | -3.541 |
+. | -3.539 |
Token | , |
Token ID | 11 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
entary | +7.203 |
itary | +6.739 |
Feder | +6.683 |
itialized | +6.435 |
FIG | +6.335 |
Neg logit contributions | |
Harding | -7.632 |
Anth | -7.332 |
Typhoon | -7.248 |
Deng | -6.993 |
ype | -6.900 |
Token | 000 |
Token ID | 830 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
Typhoon | +2.457 |
Harding | +2.449 |
Anth | +2.326 |
Deng | +2.325 |
ype | +2.309 |
Neg logit contributions | |
entary | -2.911 |
itary | -2.797 |
itialized | -2.731 |
FIG | -2.591 |
Feder | -2.569 |
Token | local |
Token ID | 1957 |
Feature activation | +2.64e+01 |
Pos logit contributions | |
entary | +11.834 |
Feder | +11.658 |
itary | +11.214 |
NFC | +10.761 |
igned | +10.650 |
Neg logit contributions | |
Anth | -11.964 |
Harding | -11.759 |
~~~~ | -11.069 |
Typhoon | -10.901 |
ype | -10.839 |
Token | currencies |
Token ID | 19247 |
Feature activation | +8.54e+00 |
Pos logit contributions | |
entary | +14.196 |
Feder | +13.886 |
itary | +13.814 |
igned | +13.249 |
NFC | +13.201 |
Neg logit contributions | |
Anth | -15.650 |
Harding | -15.640 |
Typhoon | -15.022 |
~~~~ | -14.487 |
ackets | -14.240 |
Token | operating |
Token ID | 5361 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
entary | +5.892 |
itary | +5.648 |
Feder | +5.486 |
itialized | +5.411 |
FIG | +5.303 |
Neg logit contributions | |
Harding | -6.017 |
Typhoon | -5.988 |
Anth | -5.953 |
Deng | -5.588 |
ype | -5.543 |
Token | in |
Token ID | 287 |
Feature activation | +8.43e+00 |
Pos logit contributions | |
entary | +7.893 |
itary | +7.534 |
Feder | +7.433 |
igned | +6.925 |
wastes | +6.857 |
Neg logit contributions | |
Anth | -9.806 |
Typhoon | -9.744 |
Harding | -9.639 |
ype | -9.153 |
Deng | -9.142 |
Token | communities |
Token ID | 5348 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
entary | +5.853 |
itary | +5.673 |
Feder | +5.567 |
itialized | +5.309 |
wastes | +5.271 |
Neg logit contributions | |
Anth | -5.872 |
Harding | -5.757 |
Typhoon | -5.726 |
ype | -5.501 |
~~~~ | -5.462 |
Token | around |
Token ID | 1088 |
Feature activation | +9.72e+00 |
Pos logit contributions | |
entary | +5.514 |
itary | +5.390 |
Feder | +5.285 |
itialized | +5.046 |
igned | +5.012 |
Neg logit contributions | |
Typhoon | -5.765 |
Anth | -5.738 |
Harding | -5.735 |
Deng | -5.440 |
ype | -5.425 |
Token | F |
Token ID | 37 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
entary | +7.648 |
itary | +7.270 |
FIG | +6.979 |
Feder | +6.970 |
itialized | +6.924 |
Neg logit contributions | |
Typhoon | -7.044 |
Harding | -6.898 |
Deng | -6.664 |
Anth | -6.582 |
+. | -6.543 |
Token | CC |
Token ID | 4093 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
entary | +7.576 |
itary | +7.320 |
igned | +7.033 |
itialized | +6.988 |
FIG | +6.985 |
Neg logit contributions | |
Harding | -4.489 |
Typhoon | -4.364 |
Deng | -4.267 |
Anth | -4.267 |
+. | -4.067 |
Token | orp |
Token ID | 16300 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
entary | +11.415 |
itary | +10.947 |
wastes | +10.463 |
Feder | +10.460 |
FIG | +10.446 |
Neg logit contributions | |
Harding | -9.559 |
Typhoon | -9.381 |
Deng | -9.139 |
Anth | -9.034 |
+. | -8.832 |
Token | Sh |
Token ID | 2484 |
Feature activation | +6.71e+00 |
Pos logit contributions | |
entary | +8.241 |
itary | +7.990 |
itialized | +7.473 |
Feder | +7.417 |
FIG | +7.365 |
Neg logit contributions | |
Harding | -7.172 |
Typhoon | -7.015 |
Anth | -6.825 |
Deng | -6.801 |
+. | -6.581 |
Token | ill |
Token ID | 359 |
Feature activation | +8.61e+00 |
Pos logit contributions | |
entary | +4.747 |
itary | +4.464 |
itialized | +4.334 |
igned | +4.223 |
FIG | +4.188 |
Neg logit contributions | |
Typhoon | -4.865 |
Harding | -4.805 |
Anth | -4.605 |
Deng | -4.601 |
+. | -4.461 |
Token | # |
Token ID | 1303 |
Feature activation | +2.60e+01 |
Pos logit contributions | |
entary | +6.346 |
itary | +6.056 |
Feder | +5.719 |
itialized | +5.704 |
FIG | +5.661 |
Neg logit contributions | |
Typhoon | -5.617 |
Harding | -5.605 |
Anth | -5.376 |
Deng | -5.359 |
ype | -5.220 |
Token | A |
Token ID | 32 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
FIG | +15.816 |
entary | +15.784 |
itary | +15.689 |
MAG | +15.020 |
ear | +14.971 |
Neg logit contributions | |
Harding | -12.524 |
Deng | -12.104 |
Typhoon | -11.795 |
+. | -11.078 |
Avery | -10.977 |
Token | J |
Token ID | 41 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
entary | +6.965 |
itary | +6.618 |
FIG | +6.246 |
itialized | +6.125 |
igned | +6.038 |
Neg logit contributions | |
Harding | -9.267 |
Typhoon | -9.079 |
Deng | -8.802 |
Anth | -8.752 |
ype | -8.648 |
Token | edi |
Token ID | 13740 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
entary | +4.493 |
itary | +4.235 |
FIG | +4.039 |
itialized | +4.034 |
Feder | +3.971 |
Neg logit contributions | |
Harding | -4.046 |
Typhoon | -4.045 |
Deng | -3.813 |
Anth | -3.808 |
+. | -3.778 |
Token | You |
Token ID | 1639 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
entary | +9.074 |
itary | +8.698 |
FIG | +8.465 |
Feder | +8.355 |
itialized | +8.121 |
Neg logit contributions | |
Harding | -7.573 |
Typhoon | -7.538 |
Deng | -7.224 |
+. | -7.127 |
ype | -7.033 |
Token | Are |
Token ID | 8491 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
entary | +8.783 |
itary | +8.519 |
itialized | +8.199 |
FIG | +8.145 |
Feder | +8.059 |
Neg logit contributions | |
Harding | -7.837 |
Typhoon | -7.749 |
Deng | -7.348 |
Anth | -7.161 |
ype | -7.105 |
Token | independence |
Token ID | 39894 |
Feature activation | +1.97e+01 |
Pos logit contributions | |
entary | +6.603 |
itary | +6.592 |
FIG | +6.307 |
Feder | +5.917 |
ilan | +5.858 |
Neg logit contributions | |
Harding | -11.251 |
Typhoon | -11.041 |
Deng | -10.932 |
Anth | -10.667 |
ype | -10.311 |
Token | flag |
Token ID | 6056 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
Feder | +10.353 |
entary | +10.093 |
itary | +9.676 |
wastes | +9.342 |
igned | +9.331 |
Neg logit contributions | |
Anth | -13.799 |
Harding | -13.039 |
vu | -12.660 |
ype | -12.573 |
ackets | -12.509 |
Token | , |
Token ID | 11 |
Feature activation | +8.52e+00 |
Pos logit contributions | |
entary | +7.070 |
itary | +6.707 |
Feder | +6.595 |
wastes | +6.382 |
igned | +6.271 |
Neg logit contributions | |
Anth | -7.827 |
Harding | -7.747 |
Typhoon | -7.557 |
ype | -7.513 |
Deng | -7.337 |
Token | called |
Token ID | 1444 |
Feature activation | +1.95e+01 |
Pos logit contributions | |
entary | +5.513 |
itary | +5.251 |
Feder | +5.187 |
igned | +4.979 |
wastes | +4.962 |
Neg logit contributions | |
Anth | -6.193 |
Harding | -6.101 |
Typhoon | -5.972 |
ype | -5.932 |
+. | -5.856 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e+01 |
Pos logit contributions | |
Feder | +12.771 |
entary | +12.755 |
itary | +12.073 |
FIG | +11.570 |
Led | +11.297 |
Neg logit contributions | |
Anth | -11.143 |
Harding | -10.890 |
ype | -10.411 |
+. | -10.268 |
Typhoon | -10.155 |
Token | ' |
Token ID | 705 |
Feature activation | +2.56e+01 |
Pos logit contributions | |
Feder | +15.858 |
entary | +14.912 |
itary | +14.781 |
igned | +13.893 |
NFC | +13.876 |
Neg logit contributions | |
Anth | -12.001 |
Harding | -11.799 |
ype | -11.220 |
+. | -11.021 |
Typhoon | -10.686 |
Token | est |
Token ID | 395 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
FIG | +15.789 |
itary | +15.470 |
entary | +15.289 |
Feder | +14.736 |
igned | +14.672 |
Neg logit contributions | |
Harding | -13.062 |
Typhoon | -12.092 |
Deng | -12.024 |
Avery | -11.370 |
Hansen | -11.016 |
Token | el |
Token ID | 417 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
entary | +7.311 |
itary | +6.654 |
igned | +6.363 |
Feder | +6.173 |
ilan | +6.169 |
Neg logit contributions | |
Harding | -10.392 |
Anth | -10.146 |
Typhoon | -10.086 |
Deng | -9.619 |
+++ | -9.452 |
Token | ada |
Token ID | 4763 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
Harding | +0.716 |
Typhoon | +0.716 |
Anth | +0.660 |
Deng | +0.654 |
ype | +0.632 |
Neg logit contributions | |
entary | -2.308 |
itary | -2.233 |
itialized | -2.203 |
FIG | -2.139 |
Feder | -2.135 |
Token | ,' |
Token ID | 4032 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
entary | +7.872 |
itary | +7.600 |
Feder | +7.419 |
FIG | +7.173 |
itialized | +7.126 |
Neg logit contributions | |
Harding | -6.636 |
Anth | -6.458 |
Typhoon | -6.385 |
Deng | -6.257 |
ype | -6.143 |
Token | to |
Token ID | 284 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
entary | +5.107 |
itary | +4.861 |
Feder | +4.666 |
FIG | +4.516 |
wastes | +4.504 |
Neg logit contributions | |
Anth | -5.524 |
Harding | -5.523 |
Typhoon | -5.413 |
ype | -5.276 |
Deng | -5.192 |
Token | 64 |
Token ID | 2414 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
entary | +5.068 |
itary | +4.552 |
FIG | +4.548 |
Feder | +4.420 |
igned | +4.329 |
Neg logit contributions | |
Typhoon | -12.253 |
Harding | -12.248 |
Anth | -12.016 |
Deng | -11.761 |
atus | -11.418 |
Token | 406 |
Token ID | 29703 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
entary | +6.704 |
FIG | +6.313 |
itary | +6.236 |
itialized | +6.072 |
wastes | +5.746 |
Neg logit contributions | |
Typhoon | -10.978 |
Harding | -10.844 |
Anth | -10.657 |
Deng | -10.609 |
Zeal | -10.225 |
Token | Mem |
Token ID | 4942 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
entary | +0.245 |
itary | +0.224 |
itialized | +0.212 |
Feder | +0.198 |
FIG | +0.198 |
Neg logit contributions | |
Harding | -0.589 |
Typhoon | -0.587 |
Anth | -0.576 |
Deng | -0.570 |
ype | -0.563 |
Token | c |
Token ID | 66 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
entary | +2.231 |
itary | +2.147 |
itialized | +1.984 |
FIG | +1.940 |
Feder | +1.908 |
Neg logit contributions | |
Typhoon | -3.543 |
Harding | -3.526 |
Anth | -3.423 |
Deng | -3.381 |
+. | -3.293 |
Token | py |
Token ID | 9078 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
Typhoon | +1.846 |
Harding | +1.820 |
ype | +1.792 |
Anth | +1.779 |
"> | +1.761 |
Neg logit contributions | |
entary | -3.327 |
itary | -3.180 |
itialized | -3.135 |
Feder | -3.053 |
FIG | -2.999 |
Token | Reading |
Token ID | 36120 |
Feature activation | +2.55e+01 |
Pos logit contributions | |
Typhoon | +5.656 |
Harding | +5.646 |
Anth | +5.624 |
+. | +5.577 |
"> | +5.572 |
Neg logit contributions | |
entary | -4.382 |
itary | -4.090 |
itialized | -3.990 |
Feder | -3.826 |
wastes | -3.714 |
Token | 55 |
Token ID | 5996 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
entary | +12.340 |
Feder | +11.030 |
itary | +10.311 |
wastes | +10.090 |
itialized | +10.041 |
Neg logit contributions | |
Anth | -17.779 |
Typhoon | -17.190 |
Deng | -16.746 |
Harding | -16.746 |
~~~~ | -16.294 |
Token | 80 |
Token ID | 1795 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
entary | +1.796 |
itary | +1.708 |
itialized | +1.634 |
FIG | +1.613 |
Feder | +1.593 |
Neg logit contributions | |
Typhoon | -2.020 |
Harding | -2.012 |
Anth | -1.942 |
Deng | -1.917 |
ype | -1.882 |
Token | 953 |
Token ID | 49649 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
entary | +5.844 |
itary | +5.517 |
FIG | +5.297 |
Feder | +5.258 |
lis | +4.959 |
Neg logit contributions | |
Typhoon | -11.412 |
Harding | -11.082 |
Anth | -10.851 |
+. | -10.293 |
Avery | -10.286 |
Token | 16 |
Token ID | 1467 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
entary | +6.533 |
itary | +6.384 |
Feder | +6.232 |
itialized | +6.027 |
wastes | +5.929 |
Neg logit contributions | |
Anth | -10.515 |
Harding | -10.040 |
Typhoon | -9.916 |
ype | -9.776 |
~~~~ | -9.763 |
Token | 27 |
Token ID | 1983 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
entary | +4.432 |
itary | +4.320 |
FIG | +4.221 |
itialized | +4.141 |
Feder | +4.076 |
Neg logit contributions | |
Typhoon | -4.114 |
Harding | -4.098 |
Anth | -4.030 |
ype | -3.850 |
Deng | -3.838 |
Token | � |
Token ID | 447 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
entary | +3.554 |
itary | +3.456 |
itialized | +3.229 |
FIG | +3.217 |
Feder | +3.211 |
Neg logit contributions | |
Typhoon | -3.516 |
Harding | -3.472 |
Anth | -3.368 |
Deng | -3.305 |
+. | -3.275 |
Token | � |
Token ID | 247 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
Harding | +1.409 |
Typhoon | +1.398 |
Deng | +1.347 |
Anth | +1.346 |
+. | +1.327 |
Neg logit contributions | |
entary | -1.420 |
itary | -1.354 |
itialized | -1.318 |
FIG | -1.255 |
Feder | -1.252 |
Token | ite |
Token ID | 578 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
entary | +9.126 |
itary | +9.085 |
Feder | +8.668 |
FIG | +8.634 |
itialized | +8.294 |
Neg logit contributions | |
Harding | -8.205 |
Typhoon | -7.946 |
Deng | -7.689 |
Anth | -7.678 |
ype | -7.414 |
Token | militia |
Token ID | 21085 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
entary | +4.298 |
itary | +4.095 |
Feder | +4.018 |
FIG | +3.913 |
itialized | +3.826 |
Neg logit contributions | |
Harding | -4.737 |
Anth | -4.653 |
Typhoon | -4.615 |
ype | -4.502 |
Deng | -4.458 |
Token | , |
Token ID | 11 |
Feature activation | +1.95e+01 |
Pos logit contributions | |
entary | +5.722 |
itary | +5.556 |
Feder | +5.460 |
FIG | +5.249 |
itialized | +5.161 |
Neg logit contributions | |
Harding | -5.799 |
Anth | -5.715 |
Typhoon | -5.661 |
+. | -5.545 |
ype | -5.453 |
Token | the |
Token ID | 262 |
Feature activation | +2.53e+01 |
Pos logit contributions | |
Feder | +13.011 |
entary | +12.923 |
itary | +12.127 |
FIG | +11.730 |
itialized | +11.713 |
Neg logit contributions | |
Anth | -10.824 |
Harding | -10.340 |
vu | -10.203 |
+. | -10.124 |
Typhoon | -10.115 |
Token | Har |
Token ID | 2113 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
Feder | +16.045 |
itary | +14.541 |
entary | +14.361 |
NFC | +14.023 |
Beir | +13.835 |
Neg logit contributions | |
Anth | -13.871 |
ype | -12.758 |
+. | -12.710 |
Harding | -12.497 |
Typhoon | -12.332 |
Token | ak |
Token ID | 461 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
entary | +4.229 |
itary | +4.043 |
FIG | +3.721 |
itialized | +3.686 |
igned | +3.667 |
Neg logit contributions | |
Harding | -5.344 |
Typhoon | -5.340 |
Anth | -5.131 |
Deng | -5.042 |
+. | -5.016 |
Token | at |
Token ID | 265 |
Feature activation | +7.03e+00 |
Pos logit contributions | |
entary | +2.589 |
itary | +2.498 |
itialized | +2.396 |
Feder | +2.356 |
FIG | +2.324 |
Neg logit contributions | |
Harding | -1.582 |
Typhoon | -1.558 |
Anth | -1.501 |
Deng | -1.475 |
+. | -1.448 |
Token | al |
Token ID | 435 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
entary | +5.017 |
itary | +4.824 |
Feder | +4.654 |
itialized | +4.482 |
FIG | +4.444 |
Neg logit contributions | |
Typhoon | -4.828 |
Harding | -4.816 |
Anth | -4.754 |
+. | -4.629 |
ype | -4.532 |
Token | - |
Token ID | 12 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
entary | +3.816 |
itary | +3.664 |
Feder | +3.478 |
itialized | +3.453 |
FIG | +3.399 |
Neg logit contributions | |
Typhoon | -3.721 |
Harding | -3.690 |
Anth | -3.607 |
ype | -3.549 |
Deng | -3.510 |
Token | on |
Token ID | 319 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
entary | +0.760 |
itary | +0.725 |
itialized | +0.698 |
FIG | +0.676 |
Feder | +0.675 |
Neg logit contributions | |
Harding | -0.769 |
Typhoon | -0.766 |
Anth | -0.742 |
Deng | -0.731 |
+. | -0.719 |
Token | each |
Token ID | 1123 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
entary | +6.463 |
itary | +6.415 |
FIG | +6.279 |
Feder | +6.195 |
igned | +6.075 |
Neg logit contributions | |
Harding | -7.668 |
Anth | -7.539 |
Typhoon | -7.520 |
ype | -7.266 |
~~~~ | -7.118 |
Token | side |
Token ID | 1735 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
Harding | +0.974 |
Typhoon | +0.971 |
Deng | +0.941 |
Anth | +0.941 |
+. | +0.928 |
Neg logit contributions | |
entary | -0.585 |
itary | -0.543 |
itialized | -0.524 |
FIG | -0.491 |
Feder | -0.489 |
Token | for |
Token ID | 329 |
Feature activation | +7.68e+00 |
Pos logit contributions | |
entary | +4.449 |
itary | +4.429 |
wastes | +4.228 |
Feder | +4.184 |
FIG | +4.069 |
Neg logit contributions | |
Anth | -6.534 |
Harding | -6.484 |
Typhoon | -6.456 |
ype | -6.247 |
Deng | -6.237 |
Token | about |
Token ID | 546 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
entary | +3.753 |
itary | +3.666 |
Feder | +3.493 |
wastes | +3.372 |
FIG | +3.368 |
Neg logit contributions | |
Harding | -6.875 |
Typhoon | -6.810 |
Anth | -6.772 |
+. | -6.564 |
ype | -6.554 |
Token | 2 |
Token ID | 362 |
Feature activation | +2.52e+01 |
Pos logit contributions | |
Feder | +5.773 |
entary | +5.552 |
itary | +5.462 |
NFC | +5.421 |
wastes | +5.380 |
Neg logit contributions | |
Anth | -13.605 |
Harding | -13.392 |
Typhoon | -12.985 |
ackets | -12.964 |
ype | -12.776 |
Token | / |
Token ID | 14 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
itary | +6.695 |
Feder | +6.618 |
entary | +6.134 |
NFC | +5.875 |
FIG | +5.794 |
Neg logit contributions | |
Anth | -21.471 |
Harding | -21.220 |
Typhoon | -21.065 |
vertisement | -20.731 |
ackets | -20.290 |
Token | 3 |
Token ID | 18 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
entary | +0.738 |
itary | +0.708 |
itialized | +0.685 |
FIG | +0.667 |
Feder | +0.664 |
Neg logit contributions | |
Typhoon | -0.609 |
Harding | -0.608 |
Anth | -0.580 |
Deng | -0.576 |
ype | -0.563 |
Token | minutes |
Token ID | 2431 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
entary | +2.155 |
itary | +1.997 |
itialized | +1.871 |
Feder | +1.799 |
wastes | +1.794 |
Neg logit contributions | |
Harding | -4.942 |
Anth | -4.926 |
Typhoon | -4.898 |
Deng | -4.763 |
ype | -4.750 |
Token | until |
Token ID | 1566 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
entary | +1.334 |
itary | +1.225 |
itialized | +1.142 |
Feder | +1.094 |
igned | +1.088 |
Neg logit contributions | |
Harding | -2.984 |
Typhoon | -2.980 |
Anth | -2.918 |
Deng | -2.897 |
ype | -2.886 |
Token | golden |
Token ID | 10861 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
wastes | +2.877 |
entary | +2.657 |
itary | +2.545 |
igned | +2.515 |
Feder | +2.453 |
Neg logit contributions | |
Harding | -14.764 |
Typhoon | -14.532 |
Deng | -14.326 |
Anth | -14.322 |
ackets | -14.261 |
Token | have |
Token ID | 423 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Harding | +1.306 |
Typhoon | +1.304 |
Anth | +1.248 |
Deng | +1.246 |
ype | +1.226 |
Neg logit contributions | |
entary | -1.525 |
itary | -1.453 |
itialized | -1.417 |
FIG | -1.347 |
Feder | -1.338 |
Token | been |
Token ID | 587 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
entary | +1.923 |
itary | +1.835 |
itialized | +1.772 |
Feder | +1.740 |
FIG | +1.706 |
Neg logit contributions | |
Harding | -2.032 |
Typhoon | -2.021 |
Anth | -1.985 |
Deng | -1.923 |
+. | -1.913 |
Token | initiating |
Token ID | 40150 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
entary | +1.941 |
itary | +1.848 |
itialized | +1.778 |
Feder | +1.753 |
FIG | +1.728 |
Neg logit contributions | |
Harding | -1.991 |
Typhoon | -1.978 |
Anth | -1.932 |
Deng | -1.888 |
ype | -1.872 |
Token | their |
Token ID | 511 |
Feature activation | +1.64e+01 |
Pos logit contributions | |
entary | +10.941 |
Feder | +10.712 |
itary | +10.477 |
NFC | +10.267 |
wastes | +9.914 |
Neg logit contributions | |
Anth | -12.735 |
Harding | -12.330 |
Typhoon | -11.831 |
ackets | -11.619 |
ype | -11.422 |
Token | own |
Token ID | 898 |
Feature activation | +1.86e+01 |
Pos logit contributions | |
entary | +7.766 |
Feder | +7.604 |
itary | +7.515 |
wastes | +7.082 |
NFC | +6.989 |
Neg logit contributions | |
Anth | -13.271 |
Harding | -13.130 |
Typhoon | -12.506 |
vu | -12.404 |
ackets | -12.325 |
Token | local |
Token ID | 1957 |
Feature activation | +2.51e+01 |
Pos logit contributions | |
Feder | +11.082 |
entary | +11.041 |
itary | +10.628 |
NFC | +10.301 |
wastes | +10.238 |
Neg logit contributions | |
Anth | -12.429 |
Harding | -12.099 |
Typhoon | -11.526 |
ackets | -11.347 |
~~~~ | -10.954 |
Token | currency |
Token ID | 7395 |
Feature activation | +8.63e+00 |
Pos logit contributions | |
entary | +12.584 |
Feder | +12.325 |
itary | +12.285 |
NFC | +11.820 |
wastes | +11.664 |
Neg logit contributions | |
Anth | -16.369 |
Harding | -15.941 |
Typhoon | -15.630 |
ackets | -15.066 |
~~~~ | -14.704 |
Token | movements |
Token ID | 8650 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
entary | +6.004 |
itary | +5.757 |
Feder | +5.542 |
wastes | +5.410 |
itialized | +5.378 |
Neg logit contributions | |
Anth | -6.060 |
Harding | -6.049 |
Typhoon | -5.956 |
Deng | -5.657 |
ype | -5.648 |
Token | . |
Token ID | 13 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
entary | +2.877 |
itary | +2.754 |
itialized | +2.619 |
Feder | +2.613 |
FIG | +2.555 |
Neg logit contributions | |
Typhoon | -2.757 |
Harding | -2.748 |
Anth | -2.690 |
Deng | -2.603 |
ype | -2.585 |
Token | There |
Token ID | 1318 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
entary | +2.654 |
itary | +2.515 |
Feder | +2.467 |
itialized | +2.416 |
FIG | +2.391 |
Neg logit contributions | |
Harding | -2.518 |
Typhoon | -2.486 |
Anth | -2.481 |
ype | -2.390 |
+. | -2.386 |
Token | are |
Token ID | 389 |
Feature activation | +8.21e+00 |
Pos logit contributions | |
Harding | +0.192 |
Typhoon | +0.191 |
Anth | +0.184 |
Deng | +0.182 |
+. | +0.179 |
Neg logit contributions | |
entary | -0.239 |
itary | -0.228 |
itialized | -0.222 |
FIG | -0.214 |
Feder | -0.213 |
Token | which |
Token ID | 543 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
entary | +3.699 |
itary | +3.646 |
Feder | +3.527 |
itialized | +3.433 |
wastes | +3.240 |
Neg logit contributions | |
Typhoon | -5.341 |
Anth | -5.242 |
Harding | -5.226 |
Deng | -5.143 |
ype | -5.079 |
Token | such |
Token ID | 884 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
entary | +3.901 |
itary | +3.809 |
Feder | +3.674 |
wastes | +3.523 |
itialized | +3.484 |
Neg logit contributions | |
Typhoon | -4.180 |
Harding | -4.158 |
Anth | -4.124 |
Deng | -4.011 |
ype | -3.996 |
Token | Acts |
Token ID | 25528 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
entary | +4.377 |
itary | +4.231 |
Feder | +4.135 |
wastes | +3.965 |
itialized | +3.929 |
Neg logit contributions | |
Typhoon | -4.045 |
Harding | -3.987 |
Anth | -3.947 |
Deng | -3.832 |
ype | -3.825 |
Token | , |
Token ID | 11 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
entary | +1.168 |
itary | +1.115 |
itialized | +1.073 |
Feder | +1.037 |
FIG | +1.031 |
Neg logit contributions | |
Harding | -1.091 |
Typhoon | -1.090 |
Anth | -1.054 |
Deng | -1.041 |
ype | -1.021 |
Token | Records |
Token ID | 13407 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
entary | +4.279 |
itary | +4.101 |
itialized | +3.962 |
Feder | +3.906 |
wastes | +3.846 |
Neg logit contributions | |
Typhoon | -2.683 |
Harding | -2.669 |
Anth | -2.595 |
Deng | -2.556 |
ype | -2.503 |
Token | and |
Token ID | 290 |
Feature activation | +2.51e+01 |
Pos logit contributions | |
Harding | +2.089 |
Typhoon | +2.051 |
Anth | +1.984 |
Deng | +1.956 |
+. | +1.930 |
Neg logit contributions | |
entary | -2.773 |
itary | -2.650 |
itialized | -2.611 |
FIG | -2.519 |
Feder | -2.480 |
Token | Proceedings |
Token ID | 30641 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
entary | +12.224 |
itary | +12.171 |
Feder | +11.632 |
itialized | +10.273 |
igned | +10.228 |
Neg logit contributions | |
Anth | -16.753 |
vu | -16.103 |
Deng | -16.102 |
Typhoon | -16.079 |
Harding | -16.037 |
Token | shall |
Token ID | 2236 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
entary | +2.999 |
itary | +2.837 |
Feder | +2.648 |
itialized | +2.596 |
wastes | +2.550 |
Neg logit contributions | |
Typhoon | -4.384 |
Harding | -4.375 |
Anth | -4.254 |
Deng | -4.200 |
ype | -4.158 |
Token | be |
Token ID | 307 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
entary | +2.899 |
itary | +2.729 |
itialized | +2.524 |
Feder | +2.516 |
FIG | +2.452 |
Neg logit contributions | |
Harding | -3.798 |
Typhoon | -3.789 |
Anth | -3.694 |
Deng | -3.630 |
ype | -3.576 |
Token | proved |
Token ID | 8302 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
entary | +5.125 |
itary | +4.897 |
Feder | +4.640 |
igned | +4.626 |
itialized | +4.576 |
Neg logit contributions | |
Typhoon | -6.594 |
Harding | -6.334 |
Anth | -6.272 |
ype | -6.190 |
Deng | -6.140 |
Token | , |
Token ID | 11 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
entary | +3.446 |
itary | +3.273 |
itialized | +3.092 |
Feder | +3.074 |
igned | +3.010 |
Neg logit contributions | |
Typhoon | -3.241 |
Harding | -3.189 |
Anth | -3.088 |
Deng | -3.036 |
ype | -2.981 |
Token | during |
Token ID | 1141 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
entary | +0.120 |
itary | +0.115 |
itialized | +0.111 |
FIG | +0.107 |
Feder | +0.107 |
Neg logit contributions | |
Harding | -0.106 |
Typhoon | -0.106 |
Anth | -0.102 |
Deng | -0.101 |
+. | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
entary | +2.527 |
itary | +2.417 |
itialized | +2.346 |
Feder | +2.295 |
FIG | +2.225 |
Neg logit contributions | |
Harding | -2.735 |
Typhoon | -2.711 |
Anth | -2.677 |
Deng | -2.599 |
+. | -2.591 |
Token | presidential |
Token ID | 4787 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
entary | +3.495 |
itary | +3.337 |
itialized | +3.277 |
Feder | +3.222 |
wastes | +3.134 |
Neg logit contributions | |
Typhoon | -3.554 |
Harding | -3.525 |
Anth | -3.486 |
+. | -3.396 |
ype | -3.381 |
Token | campaign |
Token ID | 1923 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
entary | +1.627 |
itary | +1.542 |
itialized | +1.504 |
Feder | +1.443 |
FIG | +1.435 |
Neg logit contributions | |
Typhoon | -1.528 |
Harding | -1.518 |
Anth | -1.475 |
Deng | -1.462 |
+. | -1.443 |
Token | ), |
Token ID | 828 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
entary | +4.245 |
itary | +4.036 |
itialized | +3.872 |
Feder | +3.831 |
FIG | +3.749 |
Neg logit contributions | |
Typhoon | -5.256 |
Harding | -5.245 |
Anth | -5.205 |
+. | -5.034 |
Deng | -5.018 |
Token | called |
Token ID | 1444 |
Feature activation | +2.50e+01 |
Pos logit contributions | |
entary | +2.382 |
itary | +2.276 |
itialized | +2.200 |
Feder | +2.175 |
FIG | +2.124 |
Neg logit contributions | |
Typhoon | -2.498 |
Harding | -2.498 |
Anth | -2.450 |
Deng | -2.379 |
+. | -2.379 |
Token | Milo |
Token ID | 32662 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
Feder | +13.647 |
entary | +12.864 |
mockery | +12.768 |
FIRE | +12.481 |
itary | +12.344 |
Neg logit contributions | |
Anth | -15.171 |
ackets | -13.770 |
ype | -13.576 |
+. | -13.482 |
~~~~ | -13.455 |
Token | 's |
Token ID | 338 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
entary | +4.424 |
itary | +4.286 |
Feder | +4.067 |
itialized | +4.059 |
wastes | +4.025 |
Neg logit contributions | |
Harding | -5.229 |
Typhoon | -5.217 |
Anth | -5.165 |
+. | -4.982 |
ype | -4.966 |
Token | comments |
Token ID | 3651 |
Feature activation | +1.65e+01 |
Pos logit contributions | |
entary | +7.351 |
itary | +6.950 |
mockery | +6.883 |
wastes | +6.825 |
Feder | +6.790 |
Neg logit contributions | |
Typhoon | -8.180 |
Anth | -8.179 |
Harding | -8.034 |
ype | -7.953 |
+. | -7.888 |
Token | in |
Token ID | 287 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
itary | +8.801 |
mockery | +8.575 |
entary | +8.531 |
wastes | +8.458 |
Feder | +8.279 |
Neg logit contributions | |
Typhoon | -11.650 |
Anth | -11.422 |
Harding | -11.314 |
+. | -11.107 |
vu | -11.059 |
Token | the |
Token ID | 262 |
Feature activation | +7.54e+00 |
Pos logit contributions | |
entary | +7.625 |
itary | +7.214 |
itialized | +7.121 |
Feder | +7.031 |
mockery | +6.851 |
Neg logit contributions | |
Anth | -10.275 |
Typhoon | -9.868 |
Harding | -9.849 |
+. | -9.650 |
ype | -9.554 |
Token | whatever |
Token ID | 4232 |
Feature activation | +8.88e+00 |
Pos logit contributions | |
entary | +3.145 |
itary | +2.962 |
itialized | +2.888 |
Feder | +2.835 |
FIG | +2.786 |
Neg logit contributions | |
Harding | -2.937 |
Anth | -2.906 |
Typhoon | -2.892 |
Deng | -2.766 |
ype | -2.727 |
Token | it |
Token ID | 340 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
entary | +6.093 |
itary | +5.703 |
itialized | +5.544 |
Feder | +5.525 |
igned | +5.348 |
Neg logit contributions | |
Anth | -6.442 |
Harding | -6.335 |
Typhoon | -6.201 |
Deng | -5.961 |
ype | -5.833 |
Token | is |
Token ID | 318 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
entary | +1.999 |
itary | +1.908 |
itialized | +1.847 |
Feder | +1.792 |
FIG | +1.782 |
Neg logit contributions | |
Harding | -1.856 |
Typhoon | -1.846 |
Anth | -1.801 |
Deng | -1.767 |
+. | -1.728 |
Token | ). |
Token ID | 737 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
entary | +2.831 |
itary | +2.691 |
itialized | +2.612 |
Feder | +2.542 |
FIG | +2.514 |
Neg logit contributions | |
Harding | -2.565 |
Typhoon | -2.556 |
Anth | -2.541 |
Deng | -2.451 |
ype | -2.391 |
Token |
|
Token ID | 198 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
entary | +9.300 |
Feder | +8.405 |
itary | +8.351 |
itialized | +8.254 |
FIG | +8.208 |
Neg logit contributions | |
Anth | -10.579 |
Harding | -10.173 |
Typhoon | -10.012 |
Deng | -9.736 |
ype | -9.606 |
Token |
|
Token ID | 198 |
Feature activation | +2.48e+01 |
Pos logit contributions | |
entary | +2.174 |
itary | +2.094 |
itialized | +1.985 |
FIG | +1.984 |
Feder | +1.966 |
Neg logit contributions | |
Harding | -2.259 |
Typhoon | -2.245 |
Anth | -2.180 |
Deng | -2.143 |
ype | -2.089 |
Token | sudo |
Token ID | 24032 |
Feature activation | +9.76e+00 |
Pos logit contributions | |
entary | +14.486 |
FIG | +14.125 |
itary | +13.565 |
lis | +13.069 |
igned | +12.851 |
Neg logit contributions | |
Harding | -14.760 |
Typhoon | -14.480 |
Deng | -14.382 |
Anth | -13.335 |
Avery | -13.208 |
Token | system |
Token ID | 1080 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
entary | +6.846 |
itary | +6.269 |
itialized | +6.029 |
FIG | +5.906 |
Feder | +5.887 |
Neg logit contributions | |
Anth | -6.843 |
Harding | -6.797 |
Typhoon | -6.756 |
Deng | -6.480 |
ype | -6.381 |
Token | ctl |
Token ID | 34168 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
entary | +1.198 |
itary | +1.091 |
itialized | +1.029 |
FIG | +0.977 |
Feder | +0.962 |
Neg logit contributions | |
Typhoon | -3.016 |
Harding | -3.008 |
Anth | -2.972 |
Deng | -2.919 |
ype | -2.874 |
Token | restart |
Token ID | 15765 |
Feature activation | +7.73e+00 |
Pos logit contributions | |
entary | +4.350 |
itary | +4.083 |
itialized | +3.991 |
FIG | +3.812 |
igned | +3.751 |
Neg logit contributions | |
Harding | -5.763 |
Anth | -5.756 |
Typhoon | -5.690 |
Deng | -5.536 |
ype | -5.362 |
Token | network |
Token ID | 3127 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
entary | +5.188 |
itary | +4.792 |
itialized | +4.709 |
FIG | +4.552 |
igned | +4.538 |
Neg logit contributions | |
Harding | -5.849 |
Anth | -5.841 |
Typhoon | -5.788 |
Deng | -5.546 |
~~~~ | -5.338 |
Token | been |
Token ID | 587 |
Feature activation | +9.29e+00 |
Pos logit contributions | |
entary | +3.650 |
itary | +3.500 |
itialized | +3.407 |
Feder | +3.279 |
wastes | +3.251 |
Neg logit contributions | |
Typhoon | -3.668 |
Harding | -3.655 |
Anth | -3.604 |
Deng | -3.452 |
+. | -3.421 |
Token | for |
Token ID | 329 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
entary | +6.351 |
itary | +5.974 |
itialized | +5.898 |
wastes | +5.841 |
Feder | +5.794 |
Neg logit contributions | |
Harding | -6.476 |
Anth | -6.472 |
Typhoon | -6.347 |
Deng | -6.158 |
+. | -6.042 |
Token | nothing |
Token ID | 2147 |
Feature activation | +9.19e+00 |
Pos logit contributions | |
entary | +7.674 |
itialized | +7.065 |
itary | +7.044 |
wastes | +6.791 |
FIG | +6.742 |
Neg logit contributions | |
Harding | -8.712 |
Anth | -8.584 |
Typhoon | -8.446 |
Deng | -8.210 |
+. | -8.070 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
entary | +7.263 |
itary | +6.941 |
itialized | +6.672 |
Feder | +6.652 |
wastes | +6.519 |
Neg logit contributions | |
Typhoon | -5.532 |
Anth | -5.532 |
Harding | -5.529 |
Deng | -5.231 |
ype | -5.055 |
Token |
|
Token ID | 198 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
entary | +7.602 |
Feder | +7.311 |
itary | +7.004 |
FIG | +6.937 |
itialized | +6.869 |
Neg logit contributions | |
Anth | -9.077 |
Harding | -8.717 |
Typhoon | -8.626 |
ype | -8.468 |
ackets | -8.311 |
Token |
|
Token ID | 198 |
Feature activation | +2.48e+01 |
Pos logit contributions | |
entary | +2.335 |
itary | +2.255 |
FIG | +2.140 |
itialized | +2.136 |
Feder | +2.131 |
Neg logit contributions | |
Harding | -2.471 |
Typhoon | -2.459 |
Anth | -2.384 |
Deng | -2.342 |
ype | -2.286 |
Token | sudo |
Token ID | 24032 |
Feature activation | +9.25e+00 |
Pos logit contributions | |
FIG | +14.720 |
entary | +14.398 |
itary | +13.990 |
lis | +13.139 |
igned | +13.098 |
Neg logit contributions | |
Harding | -14.433 |
Typhoon | -14.144 |
Deng | -13.839 |
Anth | -12.612 |
Kass | -12.552 |
Token | ch |
Token ID | 442 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
entary | +6.300 |
itary | +5.972 |
itialized | +5.731 |
FIG | +5.625 |
Feder | +5.571 |
Neg logit contributions | |
Harding | -6.620 |
Typhoon | -6.547 |
Anth | -6.489 |
Deng | -6.235 |
ype | -6.035 |
Token | mod |
Token ID | 4666 |
Feature activation | -8.59e+00 |
Pos logit contributions | |
entary | +2.321 |
itary | +2.255 |
itialized | +2.175 |
Feder | +2.082 |
FIG | +2.080 |
Neg logit contributions | |
Harding | -1.934 |
Typhoon | -1.924 |
Anth | -1.853 |
Deng | -1.825 |
+. | -1.777 |
Token | + |
Token ID | 1343 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
Typhoon | +4.758 |
+. | +4.664 |
Harding | +4.649 |
ype | +4.578 |
"> | +4.499 |
Neg logit contributions | |
entary | -7.254 |
itary | -7.010 |
itialized | -6.800 |
FIG | -6.576 |
Feder | -6.563 |
Token | x |
Token ID | 87 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
entary | +0.615 |
itary | +0.591 |
itialized | +0.578 |
FIG | +0.560 |
Feder | +0.560 |
Neg logit contributions | |
Harding | -0.337 |
Typhoon | -0.336 |
Anth | -0.320 |
Deng | -0.316 |
ype | -0.305 |
Token | enc |
Token ID | 12685 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
entary | +5.607 |
itary | +5.443 |
itialized | +5.285 |
Feder | +5.153 |
FIG | +5.139 |
Neg logit contributions | |
Harding | -5.121 |
Typhoon | -5.100 |
Anth | -4.901 |
Deng | -4.803 |
+. | -4.620 |
Token | ourage |
Token ID | 32885 |
Feature activation | +8.78e+00 |
Pos logit contributions | |
entary | +1.609 |
itary | +1.534 |
itialized | +1.485 |
Feder | +1.421 |
FIG | +1.413 |
Neg logit contributions | |
Harding | -1.760 |
Typhoon | -1.754 |
Anth | -1.690 |
Deng | -1.674 |
+. | -1.646 |
Token | consumers |
Token ID | 7008 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
entary | +6.147 |
itary | +5.864 |
Feder | +5.774 |
itialized | +5.432 |
wastes | +5.384 |
Neg logit contributions | |
Harding | -6.186 |
Anth | -6.166 |
Typhoon | -5.879 |
ype | -5.782 |
~~~~ | -5.726 |
Token | and |
Token ID | 290 |
Feature activation | +8.89e+00 |
Pos logit contributions | |
entary | +6.350 |
itary | +6.220 |
Feder | +5.964 |
itialized | +5.720 |
FIG | +5.626 |
Neg logit contributions | |
Typhoon | -7.943 |
Harding | -7.843 |
Anth | -7.781 |
Deng | -7.355 |
+. | -7.239 |
Token | entrepreneurs |
Token ID | 17038 |
Feature activation | +8.06e+00 |
Pos logit contributions | |
entary | +5.714 |
itary | +5.294 |
Feder | +5.217 |
itialized | +5.126 |
wastes | +5.102 |
Neg logit contributions | |
Harding | -6.715 |
Anth | -6.607 |
Typhoon | -6.600 |
Deng | -6.245 |
+. | -6.217 |
Token | to |
Token ID | 284 |
Feature activation | +2.48e+01 |
Pos logit contributions | |
entary | +5.145 |
itary | +5.077 |
Feder | +4.864 |
itialized | +4.729 |
FIG | +4.643 |
Neg logit contributions | |
Typhoon | -6.037 |
Harding | -6.025 |
Anth | -5.925 |
Deng | -5.628 |
ype | -5.529 |
Token | use |
Token ID | 779 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
Feder | +11.968 |
entary | +11.727 |
earn | +11.657 |
NFC | +11.384 |
earning | +11.110 |
Neg logit contributions | |
Anth | -16.018 |
Harding | -15.896 |
Typhoon | -15.182 |
ype | -14.797 |
ackets | -14.420 |
Token | local |
Token ID | 1957 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
entary | +7.493 |
itary | +7.392 |
Feder | +7.089 |
wastes | +6.678 |
NFC | +6.660 |
Neg logit contributions | |
Harding | -8.286 |
Anth | -8.130 |
Typhoon | -7.776 |
ype | -7.555 |
Deng | -7.303 |
Token | businesses |
Token ID | 5692 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
entary | +7.088 |
itary | +6.982 |
Feder | +6.704 |
wastes | +6.593 |
igned | +6.345 |
Neg logit contributions | |
Harding | -11.689 |
Anth | -11.586 |
Typhoon | -11.232 |
ype | -10.867 |
ackets | -10.681 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
entary | +4.011 |
itary | +3.863 |
Feder | +3.677 |
itialized | +3.585 |
FIG | +3.573 |
Neg logit contributions | |
Harding | -4.167 |
Typhoon | -4.079 |
Anth | -4.063 |
Deng | -3.901 |
ype | -3.890 |
Token | services |
Token ID | 2594 |
Feature activation | +6.50e+00 |
Pos logit contributions | |
entary | +8.686 |
Feder | +8.411 |
itary | +8.364 |
wastes | +8.302 |
itialized | +7.880 |
Neg logit contributions | |
Harding | -9.491 |
Typhoon | -9.232 |
Anth | -9.230 |
ype | -8.697 |
+. | -8.615 |
Token | bre |
Token ID | 4679 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
entary | +4.233 |
itary | +4.143 |
igned | +3.879 |
itialized | +3.833 |
FIG | +3.830 |
Neg logit contributions | |
Harding | -4.470 |
Typhoon | -4.402 |
Anth | -4.277 |
Deng | -4.252 |
+. | -4.044 |
Token | xit |
Token ID | 10198 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
Harding | +1.125 |
Typhoon | +1.124 |
Anth | +1.067 |
Deng | +1.066 |
ype | +1.062 |
Neg logit contributions | |
entary | -1.565 |
itary | -1.482 |
itialized | -1.462 |
Feder | -1.408 |
FIG | -1.399 |
Token | - |
Token ID | 12 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
entary | +4.604 |
itary | +4.520 |
igned | +4.193 |
Feder | +4.141 |
itialized | +4.141 |
Neg logit contributions | |
Harding | -6.135 |
Typhoon | -6.094 |
Anth | -6.028 |
Deng | -5.826 |
+. | -5.580 |
Token | is |
Token ID | 271 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
entary | +2.341 |
itary | +2.272 |
itialized | +2.173 |
FIG | +2.118 |
igned | +2.115 |
Neg logit contributions | |
Harding | -1.946 |
Typhoon | -1.926 |
Deng | -1.850 |
Anth | -1.845 |
+. | -1.794 |
Token | - |
Token ID | 12 |
Feature activation | +8.10e+00 |
Pos logit contributions | |
entary | +4.779 |
itary | +4.717 |
igned | +4.374 |
FIG | +4.308 |
itialized | +4.299 |
Neg logit contributions | |
Harding | -6.445 |
Typhoon | -6.430 |
Anth | -6.223 |
Deng | -6.133 |
+. | -5.827 |
Token | the |
Token ID | 1169 |
Feature activation | +2.47e+01 |
Pos logit contributions | |
entary | +4.561 |
itary | +4.542 |
igned | +4.223 |
FIG | +4.166 |
itialized | +4.037 |
Neg logit contributions | |
Harding | -6.929 |
Typhoon | -6.819 |
Deng | -6.657 |
Anth | -6.541 |
+. | -6.323 |
Token | - |
Token ID | 12 |
Feature activation | +2.39e+01 |
Pos logit contributions | |
igned | +8.690 |
itary | +8.412 |
entary | +8.065 |
wastes | +7.911 |
arily | +7.633 |
Neg logit contributions | |
Typhoon | -19.530 |
ÃÂÃÂ | -19.475 |
Harding | -19.337 |
ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ | -18.982 |
Anth | -18.922 |
Token | prime |
Token ID | 35505 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
itary | +10.248 |
ear | +9.958 |
rek | +9.627 |
igned | +9.472 |
entary | +9.340 |
Neg logit contributions | |
Typhoon | -18.571 |
Harding | -18.514 |
Deng | -18.246 |
Hut | -17.832 |
Thro | -17.229 |
Token | - |
Token ID | 12 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Harding | +0.898 |
Typhoon | +0.897 |
Anth | +0.861 |
Deng | +0.856 |
+. | +0.844 |
Neg logit contributions | |
entary | -1.027 |
itary | -0.974 |
itialized | -0.952 |
FIG | -0.910 |
Feder | -0.908 |
Token | chall |
Token ID | 36747 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Typhoon | +2.199 |
Harding | +2.193 |
Anth | +2.135 |
ype | +2.123 |
"> | +2.108 |
Neg logit contributions | |
entary | -2.376 |
itary | -2.227 |
itialized | -2.205 |
Feder | -2.119 |
wastes | -2.075 |
Token | enge |
Token ID | 3540 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
Harding | +0.418 |
Typhoon | +0.406 |
Anth | +0.376 |
Deng | +0.367 |
ype | +0.360 |
Neg logit contributions | |
entary | -1.972 |
itary | -1.912 |
itialized | -1.884 |
Feder | -1.830 |
FIG | -1.825 |
Token | . |
Token ID | 13 |
Feature activation | +9.28e+00 |
Pos logit contributions | |
entary | +1.409 |
itary | +1.344 |
itialized | +1.302 |
Feder | +1.260 |
FIG | +1.257 |
Neg logit contributions | |
Harding | -1.323 |
Typhoon | -1.317 |
Anth | -1.289 |
Deng | -1.257 |
ype | -1.238 |
Token |
|
Token ID | 198 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
entary | +5.931 |
Feder | +5.662 |
itary | +5.536 |
FIG | +5.493 |
itialized | +5.297 |
Neg logit contributions | |
Anth | -6.599 |
Harding | -6.530 |
Typhoon | -6.452 |
ype | -6.413 |
~~~~ | -6.223 |
Token |
|
Token ID | 198 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
entary | +1.858 |
itary | +1.786 |
itialized | +1.705 |
FIG | +1.696 |
Feder | +1.686 |
Neg logit contributions | |
Harding | -1.875 |
Typhoon | -1.869 |
Anth | -1.801 |
Deng | -1.777 |
+. | -1.742 |
Token | First |
Token ID | 5962 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
entary | +4.820 |
FIG | +4.671 |
itary | +4.631 |
itialized | +4.348 |
igned | +4.302 |
Neg logit contributions | |
Typhoon | -5.001 |
Harding | -4.998 |
Deng | -4.787 |
ype | -4.583 |
Anth | -4.513 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
entary | +8.252 |
itary | +7.991 |
Feder | +7.849 |
igned | +7.629 |
itialized | +7.562 |
Neg logit contributions | |
Harding | -9.558 |
Anth | -9.410 |
Typhoon | -9.316 |
~~~~ | -9.011 |
Deng | -8.919 |
Token | we |
Token ID | 356 |
Feature activation | +2.45e+01 |
Pos logit contributions | |
entary | +8.012 |
Feder | +7.614 |
itary | +7.591 |
wastes | +7.523 |
FIG | +7.233 |
Neg logit contributions | |
Anth | -10.248 |
Harding | -9.968 |
Typhoon | -9.789 |
ype | -9.754 |
~~~~ | -9.698 |
Token | have |
Token ID | 423 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
entary | +11.348 |
wastes | +11.193 |
Feder | +10.616 |
FIG | +10.477 |
FIRE | +10.446 |
Neg logit contributions | |
Anth | -17.508 |
Harding | -16.135 |
Typhoon | -15.624 |
Deng | -15.454 |
~~~~ | -15.251 |
Token | to |
Token ID | 284 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
entary | +7.232 |
itary | +7.091 |
Feder | +6.610 |
igned | +6.588 |
wastes | +6.507 |
Neg logit contributions | |
Anth | -9.893 |
Harding | -9.682 |
Typhoon | -9.508 |
ype | -9.339 |
Deng | -9.289 |
Token | figure |
Token ID | 3785 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
entary | +8.029 |
itary | +7.419 |
FIG | +7.282 |
Feder | +7.231 |
wastes | +7.037 |
Neg logit contributions | |
Anth | -10.221 |
Harding | -9.999 |
Typhoon | -9.636 |
Deng | -9.493 |
ype | -9.318 |
Token | out |
Token ID | 503 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
entary | +3.577 |
itary | +3.328 |
Feder | +3.140 |
itialized | +3.140 |
wastes | +3.070 |
Neg logit contributions | |
Typhoon | -5.067 |
Anth | -5.033 |
Harding | -5.017 |
ype | -4.833 |
Deng | -4.822 |
Token | how |
Token ID | 703 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
entary | +3.889 |
itary | +3.689 |
itialized | +3.543 |
Feder | +3.539 |
wastes | +3.460 |
Neg logit contributions | |
Anth | -3.913 |
Harding | -3.891 |
Typhoon | -3.872 |
Deng | -3.713 |
ype | -3.694 |
Token | and |
Token ID | 290 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
Harding | +1.728 |
Typhoon | +1.711 |
Deng | +1.643 |
Anth | +1.625 |
+. | +1.604 |
Neg logit contributions | |
entary | -2.150 |
itary | -2.037 |
itialized | -2.020 |
FIG | -1.919 |
Feder | -1.882 |
Token | the |
Token ID | 262 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
Harding | +0.588 |
Typhoon | +0.585 |
Anth | +0.564 |
Deng | +0.560 |
+. | +0.549 |
Neg logit contributions | |
entary | -0.623 |
itary | -0.592 |
itialized | -0.576 |
FIG | -0.552 |
Feder | -0.548 |
Token | remaining |
Token ID | 5637 |
Feature activation | -9.37e+00 |
Pos logit contributions | |
entary | +0.801 |
itary | +0.768 |
itialized | +0.745 |
Feder | +0.724 |
FIG | +0.720 |
Neg logit contributions | |
Harding | -0.607 |
Typhoon | -0.606 |
Anth | -0.585 |
Deng | -0.576 |
ype | -0.567 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.20e+01 |
Pos logit contributions | |
Harding | +5.721 |
Typhoon | +5.547 |
Deng | +5.293 |
"> | +5.148 |
Anth | +5.137 |
Neg logit contributions | |
entary | -7.574 |
itialized | -7.268 |
itary | -7.062 |
FIG | -6.836 |
Feder | -6.433 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
+. | +11.290 |
Harding | +10.818 |
Typhoon | +10.806 |
Avery | +10.277 |
Deng | +10.157 |
Neg logit contributions | |
entary | -14.994 |
itialized | -14.839 |
itary | -14.313 |
FIG | -13.672 |
mockery | -13.483 |
Token | 5 |
Token ID | 20 |
Feature activation | -2.71e+01 |
Pos logit contributions | |
Harding | +0.070 |
Typhoon | +0.069 |
Anth | +0.067 |
Deng | +0.066 |
+. | +0.065 |
Neg logit contributions | |
entary | -0.086 |
itary | -0.082 |
itialized | -0.080 |
FIG | -0.077 |
Feder | -0.077 |
Token | acres |
Token ID | 16051 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
+. | +12.097 |
Typhoon | +11.351 |
Harding | +11.298 |
Avery | +11.272 |
"> | +10.756 |
Neg logit contributions | |
entary | -17.744 |
itialized | -17.274 |
itary | -16.940 |
FIG | -16.326 |
mockery | -16.216 |
Token | , |
Token ID | 11 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
Harding | +6.449 |
Typhoon | +6.296 |
Deng | +6.204 |
+. | +6.058 |
Anth | +6.008 |
Neg logit contributions | |
entary | -7.650 |
itary | -7.193 |
itialized | -7.150 |
FIG | -6.899 |
Feder | -6.452 |
Token | where |
Token ID | 810 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
Harding | +2.533 |
Typhoon | +2.512 |
Deng | +2.414 |
Anth | +2.394 |
+. | +2.365 |
Neg logit contributions | |
entary | -2.762 |
itary | -2.608 |
itialized | -2.570 |
FIG | -2.451 |
Feder | -2.396 |
Token | the |
Token ID | 262 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
Harding | +2.812 |
Typhoon | +2.788 |
Deng | +2.695 |
Anth | +2.694 |
ype | +2.632 |
Neg logit contributions | |
entary | -2.520 |
itary | -2.359 |
itialized | -2.327 |
FIG | -2.200 |
Feder | -2.157 |
Token | institute |
Token ID | 24224 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Harding | +2.914 |
Typhoon | +2.893 |
Deng | +2.771 |
Anth | +2.741 |
+. | +2.687 |
Neg logit contributions | |
entary | -3.355 |
itary | -3.176 |
itialized | -3.133 |
FIG | -2.994 |
igned | -2.900 |
Token | � |
Token ID | 447 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
entary | +1.541 |
itary | +1.466 |
itialized | +1.385 |
Feder | +1.354 |
FIG | +1.327 |
Neg logit contributions | |
Typhoon | -2.313 |
Harding | -2.297 |
Anth | -2.253 |
Deng | -2.219 |
+. | -2.215 |
Token | � |
Token ID | 247 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
Harding | +2.738 |
Typhoon | +2.707 |
Deng | +2.638 |
+. | +2.612 |
Anth | +2.598 |
Neg logit contributions | |
entary | -1.878 |
itary | -1.731 |
itialized | -1.682 |
FIG | -1.591 |
Feder | -1.587 |
Token | s |
Token ID | 82 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
"> | +5.337 |
Harding | +5.199 |
ype | +5.087 |
Typhoon | +5.039 |
+. | +4.892 |
Neg logit contributions | |
entary | -9.434 |
itialized | -8.946 |
itary | -8.679 |
gobl | -8.366 |
Beir | -8.347 |
Token | state |
Token ID | 1181 |
Feature activation | -7.57e+00 |
Pos logit contributions | |
Harding | +1.378 |
Typhoon | +1.346 |
Deng | +1.260 |
Anth | +1.249 |
ype | +1.233 |
Neg logit contributions | |
entary | -3.495 |
itary | -3.376 |
itialized | -3.293 |
FIG | -3.218 |
Feder | -3.163 |
Token | ( |
Token ID | 357 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Harding | +4.191 |
Typhoon | +4.162 |
"> | +4.050 |
Deng | +4.003 |
ype | +3.893 |
Neg logit contributions | |
entary | -6.672 |
itary | -6.342 |
itialized | -6.290 |
FIG | -5.875 |
ilan | -5.832 |
Token | such |
Token ID | 10508 |
Feature activation | -2.62e+01 |
Pos logit contributions | |
Harding | +1.410 |
Typhoon | +1.402 |
Anth | +1.368 |
Deng | +1.348 |
+. | +1.338 |
Neg logit contributions | |
entary | -1.222 |
itary | -1.138 |
itialized | -1.122 |
Feder | -1.054 |
FIG | -1.045 |
Token | as |
Token ID | 355 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
"> | +7.318 |
+++ | +5.373 |
Typhoon | +5.301 |
Deng | +5.290 |
Harding | +5.195 |
Neg logit contributions | |
gobl | -26.637 |
itialized | -25.094 |
entary | -24.761 |
inational | -22.423 |
itary | -22.297 |
Token | through |
Token ID | 832 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
Harding | +3.098 |
Deng | +2.936 |
"> | +2.894 |
Typhoon | +2.822 |
+. | +2.436 |
Neg logit contributions | |
entary | -16.663 |
itary | -16.249 |
itialized | -15.837 |
FIG | -15.715 |
ilan | -15.454 |
Token | a |
Token ID | 257 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
Typhoon | +2.704 |
Harding | +2.691 |
Deng | +2.573 |
"> | +2.525 |
Anth | +2.514 |
Neg logit contributions | |
entary | -3.146 |
itary | -2.987 |
itialized | -2.940 |
igned | -2.765 |
FIG | -2.764 |
Token | or |
Token ID | 393 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
entary | +3.426 |
itary | +3.238 |
itialized | +3.135 |
Feder | +3.067 |
FIG | +3.034 |
Neg logit contributions | |
Harding | -3.161 |
Anth | -3.132 |
Typhoon | -3.126 |
Deng | -3.030 |
+. | -2.987 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
entary | +2.368 |
itary | +2.275 |
itialized | +2.197 |
Feder | +2.131 |
FIG | +2.109 |
Neg logit contributions | |
Harding | -2.096 |
Typhoon | -2.079 |
Anth | -2.059 |
Deng | -1.999 |
+. | -1.976 |
Token | releasing |
Token ID | 13011 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
entary | +1.171 |
itary | +1.118 |
itialized | +1.077 |
Feder | +1.043 |
FIG | +1.042 |
Neg logit contributions | |
Harding | -1.119 |
Typhoon | -1.113 |
Anth | -1.083 |
Deng | -1.063 |
ype | -1.049 |
Token | an |
Token ID | 281 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
entary | +3.368 |
itary | +3.242 |
Feder | +3.055 |
itialized | +3.000 |
igned | +2.987 |
Neg logit contributions | |
Harding | -4.696 |
Typhoon | -4.657 |
Anth | -4.548 |
ype | -4.418 |
Deng | -4.404 |
Token | official |
Token ID | 1743 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
Harding | +1.598 |
Typhoon | +1.597 |
Deng | +1.512 |
Anth | +1.506 |
"> | +1.482 |
Neg logit contributions | |
entary | -2.609 |
itary | -2.474 |
itialized | -2.444 |
FIG | -2.350 |
Feder | -2.329 |
Token | statement |
Token ID | 2643 |
Feature activation | -7.03e+00 |
Pos logit contributions | |
entary | +3.005 |
itary | +2.852 |
Feder | +2.666 |
itialized | +2.590 |
igned | +2.565 |
Neg logit contributions | |
Anth | -6.518 |
Typhoon | -6.481 |
Harding | -6.458 |
Deng | -6.254 |
+. | -6.163 |
Token | soon |
Token ID | 2582 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
Typhoon | +4.000 |
Harding | +3.864 |
"> | +3.858 |
+. | +3.802 |
Deng | +3.779 |
Neg logit contributions | |
entary | -5.942 |
itary | -5.788 |
itialized | -5.703 |
Feder | -5.288 |
FIG | -5.276 |
Token | . |
Token ID | 13 |
Feature activation | -2.54e+01 |
Pos logit contributions | |
Typhoon | +2.571 |
Harding | +2.539 |
+. | +2.483 |
Anth | +2.444 |
Deng | +2.433 |
Neg logit contributions | |
entary | -3.692 |
itary | -3.494 |
itialized | -3.478 |
Feder | -3.223 |
FIG | -3.221 |
Token | As |
Token ID | 1081 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
Typhoon | +13.661 |
Harding | +12.874 |
Deng | +12.478 |
+. | +12.439 |
"> | +12.342 |
Neg logit contributions | |
entary | -16.012 |
itialized | -15.134 |
itary | -15.032 |
FIG | -15.000 |
wastes | -14.242 |
Token | well |
Token ID | 880 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
entary | +0.414 |
itary | +0.392 |
itialized | +0.379 |
Feder | +0.362 |
FIG | +0.362 |
Neg logit contributions | |
Harding | -0.501 |
Typhoon | -0.499 |
Anth | -0.485 |
Deng | -0.478 |
+. | -0.472 |
Token | as |
Token ID | 355 |
Feature activation | -8.79e+00 |
Pos logit contributions | |
"> | +5.121 |
Harding | +4.892 |
+. | +4.864 |
Typhoon | +4.823 |
Deng | +4.749 |
Neg logit contributions | |
entary | -13.932 |
itialized | -13.588 |
gobl | -13.359 |
itary | -12.971 |
FIG | -12.379 |
Token | updates |
Token ID | 5992 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
Typhoon | +4.834 |
Harding | +4.661 |
Deng | +4.461 |
+. | +4.443 |
"> | +4.442 |
Neg logit contributions | |
entary | -7.784 |
itary | -7.451 |
itialized | -7.211 |
FIG | -6.908 |
Feder | -6.901 |
Token | regarding |
Token ID | 5115 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
Harding | +0.478 |
Typhoon | +0.477 |
Anth | +0.460 |
Deng | +0.457 |
+. | +0.450 |
Neg logit contributions | |
entary | -0.486 |
itary | -0.460 |
itialized | -0.449 |
FIG | -0.428 |
Feder | -0.426 |
Token | uko |
Token ID | 29794 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Typhoon | +4.230 |
Harding | +4.165 |
ype | +4.126 |
Anth | +4.037 |
+. | +4.023 |
Neg logit contributions | |
entary | -4.738 |
itary | -4.520 |
itialized | -4.515 |
FIG | -4.308 |
Feder | -4.294 |
Token | i |
Token ID | 1312 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
entary | +2.132 |
itary | +2.038 |
itialized | +1.965 |
Feder | +1.911 |
FIG | +1.905 |
Neg logit contributions | |
Harding | -1.691 |
Typhoon | -1.681 |
Anth | -1.622 |
Deng | -1.596 |
ype | -1.559 |
Token | hol |
Token ID | 3937 |
Feature activation | -6.74e+00 |
Pos logit contributions | |
entary | +3.824 |
itary | +3.655 |
itialized | +3.562 |
Feder | +3.489 |
FIG | +3.452 |
Neg logit contributions | |
Harding | -2.368 |
Typhoon | -2.346 |
Anth | -2.276 |
Deng | -2.205 |
ype | -2.156 |
Token | a |
Token ID | 64 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
Typhoon | +4.508 |
Harding | +4.487 |
ype | +4.408 |
Deng | +4.346 |
Anth | +4.340 |
Neg logit contributions | |
entary | -4.917 |
itary | -4.671 |
itialized | -4.654 |
FIG | -4.428 |
Feder | -4.386 |
Token | |
Token ID | 220 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
entary | +0.523 |
itary | +0.500 |
itialized | +0.485 |
Feder | +0.468 |
FIG | +0.468 |
Neg logit contributions | |
Harding | -0.419 |
Typhoon | -0.418 |
Anth | -0.402 |
Deng | -0.397 |
+. | -0.389 |
Token | � |
Token ID | 134 |
Feature activation | -2.53e+01 |
Pos logit contributions | |
Typhoon | +3.838 |
Harding | +3.754 |
+. | +3.634 |
~~~~ | +3.592 |
ype | +3.546 |
Neg logit contributions | |
entary | -11.968 |
itary | -11.343 |
itialized | -11.229 |
Feder | -11.047 |
FIG | -10.914 |
Token | � |
Token ID | 119 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
"> | +6.291 |
~~~~ | +5.737 |
Typhoon | +5.630 |
� | +5.552 |
ype | +5.141 |
Neg logit contributions | |
entary | -23.559 |
itary | -22.580 |
itialized | -22.381 |
gobl | -22.280 |
Feder | -21.555 |
Token | o |
Token ID | 78 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
entary | +1.614 |
itary | +1.542 |
itialized | +1.490 |
FIG | +1.437 |
Feder | +1.428 |
Neg logit contributions | |
Harding | -1.388 |
Typhoon | -1.382 |
Anth | -1.327 |
Deng | -1.318 |
+. | -1.283 |
Token | |
Token ID | 220 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
entary | +4.733 |
itary | +4.519 |
itialized | +4.339 |
Feder | +4.333 |
wastes | +4.233 |
Neg logit contributions | |
Harding | -3.678 |
Typhoon | -3.638 |
Anth | -3.577 |
Deng | -3.450 |
ype | -3.431 |
Token | ia |
Token ID | 544 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
Typhoon | +5.372 |
Harding | +5.360 |
ype | +5.203 |
+. | +5.121 |
Anth | +5.071 |
Neg logit contributions | |
entary | -9.102 |
itary | -8.641 |
itialized | -8.594 |
FIG | -8.376 |
Feder | -8.374 |
Token | e |
Token ID | 304 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
entary | +3.862 |
itary | +3.679 |
itialized | +3.527 |
Feder | +3.524 |
FIG | +3.440 |
Neg logit contributions | |
Harding | -3.229 |
Typhoon | -3.214 |
Anth | -3.154 |
Deng | -3.053 |
ype | -3.021 |
Token | o |
Token ID | 267 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
entary | +4.495 |
itary | +4.329 |
itialized | +4.127 |
Feder | +4.099 |
FIG | +4.022 |
Neg logit contributions | |
Harding | -3.788 |
Typhoon | -3.733 |
Anth | -3.646 |
Deng | -3.512 |
ype | -3.491 |
Token | Kal |
Token ID | 12612 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
entary | +6.022 |
itary | +5.738 |
itialized | +5.614 |
Feder | +5.484 |
FIG | +5.424 |
Neg logit contributions | |
Harding | -4.301 |
Typhoon | -4.212 |
Anth | -4.123 |
Deng | -3.975 |
ype | -3.905 |
Token | an |
Token ID | 272 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
entary | +0.724 |
itary | +0.689 |
itialized | +0.666 |
Feder | +0.640 |
FIG | +0.640 |
Neg logit contributions | |
Harding | -0.643 |
Typhoon | -0.642 |
Anth | -0.617 |
Deng | -0.611 |
+. | -0.600 |
Token | ial |
Token ID | 498 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
Harding | +0.195 |
Typhoon | +0.194 |
Anth | +0.188 |
Deng | +0.187 |
+. | +0.184 |
Neg logit contributions | |
entary | -0.161 |
itary | -0.152 |
itialized | -0.147 |
FIG | -0.140 |
Feder | -0.140 |
Token | i |
Token ID | 72 |
Feature activation | -9.86e+00 |
Pos logit contributions | |
entary | +2.482 |
itary | +2.419 |
itialized | +2.144 |
Feder | +2.140 |
igned | +2.130 |
Neg logit contributions | |
Harding | -4.336 |
Typhoon | -4.312 |
Anth | -4.231 |
Deng | -4.159 |
+. | -4.075 |
Token | � |
Token ID | 134 |
Feature activation | -2.52e+01 |
Pos logit contributions | |
Typhoon | +2.734 |
Harding | +2.709 |
+. | +2.568 |
Deng | +2.553 |
"> | +2.349 |
Neg logit contributions | |
entary | -11.096 |
itialized | -10.572 |
itary | -10.502 |
FIG | -9.990 |
Feder | -9.948 |
Token | � |
Token ID | 119 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
"> | +7.549 |
~~~~ | +6.870 |
Typhoon | +6.847 |
ype | +5.869 |
� | +5.762 |
Neg logit contributions | |
gobl | -23.822 |
entary | -22.673 |
itialized | -22.342 |
itary | -21.888 |
inational | -20.638 |
Token | il |
Token ID | 346 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
entary | +4.573 |
itary | +4.410 |
ilan | +4.053 |
igned | +3.863 |
Feder | +3.826 |
Neg logit contributions | |
Typhoon | -8.554 |
Harding | -8.505 |
Anth | -8.343 |
Deng | -8.253 |
+. | -7.873 |
Token | oa |
Token ID | 12162 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Typhoon | +4.340 |
Harding | +4.311 |
+. | +4.202 |
ype | +4.199 |
"> | +4.119 |
Neg logit contributions | |
entary | -3.966 |
itialized | -3.798 |
itary | -3.701 |
Feder | -3.553 |
FIG | -3.498 |
Token | . |
Token ID | 13 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
entary | +0.762 |
itary | +0.726 |
itialized | +0.703 |
Feder | +0.679 |
FIG | +0.677 |
Neg logit contributions | |
Harding | -0.693 |
Typhoon | -0.690 |
Anth | -0.667 |
Deng | -0.659 |
ype | -0.647 |
Token |
|
Token ID | 198 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
entary | +2.069 |
itary | +1.969 |
itialized | +1.897 |
Feder | +1.871 |
FIG | +1.844 |
Neg logit contributions | |
Harding | -1.932 |
Typhoon | -1.918 |
Anth | -1.878 |
Deng | -1.831 |
ype | -1.817 |
Token | , |
Token ID | 11 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
entary | +3.094 |
itary | +2.935 |
itialized | +2.829 |
Feder | +2.805 |
FIG | +2.754 |
Neg logit contributions | |
Typhoon | -2.913 |
Harding | -2.882 |
Anth | -2.837 |
Deng | -2.742 |
ype | -2.711 |
Token | wants |
Token ID | 3382 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Harding | +5.819 |
Typhoon | +5.652 |
Deng | +5.623 |
Anth | +5.375 |
"> | +5.347 |
Neg logit contributions | |
entary | -6.762 |
itary | -6.409 |
itialized | -6.304 |
FIG | -5.978 |
ilan | -5.790 |
Token | an |
Token ID | 281 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
Harding | +6.367 |
Deng | +6.170 |
Typhoon | +6.032 |
Avery | +5.862 |
+. | +5.705 |
Neg logit contributions | |
entary | -8.463 |
itialized | -8.167 |
itary | -8.151 |
FIG | -7.754 |
wastes | -7.451 |
Token | apology |
Token ID | 17029 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
Harding | +5.870 |
Deng | +5.603 |
Typhoon | +5.441 |
Avery | +5.356 |
Anth | +5.285 |
Neg logit contributions | |
entary | -8.444 |
itary | -8.173 |
itialized | -8.106 |
wastes | -7.548 |
FIG | -7.502 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | -7.37e+00 |
Pos logit contributions | |
Harding | +6.879 |
Deng | +6.690 |
Typhoon | +6.509 |
+. | +6.354 |
ype | +6.152 |
Neg logit contributions | |
entary | -12.349 |
itialized | -12.170 |
itary | -11.638 |
wastes | -11.207 |
FIG | -11.133 |
Token | from |
Token ID | 422 |
Feature activation | -2.45e+01 |
Pos logit contributions | |
Harding | +4.199 |
Typhoon | +4.066 |
Deng | +4.056 |
+. | +3.824 |
"> | +3.802 |
Neg logit contributions | |
entary | -6.331 |
itialized | -6.056 |
itary | -5.992 |
FIG | -5.688 |
wastes | -5.578 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
Deng | +13.836 |
Harding | +13.535 |
Typhoon | +12.754 |
Avery | +12.736 |
"> | +11.583 |
Neg logit contributions | |
entary | -16.141 |
itary | -15.453 |
itialized | -15.135 |
ilan | -14.530 |
wastes | -14.048 |
Token | Cavs |
Token ID | 38943 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
Harding | +7.558 |
Deng | +7.429 |
Typhoon | +7.226 |
Avery | +6.788 |
"> | +6.746 |
Neg logit contributions | |
entary | -9.878 |
itary | -9.539 |
itialized | -9.220 |
FIG | -8.788 |
ilan | -8.662 |
Token | ' |
Token ID | 6 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Harding | +6.700 |
Deng | +6.503 |
Typhoon | +6.472 |
"> | +6.101 |
Anth | +6.094 |
Neg logit contributions | |
entary | -9.239 |
itialized | -8.718 |
itary | -8.519 |
FIG | -8.085 |
ilan | -7.931 |
Token | J |
Token ID | 449 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
Harding | +5.902 |
Deng | +5.770 |
Typhoon | +5.684 |
Avery | +5.403 |
Anth | +5.295 |
Neg logit contributions | |
entary | -9.106 |
itary | -8.665 |
itialized | -8.586 |
FIG | -8.304 |
ilan | -8.143 |
Token | . |
Token ID | 13 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
Harding | +2.421 |
Typhoon | +2.355 |
Deng | +2.330 |
Anth | +2.302 |
ype | +2.282 |
Neg logit contributions | |
entary | -3.300 |
itary | -3.149 |
itialized | -3.097 |
FIG | -2.992 |
Feder | -2.951 |
Token | ā |
Token ID | 10235 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
entary | +2.243 |
itary | +2.147 |
itialized | +2.089 |
Feder | +2.035 |
FIG | +2.020 |
Neg logit contributions | |
Harding | -1.533 |
Typhoon | -1.522 |
Anth | -1.473 |
Deng | -1.440 |
ype | -1.410 |
Token | Kal |
Token ID | 12612 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
entary | +2.133 |
itary | +2.037 |
itialized | +1.978 |
Feder | +1.922 |
FIG | +1.908 |
Neg logit contributions | |
Harding | -1.658 |
Typhoon | -1.649 |
Anth | -1.593 |
Deng | -1.563 |
+. | -1.535 |
Token | an |
Token ID | 272 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
entary | +0.827 |
itary | +0.793 |
itialized | +0.770 |
Feder | +0.744 |
FIG | +0.744 |
Neg logit contributions | |
Harding | -0.566 |
Typhoon | -0.564 |
Anth | -0.539 |
Deng | -0.533 |
+. | -0.522 |
Token | ial |
Token ID | 498 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Typhoon | +1.339 |
Harding | +1.338 |
Anth | +1.294 |
Deng | +1.283 |
ype | +1.271 |
Neg logit contributions | |
entary | -1.180 |
itary | -1.114 |
itialized | -1.091 |
FIG | -1.045 |
Feder | -1.038 |
Token | i |
Token ID | 72 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
entary | +1.358 |
itary | +1.286 |
itialized | +1.211 |
Feder | +1.162 |
FIG | +1.156 |
Neg logit contributions | |
Harding | -2.006 |
Typhoon | -2.000 |
Anth | -1.949 |
Deng | -1.930 |
+. | -1.896 |
Token | � |
Token ID | 134 |
Feature activation | -2.44e+01 |
Pos logit contributions | |
Typhoon | +2.714 |
Harding | +2.710 |
+. | +2.530 |
Deng | +2.503 |
Anth | +2.482 |
Neg logit contributions | |
entary | -8.062 |
itary | -7.764 |
itialized | -7.680 |
FIG | -7.440 |
Feder | -7.351 |
Token | � |
Token ID | 119 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
"> | +6.236 |
~~~~ | +5.605 |
Typhoon | +5.490 |
� | +4.870 |
ype | +4.556 |
Neg logit contributions | |
gobl | -24.086 |
entary | -23.487 |
itialized | -22.774 |
itary | -22.716 |
inational | -21.368 |
Token | il |
Token ID | 346 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
entary | +4.280 |
itary | +4.115 |
ilan | +3.743 |
itialized | +3.654 |
igned | +3.652 |
Neg logit contributions | |
Typhoon | -7.354 |
Harding | -7.347 |
Anth | -7.131 |
Deng | -7.084 |
+. | -6.802 |
Token | oa |
Token ID | 12162 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
Typhoon | +3.899 |
Harding | +3.881 |
ype | +3.744 |
+. | +3.744 |
Anth | +3.736 |
Neg logit contributions | |
entary | -3.376 |
itialized | -3.200 |
itary | -3.190 |
Feder | -3.022 |
FIG | -3.000 |
Token | a |
Token ID | 257 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Harding | +0.666 |
Typhoon | +0.663 |
Anth | +0.639 |
Deng | +0.634 |
+. | +0.625 |
Neg logit contributions | |
entary | -0.773 |
itary | -0.738 |
itialized | -0.719 |
FIG | -0.690 |
Feder | -0.686 |
Token | l |
Token ID | 300 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Typhoon | +1.325 |
Harding | +1.324 |
Anth | +1.267 |
Deng | +1.256 |
+. | +1.242 |
Neg logit contributions | |
entary | -1.901 |
itary | -1.826 |
itialized | -1.783 |
FIG | -1.715 |
Feder | -1.706 |
Token | :: |
Token ID | 3712 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
entary | +0.545 |
itary | +0.524 |
itialized | +0.510 |
FIG | +0.496 |
Feder | +0.494 |
Neg logit contributions | |
Harding | -0.347 |
Typhoon | -0.345 |
Anth | -0.329 |
Deng | -0.327 |
+. | -0.317 |
Token | B |
Token ID | 33 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
entary | +3.606 |
itary | +3.428 |
FIG | +3.364 |
itialized | +3.317 |
Feder | +3.168 |
Neg logit contributions | |
Typhoon | -4.932 |
Harding | -4.930 |
Deng | -4.746 |
ype | -4.577 |
Anth | -4.542 |
Token | old |
Token ID | 727 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
entary | +6.714 |
itary | +6.587 |
igned | +6.567 |
itialized | +6.343 |
ear | +5.867 |
Neg logit contributions | |
Typhoon | -13.124 |
Harding | -13.048 |
Deng | -12.778 |
Anth | -12.527 |
psi | -12.019 |
Token | ) |
Token ID | 8 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
entary | +3.956 |
itary | +3.608 |
itialized | +3.522 |
FIG | +3.434 |
Feder | +3.391 |
Neg logit contributions | |
Harding | -5.146 |
Typhoon | -5.068 |
Anth | -4.970 |
Deng | -4.966 |
+. | -4.828 |
Token | $ |
Token ID | 720 |
Feature activation | +6.03e+00 |
Pos logit contributions | |
Harding | +0.304 |
Typhoon | +0.304 |
Anth | +0.294 |
Deng | +0.292 |
+. | +0.288 |
Neg logit contributions | |
entary | -0.234 |
itary | -0.221 |
itialized | -0.212 |
FIG | -0.202 |
Feder | -0.202 |
Token | Br |
Token ID | 9414 |
Feature activation | -2.43e+01 |
Pos logit contributions | |
entary | +4.657 |
itary | +4.493 |
itialized | +4.356 |
FIG | +4.290 |
igned | +4.247 |
Neg logit contributions | |
Typhoon | -3.904 |
Harding | -3.885 |
Deng | -3.721 |
Anth | -3.612 |
+. | -3.529 |
Token | ush |
Token ID | 1530 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
"> | +7.444 |
ype | +7.164 |
ush | +6.747 |
+. | +6.576 |
atus | +6.553 |
Neg logit contributions | |
gobl | -22.295 |
Beir | -21.680 |
entary | -21.050 |
itialized | -20.952 |
Feder | -20.932 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
entary | +3.858 |
itary | +3.613 |
FIG | +3.503 |
itialized | +3.494 |
igned | +3.375 |
Neg logit contributions | |
Harding | -5.441 |
Typhoon | -5.418 |
Deng | -5.208 |
Anth | -5.112 |
~~~~ | -4.898 |
Token | = |
Token ID | 796 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
entary | +4.230 |
itary | +4.096 |
FIG | +4.001 |
itialized | +3.943 |
Feder | +3.926 |
Neg logit contributions | |
Harding | -3.235 |
Typhoon | -3.179 |
Anth | -2.988 |
Deng | -2.986 |
+. | -2.848 |
Token | New |
Token ID | 968 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Harding | +1.817 |
Typhoon | +1.811 |
Deng | +1.729 |
Anth | +1.709 |
+. | +1.683 |
Neg logit contributions | |
entary | -2.572 |
itary | -2.449 |
itialized | -2.366 |
FIG | -2.282 |
igned | -2.244 |
Token | - |
Token ID | 12 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
Harding | +2.585 |
Typhoon | +2.576 |
"> | +2.481 |
Anth | +2.478 |
+. | +2.470 |
Neg logit contributions | |
entary | -3.491 |
itary | -3.270 |
itialized | -3.245 |
Feder | -3.030 |
FIG | -3.025 |
Token | s |
Token ID | 82 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
entary | +2.368 |
itary | +2.276 |
itialized | +2.187 |
FIG | +2.122 |
Feder | +2.118 |
Neg logit contributions | |
Typhoon | -2.123 |
Harding | -2.121 |
Anth | -2.049 |
Deng | -2.020 |
+. | -1.983 |
Token | drawings |
Token ID | 23388 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
entary | +0.909 |
itary | +0.864 |
itialized | +0.836 |
Feder | +0.804 |
FIG | +0.802 |
Neg logit contributions | |
Harding | -0.913 |
Typhoon | -0.910 |
Anth | -0.883 |
Deng | -0.872 |
ype | -0.859 |
Token | — |
Token ID | 851 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
Harding | +1.469 |
Typhoon | +1.459 |
Anth | +1.397 |
Deng | +1.396 |
+. | +1.369 |
Neg logit contributions | |
entary | -1.847 |
itary | -1.764 |
itialized | -1.730 |
FIG | -1.660 |
Feder | -1.643 |
Token | oh |
Token ID | 11752 |
Feature activation | -2.14e+01 |
Pos logit contributions | |
Harding | +3.311 |
Typhoon | +3.292 |
Deng | +3.161 |
Anth | +3.119 |
+. | +3.090 |
Neg logit contributions | |
entary | -3.631 |
itary | -3.436 |
itialized | -3.371 |
FIG | -3.187 |
igned | -3.167 |
Token | my |
Token ID | 616 |
Feature activation | -9.40e+00 |
Pos logit contributions | |
Harding | +11.025 |
Deng | +10.825 |
~~~~ | +10.722 |
Typhoon | +10.713 |
!! | +10.367 |
Neg logit contributions | |
entary | -14.747 |
itialized | -14.184 |
itary | -14.114 |
igned | -13.264 |
FIG | -13.212 |
Token | God |
Token ID | 1793 |
Feature activation | -2.43e+01 |
Pos logit contributions | |
Harding | +5.738 |
Typhoon | +5.678 |
Deng | +5.501 |
"> | +5.374 |
~~~~ | +5.356 |
Neg logit contributions | |
entary | -7.527 |
itary | -7.078 |
itialized | -6.955 |
FIG | -6.750 |
igned | -6.612 |
Token | , |
Token ID | 11 |
Feature activation | -2.22e+01 |
Pos logit contributions | |
Harding | +11.917 |
!! | +11.834 |
~~~~ | +11.735 |
Typhoon | +11.735 |
Deng | +11.508 |
Neg logit contributions | |
entary | -16.256 |
itialized | -15.800 |
itary | -15.193 |
FIG | -14.766 |
igned | -14.575 |
Token | he |
Token ID | 339 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
Typhoon | +12.161 |
Harding | +12.123 |
Deng | +11.871 |
~~~~ | +11.316 |
"> | +11.307 |
Neg logit contributions | |
entary | -15.412 |
itialized | -14.496 |
itary | -14.211 |
FIG | -13.398 |
igned | -13.106 |
Token | � |
Token ID | 447 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
Harding | +2.146 |
Typhoon | +2.125 |
Anth | +2.053 |
Deng | +2.048 |
ype | +2.021 |
Neg logit contributions | |
entary | -2.098 |
itary | -1.977 |
itialized | -1.944 |
FIG | -1.846 |
Feder | -1.813 |
Token | � |
Token ID | 247 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
entary | +2.646 |
itary | +2.512 |
itialized | +2.366 |
FIG | +2.236 |
igned | +2.232 |
Neg logit contributions | |
Typhoon | -6.169 |
Anth | -6.107 |
Harding | -6.048 |
Deng | -5.873 |
ype | -5.810 |
Token | s |
Token ID | 82 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
entary | +0.088 |
itary | +0.084 |
itialized | +0.081 |
FIG | +0.078 |
Feder | +0.078 |
Neg logit contributions | |
Harding | -0.078 |
Typhoon | -0.078 |
Anth | -0.075 |
Deng | -0.074 |
+. | -0.073 |
Token | ko |
Token ID | 41727 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
entary | +3.051 |
itary | +2.924 |
itialized | +2.816 |
Feder | +2.739 |
FIG | +2.737 |
Neg logit contributions | |
Harding | -2.207 |
Typhoon | -2.185 |
Anth | -2.103 |
Deng | -2.075 |
ype | -2.006 |
Token | Kal |
Token ID | 12612 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Harding | +0.839 |
Typhoon | +0.836 |
Anth | +0.795 |
Deng | +0.785 |
+. | +0.771 |
Neg logit contributions | |
entary | -1.694 |
itary | -1.628 |
itialized | -1.599 |
FIG | -1.547 |
Feder | -1.543 |
Token | an |
Token ID | 272 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Harding | +0.134 |
Typhoon | +0.133 |
Anth | +0.128 |
Deng | +0.127 |
+. | +0.125 |
Neg logit contributions | |
entary | -0.174 |
itary | -0.167 |
itialized | -0.162 |
FIG | -0.156 |
Feder | -0.156 |
Token | ial |
Token ID | 498 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Harding | +1.234 |
Typhoon | +1.234 |
Anth | +1.191 |
Deng | +1.182 |
ype | +1.168 |
Neg logit contributions | |
entary | -1.184 |
itary | -1.119 |
itialized | -1.097 |
FIG | -1.051 |
Feder | -1.046 |
Token | i |
Token ID | 72 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
entary | +0.968 |
itary | +0.916 |
itialized | +0.872 |
Feder | +0.836 |
FIG | +0.835 |
Neg logit contributions | |
Harding | -1.295 |
Typhoon | -1.291 |
Anth | -1.256 |
Deng | -1.243 |
+. | -1.223 |
Token | � |
Token ID | 134 |
Feature activation | -2.43e+01 |
Pos logit contributions | |
Harding | +2.335 |
Typhoon | +2.330 |
Deng | +2.186 |
+. | +2.175 |
Anth | +2.171 |
Neg logit contributions | |
entary | -5.551 |
itary | -5.338 |
itialized | -5.272 |
FIG | -5.096 |
Feder | -5.031 |
Token | � |
Token ID | 119 |
Feature activation | +6.90e+00 |
Pos logit contributions | |
"> | +6.478 |
~~~~ | +5.659 |
Typhoon | +5.591 |
� | +5.073 |
meier | +4.809 |
Neg logit contributions | |
gobl | -23.255 |
entary | -23.166 |
itary | -22.368 |
itialized | -22.253 |
inational | -21.093 |
Token | il |
Token ID | 346 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
entary | +3.788 |
itary | +3.627 |
itialized | +3.287 |
ilan | +3.254 |
igned | +3.239 |
Neg logit contributions | |
Harding | -6.046 |
Typhoon | -6.029 |
Anth | -5.862 |
Deng | -5.814 |
+. | -5.603 |
Token | oa |
Token ID | 12162 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
Typhoon | +3.788 |
Harding | +3.766 |
Anth | +3.636 |
ype | +3.635 |
+. | +3.632 |
Neg logit contributions | |
entary | -3.255 |
itary | -3.082 |
itialized | -3.076 |
Feder | -2.904 |
FIG | -2.881 |
Token | a |
Token ID | 257 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Harding | +2.191 |
Typhoon | +2.173 |
Anth | +2.097 |
Deng | +2.089 |
+. | +2.070 |
Neg logit contributions | |
entary | -2.560 |
itary | -2.448 |
itialized | -2.398 |
FIG | -2.286 |
Feder | -2.257 |
Token | � |
Token ID | 134 |
Feature activation | -2.14e+01 |
Pos logit contributions | |
entary | +0.379 |
itary | +0.362 |
itialized | +0.352 |
FIG | +0.339 |
Feder | +0.339 |
Neg logit contributions | |
Harding | -0.293 |
Typhoon | -0.292 |
Anth | -0.281 |
Deng | -0.278 |
+. | -0.272 |
Token | a |
Token ID | 257 |
Feature activation | -7.88e+00 |
Pos logit contributions | |
Typhoon | +1.995 |
Harding | +1.983 |
Deng | +1.905 |
Anth | +1.883 |
+. | +1.863 |
Neg logit contributions | |
entary | -2.134 |
itary | -2.027 |
itialized | -1.951 |
FIG | -1.889 |
Feder | -1.869 |
Token | directive |
Token ID | 22644 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
Typhoon | +5.224 |
Harding | +5.175 |
Deng | +4.976 |
"> | +4.952 |
+. | +4.892 |
Neg logit contributions | |
entary | -5.844 |
itary | -5.683 |
itialized | -5.481 |
FIG | -5.269 |
igned | -5.143 |
Token | you |
Token ID | 345 |
Feature activation | -8.18e+00 |
Pos logit contributions | |
Typhoon | +2.791 |
Harding | +2.785 |
Deng | +2.666 |
+. | +2.620 |
"> | +2.619 |
Neg logit contributions | |
entary | -3.051 |
itary | -2.914 |
itialized | -2.824 |
FIG | -2.688 |
Feder | -2.668 |
Token | get |
Token ID | 651 |
Feature activation | -1.71e+01 |
Pos logit contributions | |
Typhoon | +5.528 |
Harding | +5.476 |
"> | +5.353 |
+. | +5.328 |
Deng | +5.322 |
Neg logit contributions | |
entary | -5.985 |
itary | -5.757 |
itialized | -5.511 |
FIG | -5.169 |
Feder | -5.092 |
Token | access |
Token ID | 1895 |
Feature activation | -1.61e+01 |
Pos logit contributions | |
Harding | +9.721 |
Typhoon | +9.674 |
"> | +9.593 |
Deng | +9.427 |
+. | +9.342 |
Neg logit contributions | |
entary | -12.224 |
itary | -11.552 |
itialized | -11.027 |
FIG | -10.763 |
ilan | -10.621 |
Token | to |
Token ID | 284 |
Feature activation | -2.42e+01 |
Pos logit contributions | |
Harding | +7.583 |
"> | +7.349 |
ype | +7.224 |
Typhoon | +7.211 |
Deng | +7.026 |
Neg logit contributions | |
entary | -12.880 |
itary | -12.352 |
wastes | -11.889 |
itialized | -11.888 |
FIG | -11.825 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e+01 |
Pos logit contributions | |
Typhoon | +12.610 |
"> | +12.292 |
Deng | +12.155 |
Harding | +12.145 |
aut | +11.653 |
Neg logit contributions | |
entary | -15.565 |
itary | -15.309 |
itialized | -14.329 |
ilan | -13.847 |
wcsstore | -13.581 |
Token | element |
Token ID | 5002 |
Feature activation | -1.92e+01 |
Pos logit contributions | |
Typhoon | +11.974 |
"> | +11.600 |
Harding | +11.402 |
Deng | +11.388 |
aut | +11.002 |
Neg logit contributions | |
entary | -13.704 |
itary | -13.088 |
itialized | -12.350 |
ilan | -11.854 |
FIG | -11.818 |
Token | that |
Token ID | 326 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
Harding | +11.118 |
Typhoon | +10.663 |
"> | +10.549 |
+. | +10.484 |
Deng | +10.428 |
Neg logit contributions | |
entary | -13.138 |
itary | -12.268 |
itialized | -11.841 |
wcsstore | -11.568 |
ilan | -11.563 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
Typhoon | +5.012 |
Harding | +5.010 |
Deng | +4.852 |
"> | +4.648 |
ype | +4.648 |
Neg logit contributions | |
entary | -5.346 |
itary | -5.127 |
itialized | -4.848 |
FIG | -4.645 |
igned | -4.616 |
Token | directive |
Token ID | 22644 |
Feature activation | -7.51e+00 |
Pos logit contributions | |
Typhoon | +7.156 |
Harding | +6.757 |
"> | +6.742 |
Deng | +6.726 |
+. | +6.526 |
Neg logit contributions | |
entary | -8.752 |
itary | -8.424 |
itialized | -8.080 |
wastes | -7.633 |
FIG | -7.618 |
Token | know |
Token ID | 760 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
Typhoon | +7.035 |
Harding | +6.916 |
"> | +6.770 |
Deng | +6.615 |
ype | +6.555 |
Neg logit contributions | |
entary | -8.506 |
itary | -8.227 |
itialized | -8.050 |
FIG | -7.879 |
Feder | -7.333 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
Typhoon | +3.621 |
Harding | +3.603 |
Deng | +3.461 |
"> | +3.402 |
+. | +3.396 |
Neg logit contributions | |
entary | -5.218 |
itary | -5.013 |
itialized | -4.947 |
FIG | -4.733 |
Feder | -4.586 |
Token | what |
Token ID | 644 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
Harding | +3.889 |
Typhoon | +3.851 |
Deng | +3.670 |
+. | +3.658 |
"> | +3.632 |
Neg logit contributions | |
entary | -5.660 |
itialized | -5.473 |
itary | -5.469 |
FIG | -5.188 |
igned | -5.090 |
Token | the |
Token ID | 262 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
Typhoon | +3.211 |
Harding | +3.179 |
Deng | +3.057 |
+. | +2.973 |
Anth | +2.957 |
Neg logit contributions | |
entary | -3.509 |
itary | -3.346 |
itialized | -3.302 |
FIG | -3.132 |
igned | -3.057 |
Token | weather |
Token ID | 6193 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
Typhoon | +5.509 |
Harding | +5.339 |
Deng | +5.179 |
+. | +4.951 |
Anth | +4.935 |
Neg logit contributions | |
entary | -5.835 |
itary | -5.655 |
itialized | -5.440 |
FIG | -5.153 |
igned | -5.049 |
Token | will |
Token ID | 481 |
Feature activation | -2.42e+01 |
Pos logit contributions | |
Typhoon | +6.207 |
Harding | +6.030 |
Deng | +5.637 |
ype | +5.557 |
"> | +5.462 |
Neg logit contributions | |
entary | -9.599 |
itialized | -9.463 |
itary | -9.136 |
FIG | -8.641 |
igned | -8.579 |
Token | do |
Token ID | 466 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
Typhoon | +10.480 |
"> | +10.106 |
ype | +9.580 |
aut | +9.353 |
+. | +9.242 |
Neg logit contributions | |
entary | -18.971 |
itialized | -18.133 |
itary | -17.660 |
igned | -17.279 |
ilan | -16.633 |
Token | . |
Token ID | 13 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
Harding | +2.673 |
Typhoon | +2.667 |
Deng | +2.541 |
+. | +2.506 |
"> | +2.478 |
Neg logit contributions | |
entary | -3.532 |
itary | -3.381 |
itialized | -3.363 |
FIG | -3.210 |
Feder | -3.133 |
Token | It |
Token ID | 632 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
Typhoon | +2.752 |
Harding | +2.726 |
Deng | +2.617 |
Anth | +2.553 |
+. | +2.523 |
Neg logit contributions | |
entary | -3.309 |
itary | -3.170 |
itialized | -3.117 |
FIG | -2.960 |
igned | -2.940 |
Token | might |
Token ID | 1244 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
Harding | +0.435 |
Typhoon | +0.434 |
Anth | +0.417 |
Deng | +0.415 |
+. | +0.407 |
Neg logit contributions | |
entary | -0.466 |
itary | -0.444 |
itialized | -0.431 |
FIG | -0.414 |
Feder | -0.412 |
Token | become |
Token ID | 1716 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Typhoon | +9.160 |
"> | +8.584 |
Deng | +8.580 |
+. | +8.533 |
Harding | +8.503 |
Neg logit contributions | |
entary | -11.793 |
itialized | -11.413 |
itary | -11.218 |
igned | -10.837 |
FIG | -10.749 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
"> | +7.894 |
Anth | +7.770 |
+++ | +7.696 |
Chance | +7.302 |
+. | +6.817 |
Neg logit contributions | |
entary | -22.586 |
gobl | -22.494 |
itialized | -21.375 |
Feder | -20.533 |
itary | -20.491 |
Token | Steve |
Token ID | 6542 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
entary | +4.628 |
itary | +4.397 |
Feder | +4.342 |
itialized | +4.310 |
igned | +4.120 |
Neg logit contributions | |
Harding | -3.756 |
Typhoon | -3.726 |
Anth | -3.674 |
+. | -3.605 |
ype | -3.603 |
Token | Care |
Token ID | 7276 |
Feature activation | +9.33e+00 |
Pos logit contributions | |
Harding | +0.553 |
Typhoon | +0.548 |
Anth | +0.527 |
Deng | +0.525 |
+. | +0.514 |
Neg logit contributions | |
entary | -0.631 |
itary | -0.602 |
itialized | -0.586 |
FIG | -0.561 |
Feder | -0.557 |
Token | ll |
Token ID | 297 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
entary | +4.229 |
itary | +4.096 |
FIG | +3.841 |
igned | +3.839 |
Feder | +3.788 |
Neg logit contributions | |
Typhoon | -8.719 |
Harding | -8.538 |
Anth | -8.386 |
Deng | -8.164 |
+. | -8.073 |
Token |
|
Token ID | 198 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
Harding | +0.714 |
Typhoon | +0.710 |
Anth | +0.683 |
Deng | +0.679 |
+. | +0.665 |
Neg logit contributions | |
entary | -0.862 |
itary | -0.821 |
itialized | -0.800 |
FIG | -0.765 |
Feder | -0.762 |
Token |
|
Token ID | 198 |
Feature activation | -2.42e+01 |
Pos logit contributions | |
Harding | +1.965 |
Typhoon | +1.956 |
Anth | +1.883 |
Deng | +1.877 |
"> | +1.863 |
Neg logit contributions | |
entary | -2.756 |
itary | -2.599 |
itialized | -2.574 |
FIG | -2.397 |
Feder | -2.395 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
"> | +7.941 |
Anth | +7.511 |
+++ | +7.241 |
Chance | +6.936 |
~~~~ | +6.586 |
Neg logit contributions | |
gobl | -23.998 |
entary | -23.164 |
itialized | -22.083 |
Feder | -21.081 |
itary | -20.828 |
Token | Lee |
Token ID | 5741 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
entary | +5.857 |
itary | +5.568 |
Feder | +5.556 |
itialized | +5.458 |
igned | +5.252 |
Neg logit contributions | |
Harding | -4.639 |
Typhoon | -4.589 |
Anth | -4.507 |
ype | -4.453 |
+. | -4.435 |
Token | Pace |
Token ID | 44111 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
entary | +0.211 |
itary | +0.203 |
itialized | +0.198 |
Feder | +0.192 |
FIG | +0.192 |
Neg logit contributions | |
Harding | -0.129 |
Typhoon | -0.129 |
Anth | -0.124 |
Deng | -0.122 |
+. | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
Harding | +1.707 |
Typhoon | +1.692 |
Anth | +1.620 |
Deng | +1.619 |
+. | +1.569 |
Neg logit contributions | |
entary | -2.131 |
itary | -2.044 |
itialized | -1.977 |
FIG | -1.908 |
Feder | -1.888 |
Token |
|
Token ID | 198 |
Feature activation | -1.95e+01 |
Pos logit contributions | |
Harding | +0.410 |
Typhoon | +0.409 |
Anth | +0.394 |
Deng | +0.391 |
+. | +0.384 |
Neg logit contributions | |
entary | -0.491 |
itary | -0.467 |
itialized | -0.456 |
FIG | -0.436 |
Feder | -0.435 |
Token | , |
Token ID | 11 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Harding | +1.926 |
Typhoon | +1.920 |
Anth | +1.840 |
Deng | +1.827 |
+. | +1.798 |
Neg logit contributions | |
entary | -2.422 |
itary | -2.314 |
itialized | -2.258 |
FIG | -2.168 |
Feder | -2.138 |
Token | Ass |
Token ID | 2195 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
entary | +1.941 |
itary | +1.853 |
itialized | +1.791 |
Feder | +1.744 |
FIG | +1.722 |
Neg logit contributions | |
Harding | -1.989 |
Typhoon | -1.987 |
Anth | -1.940 |
Deng | -1.906 |
ype | -1.878 |
Token | am |
Token ID | 321 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
Harding | +2.823 |
Typhoon | +2.776 |
Anth | +2.662 |
Deng | +2.643 |
+. | +2.636 |
Neg logit contributions | |
entary | -3.735 |
itary | -3.547 |
itialized | -3.507 |
FIG | -3.345 |
Feder | -3.316 |
Token | ? |
Token ID | 30 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
entary | +2.368 |
itary | +2.262 |
itialized | +2.173 |
Feder | +2.116 |
FIG | +2.102 |
Neg logit contributions | |
Typhoon | -2.152 |
Harding | -2.150 |
Anth | -2.071 |
Deng | -2.039 |
+. | -2.006 |
Token | Thank |
Token ID | 6952 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
Harding | +2.724 |
Typhoon | +2.713 |
Deng | +2.599 |
Anth | +2.596 |
+. | +2.556 |
Neg logit contributions | |
entary | -3.112 |
itary | -2.948 |
itialized | -2.897 |
FIG | -2.761 |
Feder | -2.710 |
Token | you |
Token ID | 345 |
Feature activation | -2.42e+01 |
Pos logit contributions | |
entary | +3.420 |
itary | +3.308 |
itialized | +3.195 |
Feder | +3.098 |
FIG | +3.086 |
Neg logit contributions | |
Harding | -3.438 |
Typhoon | -3.422 |
Anth | -3.363 |
Deng | -3.284 |
ype | -3.236 |
Token | for |
Token ID | 329 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
Typhoon | +14.092 |
Harding | +13.960 |
!! | +13.607 |
+. | +13.481 |
Deng | +13.441 |
Neg logit contributions | |
entary | -14.580 |
itialized | -13.720 |
itary | -13.429 |
FIG | -12.821 |
wcsstore | -12.681 |
Token | the |
Token ID | 262 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
Typhoon | +4.181 |
Harding | +4.153 |
Deng | +3.996 |
Anth | +3.896 |
+. | +3.873 |
Neg logit contributions | |
entary | -4.494 |
itary | -4.251 |
itialized | -4.146 |
FIG | -3.963 |
igned | -3.894 |
Token | history |
Token ID | 2106 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
entary | +0.439 |
itary | +0.419 |
itialized | +0.406 |
Feder | +0.390 |
FIG | +0.389 |
Neg logit contributions | |
Harding | -0.419 |
Typhoon | -0.418 |
Anth | -0.404 |
Deng | -0.400 |
+. | -0.393 |
Token | lesson |
Token ID | 11483 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
Harding | +0.063 |
Typhoon | +0.063 |
Anth | +0.061 |
Deng | +0.060 |
+. | +0.059 |
Neg logit contributions | |
entary | -0.068 |
itary | -0.065 |
itialized | -0.063 |
FIG | -0.060 |
Feder | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Harding | +3.698 |
Typhoon | +3.684 |
Deng | +3.549 |
+. | +3.497 |
Anth | +3.476 |
Neg logit contributions | |
entary | -4.637 |
itary | -4.473 |
itialized | -4.389 |
FIG | -4.169 |
Feder | -4.098 |
Token | � |
Token ID | 119 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
"> | +5.610 |
Typhoon | +5.088 |
~~~~ | +4.880 |
ype | +4.711 |
� | +4.519 |
Neg logit contributions | |
entary | -21.705 |
itary | -20.783 |
itialized | -20.594 |
gobl | -19.938 |
Feder | -19.923 |
Token | ā |
Token ID | 10235 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
entary | +2.179 |
itary | +2.080 |
itialized | +2.002 |
FIG | +1.934 |
igned | +1.929 |
Neg logit contributions | |
Harding | -1.944 |
Typhoon | -1.935 |
Anth | -1.853 |
Deng | -1.848 |
+. | -1.792 |
Token | ina |
Token ID | 1437 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
entary | +2.775 |
itary | +2.646 |
itialized | +2.555 |
Feder | +2.465 |
FIG | +2.459 |
Neg logit contributions | |
Harding | -2.427 |
Typhoon | -2.421 |
Anth | -2.345 |
Deng | -2.308 |
+. | -2.241 |
Token | a |
Token ID | 257 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
entary | +0.217 |
itary | +0.207 |
itialized | +0.201 |
FIG | +0.194 |
Feder | +0.194 |
Neg logit contributions | |
Harding | -0.188 |
Typhoon | -0.187 |
Anth | -0.180 |
Deng | -0.178 |
+. | -0.175 |
Token | |
Token ID | 220 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
entary | +2.232 |
itary | +2.131 |
itialized | +2.066 |
Feder | +2.009 |
FIG | +2.000 |
Neg logit contributions | |
Harding | -1.732 |
Typhoon | -1.717 |
Anth | -1.664 |
Deng | -1.629 |
ype | -1.591 |
Token | � |
Token ID | 134 |
Feature activation | -2.41e+01 |
Pos logit contributions | |
Typhoon | +4.211 |
Harding | +4.055 |
+. | +4.036 |
~~~~ | +4.024 |
Anth | +3.978 |
Neg logit contributions | |
entary | -13.563 |
itary | -12.842 |
itialized | -12.683 |
Feder | -12.614 |
FIG | -12.376 |
Token | � |
Token ID | 119 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
"> | +6.433 |
Typhoon | +5.598 |
ype | +5.451 |
~~~~ | +5.409 |
� | +5.259 |
Neg logit contributions | |
entary | -22.436 |
itary | -21.417 |
gobl | -21.390 |
itialized | -21.329 |
Feder | -20.870 |
Token | ike |
Token ID | 522 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
entary | +0.111 |
itary | +0.105 |
itialized | +0.102 |
FIG | +0.098 |
Feder | +0.098 |
Neg logit contributions | |
Harding | -0.099 |
Typhoon | -0.099 |
Anth | -0.095 |
Deng | -0.094 |
+. | -0.092 |
Token | p |
Token ID | 279 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
entary | +3.591 |
itary | +3.408 |
itialized | +3.280 |
Feder | +3.227 |
FIG | +3.193 |
Neg logit contributions | |
Harding | -3.302 |
Typhoon | -3.254 |
Anth | -3.194 |
Deng | -3.122 |
ype | -3.049 |
Token | ū |
Token ID | 20317 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Typhoon | +3.455 |
Harding | +3.400 |
ype | +3.319 |
Deng | +3.264 |
Anth | +3.260 |
Neg logit contributions | |
entary | -5.253 |
itary | -5.043 |
itialized | -5.024 |
Feder | -4.815 |
FIG | -4.813 |
Token | i |
Token ID | 1312 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
entary | +2.251 |
itary | +2.140 |
itialized | +2.076 |
Feder | +2.017 |
FIG | +2.011 |
Neg logit contributions | |
Harding | -1.911 |
Typhoon | -1.893 |
Anth | -1.845 |
Deng | -1.804 |
ype | -1.773 |
Token | o |
Token ID | 267 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
entary | +1.878 |
itary | +1.800 |
itialized | +1.740 |
Feder | +1.687 |
FIG | +1.682 |
Neg logit contributions | |
Harding | -1.504 |
Typhoon | -1.497 |
Anth | -1.448 |
Deng | -1.423 |
+. | -1.393 |
Token | Kal |
Token ID | 12612 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
entary | +4.617 |
itary | +4.395 |
itialized | +4.287 |
Feder | +4.197 |
FIG | +4.145 |
Neg logit contributions | |
Harding | -3.552 |
Typhoon | -3.510 |
Anth | -3.418 |
Deng | -3.327 |
ype | -3.267 |
Token | an |
Token ID | 272 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
entary | +2.494 |
itary | +2.360 |
itialized | +2.241 |
Feder | +2.160 |
igned | +2.156 |
Neg logit contributions | |
Harding | -2.726 |
Typhoon | -2.722 |
Anth | -2.619 |
Deng | -2.595 |
+. | -2.554 |
Token | ial |
Token ID | 498 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
Harding | +0.321 |
Typhoon | +0.320 |
Anth | +0.310 |
Deng | +0.307 |
+. | +0.303 |
Neg logit contributions | |
entary | -0.268 |
itary | -0.253 |
itialized | -0.245 |
FIG | -0.234 |
Feder | -0.233 |
Token | i |
Token ID | 72 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
entary | +2.262 |
itary | +2.158 |
itialized | +1.981 |
Feder | +1.929 |
FIG | +1.906 |
Neg logit contributions | |
Harding | -3.610 |
Typhoon | -3.598 |
Anth | -3.515 |
Deng | -3.484 |
+. | -3.411 |
Token | � |
Token ID | 134 |
Feature activation | -2.41e+01 |
Pos logit contributions | |
Typhoon | +2.680 |
Harding | +2.654 |
+. | +2.503 |
Deng | +2.480 |
Anth | +2.321 |
Neg logit contributions | |
entary | -10.168 |
itialized | -9.694 |
itary | -9.676 |
FIG | -9.207 |
Feder | -9.163 |
Token | � |
Token ID | 119 |
Feature activation | +9.47e+00 |
Pos logit contributions | |
"> | +6.879 |
~~~~ | +6.213 |
Typhoon | +6.165 |
ype | +5.221 |
Anth | +5.187 |
Neg logit contributions | |
gobl | -23.440 |
entary | -22.611 |
itialized | -21.862 |
itary | -21.728 |
inational | -20.402 |
Token | il |
Token ID | 346 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
entary | +4.673 |
itary | +4.491 |
ilan | +4.167 |
igned | +3.962 |
itialized | +3.912 |
Neg logit contributions | |
Typhoon | -8.576 |
Harding | -8.529 |
Anth | -8.347 |
Deng | -8.271 |
+. | -7.917 |
Token | oa |
Token ID | 12162 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
Typhoon | +3.972 |
Harding | +3.951 |
ype | +3.837 |
+. | +3.834 |
Anth | +3.792 |
Neg logit contributions | |
entary | -3.533 |
itialized | -3.353 |
itary | -3.304 |
Feder | -3.143 |
FIG | -3.099 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Harding | +0.565 |
Typhoon | +0.563 |
Anth | +0.542 |
Deng | +0.538 |
+. | +0.530 |
Neg logit contributions | |
entary | -0.632 |
itary | -0.602 |
itialized | -0.586 |
FIG | -0.562 |
Feder | -0.559 |
Token | Ma |
Token ID | 6669 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
entary | +0.941 |
itary | +0.897 |
itialized | +0.867 |
Feder | +0.842 |
FIG | +0.838 |
Neg logit contributions | |
Harding | -0.857 |
Typhoon | -0.853 |
Anth | -0.828 |
Deng | -0.815 |
ype | -0.803 |
Token | l |
Token ID | 75 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
entary | +1.030 |
itary | +0.978 |
itialized | +0.944 |
Feder | +0.909 |
FIG | +0.907 |
Neg logit contributions | |
Harding | -1.030 |
Typhoon | -1.024 |
Anth | -0.995 |
Deng | -0.982 |
+. | -0.963 |
Token | ā |
Token ID | 10235 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Typhoon | +5.196 |
Harding | +5.137 |
ype | +5.050 |
Deng | +4.959 |
Anth | +4.893 |
Neg logit contributions | |
entary | -9.915 |
itialized | -9.671 |
itary | -9.570 |
FIG | -9.197 |
Feder | -9.127 |
Token | p |
Token ID | 279 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
entary | +0.994 |
itary | +0.951 |
itialized | +0.924 |
Feder | +0.894 |
FIG | +0.894 |
Neg logit contributions | |
Harding | -0.739 |
Typhoon | -0.734 |
Anth | -0.709 |
Deng | -0.698 |
+. | -0.682 |
Token | ū |
Token ID | 20317 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
Typhoon | +4.290 |
Harding | +4.226 |
ype | +4.185 |
Deng | +4.165 |
+. | +4.091 |
Neg logit contributions | |
entary | -5.151 |
itary | -4.888 |
itialized | -4.863 |
Feder | -4.649 |
FIG | -4.627 |
Token | |
Token ID | 220 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
entary | +0.571 |
itary | +0.545 |
itialized | +0.530 |
FIG | +0.511 |
Feder | +0.510 |
Neg logit contributions | |
Harding | -0.460 |
Typhoon | -0.458 |
Anth | -0.442 |
Deng | -0.436 |
+. | -0.427 |
Token | � |
Token ID | 134 |
Feature activation | -2.40e+01 |
Pos logit contributions | |
Typhoon | +5.981 |
Harding | +5.927 |
+. | +5.719 |
ype | +5.718 |
~~~~ | +5.692 |
Neg logit contributions | |
entary | -9.467 |
itary | -8.962 |
itialized | -8.807 |
Feder | -8.647 |
FIG | -8.584 |
Token | � |
Token ID | 119 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
"> | +5.498 |
~~~~ | +5.112 |
Typhoon | +5.027 |
� | +4.802 |
ype | +4.545 |
Neg logit contributions | |
entary | -23.161 |
itary | -22.439 |
itialized | -22.099 |
gobl | -21.825 |
Feder | -21.436 |
Token | o |
Token ID | 78 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
Harding | +2.302 |
Typhoon | +2.297 |
Anth | +2.233 |
ype | +2.215 |
Deng | +2.194 |
Neg logit contributions | |
entary | -2.786 |
itary | -2.669 |
itialized | -2.610 |
Feder | -2.526 |
FIG | -2.507 |
Token | K |
Token ID | 509 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
entary | +3.605 |
itary | +3.443 |
itialized | +3.332 |
Feder | +3.284 |
FIG | +3.237 |
Neg logit contributions | |
Harding | -2.729 |
Typhoon | -2.700 |
Anth | -2.635 |
Deng | -2.548 |
ype | -2.517 |
Token | ā |
Token ID | 10235 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
Typhoon | +2.847 |
Harding | +2.817 |
Anth | +2.733 |
ype | +2.726 |
Deng | +2.692 |
Neg logit contributions | |
entary | -3.562 |
itary | -3.402 |
itialized | -3.351 |
Feder | -3.199 |
FIG | -3.192 |
Token | n |
Token ID | 77 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
Harding | +0.613 |
Typhoon | +0.612 |
Anth | +0.590 |
Deng | +0.585 |
+. | +0.575 |
Neg logit contributions | |
entary | -0.679 |
itary | -0.647 |
itialized | -0.629 |
FIG | -0.603 |
Feder | -0.602 |
Token | no |
Token ID | 645 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
entary | +2.145 |
itary | +2.055 |
itialized | +1.984 |
Feder | +1.934 |
FIG | +1.926 |
Neg logit contributions | |
Harding | -1.596 |
Typhoon | -1.593 |
Anth | -1.534 |
Deng | -1.504 |
+. | -1.477 |
Token | ho |
Token ID | 8873 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Harding | +1.308 |
Typhoon | +1.304 |
Anth | +1.249 |
Deng | +1.245 |
ype | +1.218 |
Neg logit contributions | |
entary | -1.688 |
itary | -1.612 |
itialized | -1.578 |
FIG | -1.516 |
Feder | -1.505 |
Token | ak |
Token ID | 47594 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
Harding | +0.901 |
Typhoon | +0.899 |
Anth | +0.864 |
Deng | +0.856 |
+. | +0.842 |
Neg logit contributions | |
entary | -1.144 |
itary | -1.092 |
itialized | -1.067 |
FIG | -1.025 |
Feder | -1.021 |
Token | ula |
Token ID | 4712 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
Typhoon | +6.066 |
Harding | +5.848 |
ype | +5.782 |
+. | +5.652 |
Deng | +5.640 |
Neg logit contributions | |
entary | -7.941 |
itary | -7.639 |
itialized | -7.621 |
Feder | -7.228 |
FIG | -7.220 |
Token | |
Token ID | 220 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
Harding | +0.473 |
Typhoon | +0.471 |
Anth | +0.453 |
Deng | +0.450 |
+. | +0.442 |
Neg logit contributions | |
entary | -0.580 |
itary | -0.554 |
itialized | -0.540 |
FIG | -0.519 |
Feder | -0.517 |
Token | � |
Token ID | 134 |
Feature activation | -2.40e+01 |
Pos logit contributions | |
Typhoon | +3.900 |
Harding | +3.759 |
~~~~ | +3.736 |
+. | +3.665 |
"> | +3.602 |
Neg logit contributions | |
entary | -14.064 |
itary | -13.276 |
itialized | -13.155 |
Feder | -12.921 |
FIG | -12.698 |
Token | � |
Token ID | 119 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
"> | +7.037 |
Typhoon | +6.453 |
~~~~ | +6.407 |
ype | +5.996 |
� | +5.851 |
Neg logit contributions | |
entary | -21.779 |
itary | -20.770 |
itialized | -20.527 |
gobl | -20.325 |
Beir | -19.740 |
Token | o |
Token ID | 78 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Harding | +0.264 |
Typhoon | +0.263 |
Anth | +0.253 |
Deng | +0.251 |
+. | +0.246 |
Neg logit contributions | |
entary | -0.321 |
itary | -0.307 |
itialized | -0.299 |
FIG | -0.287 |
Feder | -0.287 |
Token | |
Token ID | 220 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
entary | +2.439 |
itary | +2.335 |
itialized | +2.260 |
Feder | +2.219 |
FIG | +2.192 |
Neg logit contributions | |
Harding | -1.764 |
Typhoon | -1.752 |
Anth | -1.696 |
Deng | -1.654 |
ype | -1.633 |
Token | ia |
Token ID | 544 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Typhoon | +5.826 |
Harding | +5.769 |
ype | +5.687 |
+. | +5.538 |
Anth | +5.437 |
Neg logit contributions | |
entary | -11.309 |
itary | -10.754 |
itialized | -10.700 |
Feder | -10.475 |
FIG | -10.471 |
Token | a |
Token ID | 257 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
entary | +1.755 |
itary | +1.673 |
itialized | +1.617 |
Feder | +1.582 |
FIG | +1.566 |
Neg logit contributions | |
Harding | -1.476 |
Typhoon | -1.472 |
Anth | -1.428 |
Deng | -1.398 |
ype | -1.377 |
Token | p |
Token ID | 279 |
Feature activation | -7.71e+00 |
Pos logit contributions | |
entary | +2.445 |
itary | +2.340 |
itialized | +2.253 |
Feder | +2.199 |
FIG | +2.187 |
Neg logit contributions | |
Harding | -1.959 |
Typhoon | -1.948 |
Anth | -1.886 |
Deng | -1.847 |
+. | -1.819 |
Token | ā |
Token ID | 10235 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
Typhoon | +4.440 |
Harding | +4.396 |
ype | +4.364 |
Deng | +4.257 |
Anth | +4.231 |
Neg logit contributions | |
entary | -6.215 |
itialized | -5.989 |
itary | -5.948 |
Feder | -5.709 |
FIG | -5.681 |
Token | h |
Token ID | 71 |
Feature activation | -7.01e+00 |
Pos logit contributions | |
Typhoon | +1.668 |
Harding | +1.667 |
Anth | +1.584 |
Deng | +1.580 |
ype | +1.551 |
Neg logit contributions | |
entary | -2.460 |
itary | -2.353 |
itialized | -2.308 |
FIG | -2.222 |
Feder | -2.215 |
Token | ana |
Token ID | 2271 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Typhoon | +3.640 |
Harding | +3.638 |
ype | +3.527 |
Deng | +3.441 |
Anth | +3.428 |
Neg logit contributions | |
entary | -6.073 |
itary | -5.860 |
itialized | -5.843 |
FIG | -5.637 |
Feder | -5.610 |
Token | ki |
Token ID | 47748 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
Harding | +0.242 |
Typhoon | +0.241 |
Anth | +0.232 |
Deng | +0.230 |
+. | +0.226 |
Neg logit contributions | |
entary | -0.276 |
itary | -0.263 |
itialized | -0.256 |
FIG | -0.246 |
Feder | -0.245 |
Token | � |
Token ID | 134 |
Feature activation | -2.39e+01 |
Pos logit contributions | |
Typhoon | +4.019 |
Harding | +4.004 |
Deng | +3.839 |
Anth | +3.805 |
+. | +3.758 |
Neg logit contributions | |
entary | -6.346 |
itary | -6.119 |
itialized | -5.998 |
FIG | -5.773 |
Feder | -5.684 |
Token | � |
Token ID | 119 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
"> | +6.171 |
~~~~ | +5.440 |
Typhoon | +5.335 |
� | +5.057 |
ype | +4.989 |
Neg logit contributions | |
entary | -22.716 |
gobl | -21.833 |
itary | -21.638 |
itialized | -21.584 |
Feder | -20.761 |
Token | i |
Token ID | 72 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
entary | +0.499 |
itary | +0.472 |
itialized | +0.454 |
FIG | +0.434 |
Feder | +0.432 |
Neg logit contributions | |
Harding | -0.616 |
Typhoon | -0.614 |
Anth | -0.595 |
Deng | -0.590 |
+. | -0.580 |
Token | pa |
Token ID | 14187 |
Feature activation | -9.17e+00 |
Pos logit contributions | |
Harding | +0.610 |
Typhoon | +0.609 |
Anth | +0.585 |
Deng | +0.581 |
+. | +0.570 |
Neg logit contributions | |
entary | -0.779 |
itary | -0.745 |
itialized | -0.726 |
FIG | -0.699 |
Feder | -0.695 |
Token | ia |
Token ID | 544 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
Harding | +4.262 |
Typhoon | +4.242 |
ype | +4.018 |
+. | +3.978 |
Anth | +3.975 |
Neg logit contributions | |
entary | -8.345 |
itialized | -8.029 |
itary | -7.965 |
FIG | -7.803 |
Feder | -7.646 |
Token | ma |
Token ID | 17266 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
entary | +0.648 |
itary | +0.620 |
itialized | +0.602 |
Feder | +0.582 |
FIG | +0.581 |
Neg logit contributions | |
Harding | -0.507 |
Typhoon | -0.505 |
Anth | -0.487 |
Deng | -0.480 |
+. | -0.471 |
Token | ho |
Token ID | 8873 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
entary | +0.319 |
itary | +0.306 |
itialized | +0.297 |
FIG | +0.287 |
Feder | +0.286 |
Neg logit contributions | |
Harding | -0.245 |
Typhoon | -0.244 |
Anth | -0.235 |
Deng | -0.232 |
+. | -0.228 |
Token | m |
Token ID | 285 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
entary | +1.850 |
itary | +1.771 |
itialized | +1.712 |
Feder | +1.665 |
FIG | +1.660 |
Neg logit contributions | |
Harding | -1.430 |
Typhoon | -1.424 |
Anth | -1.373 |
Deng | -1.351 |
+. | -1.320 |
Token | ak |
Token ID | 461 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Harding | +0.431 |
Typhoon | +0.430 |
Anth | +0.411 |
Deng | +0.406 |
ype | +0.397 |
Neg logit contributions | |
entary | -0.713 |
itary | -0.685 |
itialized | -0.670 |
FIG | -0.647 |
Feder | -0.646 |
Token | ua |
Token ID | 6413 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
Typhoon | +1.169 |
Harding | +1.164 |
Anth | +1.100 |
Deng | +1.097 |
ype | +1.079 |
Neg logit contributions | |
entary | -2.139 |
itary | -2.058 |
itialized | -2.028 |
FIG | -1.958 |
Feder | -1.949 |
Token | |
Token ID | 220 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
entary | +2.985 |
itary | +2.848 |
itialized | +2.732 |
Feder | +2.692 |
FIG | +2.666 |
Neg logit contributions | |
Harding | -2.418 |
Typhoon | -2.406 |
Anth | -2.344 |
Deng | -2.285 |
ype | -2.242 |
Token | � |
Token ID | 134 |
Feature activation | -2.39e+01 |
Pos logit contributions | |
Typhoon | +3.421 |
Harding | +3.308 |
+. | +3.179 |
~~~~ | +3.141 |
Deng | +3.125 |
Neg logit contributions | |
entary | -11.615 |
itary | -11.022 |
itialized | -10.895 |
Feder | -10.692 |
FIG | -10.580 |
Token | � |
Token ID | 119 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
"> | +5.868 |
~~~~ | +5.431 |
Typhoon | +5.169 |
� | +4.865 |
ype | +4.799 |
Neg logit contributions | |
entary | -23.047 |
itary | -22.031 |
itialized | -21.937 |
gobl | -21.919 |
Feder | -21.052 |
Token | ole |
Token ID | 2305 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
entary | +1.769 |
itary | +1.692 |
itialized | +1.632 |
FIG | +1.575 |
igned | +1.569 |
Neg logit contributions | |
Harding | -1.494 |
Typhoon | -1.487 |
Anth | -1.428 |
Deng | -1.418 |
+. | -1.377 |
Token | |
Token ID | 220 |
Feature activation | -9.52e+00 |
Pos logit contributions | |
entary | +3.150 |
itary | +2.993 |
itialized | +2.892 |
Feder | +2.818 |
FIG | +2.800 |
Neg logit contributions | |
Harding | -2.756 |
Typhoon | -2.722 |
Anth | -2.670 |
Deng | -2.611 |
ype | -2.529 |
Token | � |
Token ID | 134 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
Typhoon | +4.455 |
Harding | +4.388 |
+. | +4.223 |
Anth | +4.149 |
ype | +4.149 |
Neg logit contributions | |
entary | -8.668 |
itary | -8.295 |
itialized | -8.124 |
Feder | -7.982 |
FIG | -7.951 |
Token | � |
Token ID | 119 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
"> | +4.765 |
Typhoon | +4.510 |
~~~~ | +4.184 |
ype | +3.920 |
Deng | +3.827 |
Neg logit contributions | |
entary | -20.451 |
itary | -19.618 |
itialized | -19.377 |
Feder | -18.865 |
gobl | -18.665 |
Token | amp |
Token ID | 696 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
Harding | +0.182 |
Typhoon | +0.181 |
Anth | +0.172 |
Deng | +0.169 |
+. | +0.165 |
Neg logit contributions | |
entary | -0.363 |
itary | -0.349 |
itialized | -0.342 |
FIG | -0.331 |
Feder | -0.331 |
Token | the |
Token ID | 262 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
entary | +0.452 |
itary | +0.431 |
itialized | +0.416 |
Feder | +0.401 |
FIG | +0.400 |
Neg logit contributions | |
Typhoon | -0.453 |
Harding | -0.452 |
Anth | -0.439 |
Deng | -0.433 |
+. | -0.426 |
Token | recreational |
Token ID | 18136 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
entary | +4.855 |
itary | +4.708 |
Feder | +4.561 |
itialized | +4.439 |
wastes | +4.396 |
Neg logit contributions | |
Typhoon | -4.856 |
Anth | -4.749 |
ype | -4.587 |
Harding | -4.575 |
Deng | -4.563 |
Token | paths |
Token ID | 13532 |
Feature activation | +8.96e+00 |
Pos logit contributions | |
entary | +4.007 |
itary | +3.935 |
Feder | +3.717 |
itialized | +3.692 |
wastes | +3.689 |
Neg logit contributions | |
Typhoon | -4.349 |
Anth | -4.275 |
Harding | -4.220 |
Deng | -4.097 |
ype | -4.042 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
entary | +5.800 |
itary | +5.674 |
Feder | +5.472 |
igned | +5.295 |
wastes | +5.278 |
Neg logit contributions | |
Anth | -6.473 |
Typhoon | -6.447 |
Harding | -6.256 |
ype | -6.141 |
Deng | -6.057 |
Token | That |
Token ID | 1320 |
Feature activation | +2.09e+01 |
Pos logit contributions | |
entary | +2.426 |
itary | +2.289 |
itialized | +2.213 |
Feder | +2.211 |
FIG | +2.150 |
Neg logit contributions | |
Typhoon | -2.406 |
Harding | -2.386 |
Anth | -2.367 |
ype | -2.308 |
Deng | -2.285 |
Token | proposal |
Token ID | 6961 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
entary | +11.253 |
Feder | +10.894 |
wastes | +10.883 |
itary | +10.653 |
igned | +10.613 |
Neg logit contributions | |
Anth | -13.973 |
Typhoon | -12.992 |
ackets | -12.987 |
ype | -12.938 |
Harding | -12.758 |
Token | was |
Token ID | 373 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
entary | +4.045 |
itary | +3.885 |
wastes | +3.668 |
Feder | +3.666 |
itialized | +3.645 |
Neg logit contributions | |
Typhoon | -4.542 |
Anth | -4.505 |
Harding | -4.478 |
ype | -4.352 |
+. | -4.301 |
Token | developed |
Token ID | 4166 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
entary | +2.168 |
itary | +2.077 |
itialized | +1.981 |
Feder | +1.938 |
igned | +1.918 |
Neg logit contributions | |
Typhoon | -2.217 |
Harding | -2.214 |
Anth | -2.170 |
Deng | -2.118 |
ype | -2.103 |
Token | through |
Token ID | 832 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
entary | +3.605 |
itary | +3.471 |
Feder | +3.287 |
itialized | +3.286 |
wastes | +3.228 |
Neg logit contributions | |
Typhoon | -3.031 |
Harding | -2.982 |
Anth | -2.967 |
Deng | -2.829 |
ype | -2.823 |
Token | a |
Token ID | 257 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
Harding | +2.618 |
Typhoon | +2.589 |
Deng | +2.491 |
Anth | +2.438 |
+. | +2.418 |
Neg logit contributions | |
entary | -2.780 |
itary | -2.680 |
itialized | -2.613 |
FIG | -2.502 |
Feder | -2.420 |
Token | Do |
Token ID | 5211 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
entary | +1.588 |
itary | +1.523 |
itialized | +1.464 |
FIG | +1.436 |
Feder | +1.413 |
Neg logit contributions | |
Harding | -1.464 |
Typhoon | -1.459 |
Deng | -1.396 |
Anth | -1.385 |
ype | -1.362 |
Token | you |
Token ID | 345 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
entary | +4.549 |
itary | +4.261 |
Feder | +4.058 |
itialized | +4.026 |
FIG | +3.912 |
Neg logit contributions | |
Anth | -6.574 |
Typhoon | -6.544 |
Harding | -6.544 |
ype | -6.334 |
Deng | -6.298 |
Token | think |
Token ID | 892 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
entary | +3.827 |
itary | +3.580 |
Feder | +3.460 |
itialized | +3.421 |
FIG | +3.370 |
Neg logit contributions | |
Harding | -4.306 |
Anth | -4.260 |
Typhoon | -4.239 |
ype | -4.093 |
Deng | -4.081 |
Token | that |
Token ID | 326 |
Feature activation | +9.65e+00 |
Pos logit contributions | |
entary | +4.793 |
itary | +4.648 |
Feder | +4.436 |
itialized | +4.386 |
FIG | +4.272 |
Neg logit contributions | |
Harding | -4.048 |
Anth | -4.045 |
Typhoon | -3.960 |
ype | -3.874 |
+. | -3.838 |
Token | teen |
Token ID | 6036 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
entary | +6.359 |
itary | +6.195 |
Feder | +6.026 |
wastes | +5.824 |
mockery | +5.755 |
Neg logit contributions | |
Anth | -6.776 |
Harding | -6.573 |
Typhoon | -6.480 |
ype | -6.434 |
+. | -6.324 |
Token | girls |
Token ID | 4813 |
Feature activation | +1.78e+01 |
Pos logit contributions | |
entary | +4.214 |
itary | +4.036 |
itialized | +3.817 |
Feder | +3.749 |
igned | +3.741 |
Neg logit contributions | |
Typhoon | -5.305 |
Anth | -5.246 |
Harding | -5.243 |
Deng | -5.077 |
ype | -4.977 |
Token | dressing |
Token ID | 18544 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
entary | +9.552 |
wastes | +9.484 |
Feder | +9.476 |
itary | +9.095 |
igned | +9.021 |
Neg logit contributions | |
Anth | -12.311 |
Typhoon | -12.109 |
Harding | -11.919 |
Deng | -11.511 |
ype | -11.359 |
Token | up |
Token ID | 510 |
Feature activation | +9.69e+00 |
Pos logit contributions | |
entary | +0.322 |
itary | +0.307 |
itialized | +0.297 |
FIG | +0.287 |
Feder | +0.286 |
Neg logit contributions | |
Harding | -0.283 |
Typhoon | -0.282 |
Anth | -0.272 |
Deng | -0.269 |
+. | -0.265 |
Token | as |
Token ID | 355 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
entary | +5.459 |
itary | +5.263 |
Feder | +4.910 |
FIG | +4.799 |
wastes | +4.794 |
Neg logit contributions | |
Harding | -7.890 |
Anth | -7.818 |
Typhoon | -7.691 |
+. | -7.510 |
Deng | -7.418 |
Token | real |
Token ID | 1103 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
entary | +6.394 |
itary | +5.973 |
Feder | +5.705 |
itialized | +5.580 |
FIG | +5.479 |
Neg logit contributions | |
Anth | -8.064 |
Harding | -7.945 |
Typhoon | -7.850 |
+. | -7.783 |
ype | -7.714 |
Token | dolls |
Token ID | 36062 |
Feature activation | +1.78e+01 |
Pos logit contributions | |
entary | +3.902 |
itary | +3.748 |
itialized | +3.482 |
igned | +3.412 |
Feder | +3.405 |
Neg logit contributions | |
Typhoon | -4.828 |
Anth | -4.817 |
Harding | -4.794 |
Deng | -4.669 |
+. | -4.634 |
Token | fl |
Token ID | 2704 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
entary | +3.574 |
itary | +3.309 |
FIG | +3.094 |
itialized | +3.047 |
Feder | +2.905 |
Neg logit contributions | |
Harding | -8.961 |
Typhoon | -8.857 |
Anth | -8.855 |
Deng | -8.783 |
ype | -8.517 |
Token | i |
Token ID | 72 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
entary | +0.480 |
itary | +0.453 |
itialized | +0.432 |
FIG | +0.414 |
Feder | +0.411 |
Neg logit contributions | |
Harding | -0.679 |
Typhoon | -0.677 |
Anth | -0.658 |
Deng | -0.651 |
+. | -0.642 |
Token | X |
Token ID | 55 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
Typhoon | +1.817 |
Harding | +1.808 |
Anth | +1.739 |
Deng | +1.706 |
+. | +1.696 |
Neg logit contributions | |
entary | -3.050 |
itary | -2.961 |
itialized | -2.871 |
Feder | -2.780 |
FIG | -2.740 |
Token | B |
Token ID | 33 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
entary | +2.853 |
itary | +2.664 |
itialized | +2.603 |
FIG | +2.534 |
Feder | +2.477 |
Neg logit contributions | |
Harding | -3.626 |
Typhoon | -3.606 |
Deng | -3.526 |
Anth | -3.525 |
ype | -3.433 |
Token | MC |
Token ID | 9655 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
entary | +2.588 |
FIG | +2.155 |
itary | +2.082 |
itialized | +1.950 |
igned | +1.799 |
Neg logit contributions | |
Harding | -12.434 |
Typhoon | -12.363 |
Deng | -12.126 |
Anth | -12.114 |
ype | -11.759 |
Token | around |
Token ID | 1088 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
entary | +2.658 |
itary | +2.519 |
itialized | +2.440 |
FIG | +2.383 |
Feder | +2.367 |
Neg logit contributions | |
Harding | -2.601 |
Typhoon | -2.566 |
Anth | -2.524 |
Deng | -2.486 |
ype | -2.438 |
Token | Kodi |
Token ID | 44129 |
Feature activation | +9.97e+00 |
Pos logit contributions | |
entary | +8.582 |
itary | +7.969 |
itialized | +7.791 |
Feder | +7.697 |
FIG | +7.589 |
Neg logit contributions | |
Anth | -11.058 |
Harding | -10.705 |
ype | -10.296 |
Deng | -10.229 |
Typhoon | -10.169 |
Token | 17 |
Token ID | 1596 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
entary | +6.522 |
itary | +6.114 |
itialized | +5.891 |
Feder | +5.833 |
FIG | +5.763 |
Neg logit contributions | |
Anth | -7.088 |
Harding | -6.995 |
ype | -6.820 |
Typhoon | -6.789 |
Deng | -6.780 |
Token | Krypt |
Token ID | 44679 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
entary | +6.663 |
itary | +6.120 |
itialized | +5.979 |
igned | +5.789 |
Feder | +5.776 |
Neg logit contributions | |
Anth | -9.331 |
Harding | -9.295 |
Deng | -8.943 |
ype | -8.938 |
Typhoon | -8.797 |
Token | on |
Token ID | 261 |
Feature activation | +9.25e+00 |
Pos logit contributions | |
Harding | +1.189 |
Typhoon | +1.189 |
Anth | +1.146 |
Deng | +1.126 |
ype | +1.120 |
Neg logit contributions | |
entary | -1.735 |
itary | -1.656 |
itialized | -1.635 |
Feder | -1.571 |
FIG | -1.562 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
entary | +6.306 |
itary | +5.999 |
itialized | +5.791 |
FIG | +5.679 |
Feder | +5.654 |
Neg logit contributions | |
Harding | -6.504 |
Anth | -6.388 |
Typhoon | -6.277 |
Deng | -6.165 |
ype | -6.011 |
Token | ***** |
Token ID | 35625 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Harding | +1.957 |
Typhoon | +1.943 |
Anth | +1.923 |
Deng | +1.859 |
+. | +1.853 |
Neg logit contributions | |
entary | -2.280 |
itary | -2.160 |
itialized | -2.123 |
Feder | -2.023 |
wastes | -1.993 |
Token | When |
Token ID | 1649 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
Harding | +0.234 |
Typhoon | +0.233 |
Anth | +0.225 |
Deng | +0.223 |
+. | +0.219 |
Neg logit contributions | |
entary | -0.262 |
itary | -0.250 |
itialized | -0.243 |
FIG | -0.233 |
Feder | -0.232 |
Token | we |
Token ID | 356 |
Feature activation | -8.34e+00 |
Pos logit contributions | |
Harding | +2.105 |
Typhoon | +2.101 |
Anth | +2.018 |
Deng | +2.016 |
+. | +1.977 |
Neg logit contributions | |
entary | -1.848 |
itary | -1.742 |
itialized | -1.665 |
FIG | -1.607 |
Feder | -1.587 |
Token | watched |
Token ID | 7342 |
Feature activation | +9.98e+00 |
Pos logit contributions | |
Harding | +6.618 |
Typhoon | +6.611 |
Deng | +6.432 |
Anth | +6.366 |
"> | +6.354 |
Neg logit contributions | |
entary | -5.117 |
itary | -4.781 |
itialized | -4.656 |
FIG | -4.393 |
Feder | -4.315 |
Token | this |
Token ID | 428 |
Feature activation | +8.61e+00 |
Pos logit contributions | |
entary | +5.739 |
itary | +5.538 |
Feder | +5.446 |
itialized | +5.271 |
wastes | +5.225 |
Neg logit contributions | |
Typhoon | -7.654 |
Harding | -7.639 |
Anth | -7.581 |
+. | -7.256 |
atus | -7.153 |
Token | little |
Token ID | 1310 |
Feature activation | +1.76e+01 |
Pos logit contributions | |
entary | +3.842 |
itary | +3.634 |
Feder | +3.466 |
igned | +3.347 |
itialized | +3.297 |
Neg logit contributions | |
Harding | -7.991 |
Anth | -7.955 |
Typhoon | -7.846 |
Deng | -7.579 |
+. | -7.498 |
Token | gag |
Token ID | 32261 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
entary | +6.836 |
itary | +5.806 |
mockery | +5.782 |
wastes | +5.726 |
Feder | +5.589 |
Neg logit contributions | |
Typhoon | -15.673 |
Anth | -15.593 |
Harding | -15.350 |
ackets | -14.915 |
meier | -14.899 |
Token | with |
Token ID | 351 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
Harding | +0.370 |
Typhoon | +0.369 |
Anth | +0.354 |
Deng | +0.352 |
+. | +0.345 |
Neg logit contributions | |
entary | -0.475 |
itary | -0.454 |
itialized | -0.442 |
FIG | -0.425 |
Feder | -0.424 |
Token | Erin |
Token ID | 28894 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
entary | +7.195 |
itary | +6.492 |
Feder | +6.416 |
itialized | +6.413 |
igned | +6.072 |
Neg logit contributions | |
Typhoon | -12.187 |
Anth | -11.736 |
Harding | -11.713 |
Deng | -11.326 |
+. | -11.187 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
Harding | +1.343 |
Typhoon | +1.321 |
Deng | +1.280 |
Anth | +1.265 |
+. | +1.244 |
Neg logit contributions | |
entary | -1.661 |
itary | -1.575 |
itialized | -1.551 |
FIG | -1.471 |
igned | -1.456 |
Token | Jill |
Token ID | 22772 |
Feature activation | +8.92e+00 |
Pos logit contributions | |
itary | +6.020 |
Feder | +5.884 |
entary | +5.841 |
itialized | +5.658 |
ilan | +5.499 |
Neg logit contributions | |
Typhoon | -10.157 |
Anth | -9.896 |
Harding | -9.787 |
ype | -9.697 |
+. | -9.433 |
Token | POS |
Token ID | 28069 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
entary | +3.610 |
itary | +3.413 |
itialized | +3.308 |
Feder | +3.235 |
FIG | +3.198 |
Neg logit contributions | |
Harding | -4.571 |
Anth | -4.487 |
Typhoon | -4.454 |
Deng | -4.390 |
ype | -4.281 |
Token | runs |
Token ID | 4539 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
entary | +5.897 |
itary | +5.552 |
Feder | +5.446 |
itialized | +5.413 |
wastes | +5.401 |
Neg logit contributions | |
Harding | -6.204 |
Anth | -6.121 |
Typhoon | -6.000 |
Deng | -5.930 |
ype | -5.847 |
Token | on |
Token ID | 319 |
Feature activation | +6.62e+00 |
Pos logit contributions | |
entary | +6.013 |
itary | +5.713 |
Feder | +5.565 |
itialized | +5.395 |
NFC | +5.289 |
Neg logit contributions | |
Harding | -6.583 |
Anth | -6.562 |
Typhoon | -6.369 |
Deng | -6.295 |
ype | -6.279 |
Token | an |
Token ID | 281 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
entary | +4.471 |
itary | +4.291 |
Feder | +4.152 |
itialized | +4.052 |
igned | +3.954 |
Neg logit contributions | |
Harding | -4.843 |
Anth | -4.805 |
Typhoon | -4.752 |
Deng | -4.633 |
ype | -4.563 |
Token | iPad |
Token ID | 13133 |
Feature activation | +8.52e+00 |
Pos logit contributions | |
entary | +0.816 |
itary | +0.774 |
itialized | +0.744 |
Feder | +0.720 |
FIG | +0.718 |
Neg logit contributions | |
Harding | -0.926 |
Typhoon | -0.923 |
Anth | -0.898 |
Deng | -0.887 |
+. | -0.873 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e+01 |
Pos logit contributions | |
entary | +6.057 |
itary | +5.577 |
itialized | +5.476 |
Feder | +5.422 |
FIG | +5.305 |
Neg logit contributions | |
Harding | -6.011 |
Anth | -5.966 |
Typhoon | -5.856 |
Deng | -5.787 |
ype | -5.567 |
Token | requires |
Token ID | 4433 |
Feature activation | +1.78e+01 |
Pos logit contributions | |
entary | +9.753 |
NFC | +9.529 |
Feder | +9.295 |
wastes | +8.920 |
itary | +8.917 |
Neg logit contributions | |
Anth | -11.503 |
Harding | -11.135 |
Typhoon | -10.523 |
Deng | -10.490 |
ype | -10.405 |
Token | only |
Token ID | 691 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
entary | +10.049 |
NFC | +9.778 |
Feder | +9.622 |
itary | +9.470 |
igned | +8.886 |
Neg logit contributions | |
Anth | -12.990 |
Harding | -12.183 |
Typhoon | -11.893 |
Deng | -11.852 |
ype | -11.762 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
entary | +8.737 |
Feder | +8.306 |
itary | +8.300 |
NFC | +8.072 |
itialized | +7.560 |
Neg logit contributions | |
Anth | -11.593 |
Harding | -11.045 |
Typhoon | -10.690 |
Deng | -10.668 |
~~~~ | -10.506 |
Token | free |
Token ID | 1479 |
Feature activation | +7.90e+00 |
Pos logit contributions | |
entary | +7.914 |
Feder | +7.685 |
itary | +7.603 |
NFC | +7.445 |
igned | +7.349 |
Neg logit contributions | |
Anth | -9.053 |
Harding | -8.951 |
Typhoon | -8.793 |
Deng | -8.792 |
~~~~ | -8.345 |
Token | Shop |
Token ID | 13705 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
entary | +5.582 |
itary | +5.388 |
Feder | +5.199 |
igned | +5.036 |
itialized | +5.034 |
Neg logit contributions | |
Harding | -5.414 |
Anth | -5.362 |
Typhoon | -5.304 |
Deng | -5.187 |
ype | -5.042 |
Token | on |
Token ID | 319 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Harding | +0.089 |
Typhoon | +0.088 |
Anth | +0.085 |
Deng | +0.085 |
+. | +0.083 |
Neg logit contributions | |
entary | -0.096 |
itary | -0.092 |
itialized | -0.089 |
FIG | -0.086 |
Feder | -0.085 |
Token | employees |
Token ID | 4409 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
Harding | +1.193 |
Typhoon | +1.188 |
Deng | +1.128 |
Anth | +1.126 |
+. | +1.107 |
Neg logit contributions | |
entary | -1.417 |
itary | -1.352 |
itialized | -1.322 |
FIG | -1.268 |
Feder | -1.252 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
entary | +3.351 |
itary | +3.208 |
itialized | +3.013 |
Feder | +3.012 |
wastes | +2.941 |
Neg logit contributions | |
Typhoon | -3.373 |
Harding | -3.356 |
Anth | -3.307 |
Deng | -3.225 |
ype | -3.172 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
entary | +1.452 |
itary | +1.378 |
itialized | +1.331 |
Feder | +1.310 |
FIG | +1.302 |
Neg logit contributions | |
Harding | -1.346 |
Typhoon | -1.343 |
Anth | -1.310 |
Deng | -1.282 |
+. | -1.274 |
Token |
|
Token ID | 198 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
entary | +0.128 |
itary | +0.122 |
itialized | +0.119 |
FIG | +0.114 |
Feder | +0.114 |
Neg logit contributions | |
Harding | -0.112 |
Typhoon | -0.112 |
Anth | -0.108 |
Deng | -0.107 |
+. | -0.105 |
Token | Ms |
Token ID | 10128 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
Harding | +2.084 |
Typhoon | +2.073 |
Anth | +2.051 |
"> | +1.973 |
Deng | +1.970 |
Neg logit contributions | |
entary | -2.709 |
itary | -2.590 |
itialized | -2.552 |
Feder | -2.406 |
wastes | -2.396 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
entary | +4.827 |
itary | +4.716 |
Feder | +4.505 |
igned | +4.352 |
FIG | +4.340 |
Neg logit contributions | |
Typhoon | -5.821 |
Anth | -5.705 |
Harding | -5.654 |
ype | -5.438 |
Deng | -5.415 |
Token | Lap |
Token ID | 26944 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
entary | +1.871 |
itary | +1.704 |
itialized | +1.615 |
Feder | +1.570 |
FIG | +1.505 |
Neg logit contributions | |
Typhoon | -3.886 |
Harding | -3.849 |
Anth | -3.826 |
+. | -3.762 |
Deng | -3.740 |
Token | eral |
Token ID | 1691 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
itary | +5.675 |
entary | +5.576 |
igned | +4.868 |
ilan | +4.714 |
Feder | +4.529 |
Neg logit contributions | |
Typhoon | -12.823 |
Harding | -12.260 |
Deng | -12.197 |
Anth | -12.118 |
psi | -11.687 |
Token | also |
Token ID | 635 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Harding | +1.159 |
Typhoon | +1.149 |
Deng | +1.103 |
Anth | +1.100 |
ype | +1.067 |
Neg logit contributions | |
entary | -1.509 |
itary | -1.445 |
itialized | -1.413 |
FIG | -1.352 |
Feder | -1.338 |
Token | reached |
Token ID | 4251 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Harding | +1.879 |
Typhoon | +1.864 |
Deng | +1.799 |
Anth | +1.786 |
ype | +1.738 |
Neg logit contributions | |
entary | -2.055 |
itary | -1.951 |
itialized | -1.907 |
FIG | -1.817 |
Feder | -1.784 |
Token | + |
Token ID | 1343 |
Feature activation | +7.98e+00 |
Pos logit contributions | |
entary | +1.788 |
itary | +1.709 |
itialized | +1.636 |
Feder | +1.587 |
FIG | +1.586 |
Neg logit contributions | |
Typhoon | -1.628 |
Harding | -1.625 |
Anth | -1.580 |
Deng | -1.544 |
ype | -1.521 |
Token | - |
Token ID | 532 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
entary | +6.444 |
itary | +6.232 |
itialized | +5.895 |
igned | +5.804 |
Feder | +5.774 |
Neg logit contributions | |
Harding | -4.769 |
Typhoon | -4.743 |
Anth | -4.566 |
+. | -4.384 |
ype | -4.358 |
Token | cin |
Token ID | 17879 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
entary | +9.222 |
itary | +9.032 |
igned | +8.396 |
ilan | +8.340 |
itialized | +8.328 |
Neg logit contributions | |
Harding | -7.795 |
Typhoon | -7.794 |
Anth | -7.200 |
+. | -7.017 |
Deng | -6.978 |
Token | = |
Token ID | 796 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
entary | +4.716 |
itary | +4.553 |
itialized | +4.275 |
igned | +4.155 |
wastes | +4.126 |
Neg logit contributions | |
Typhoon | -4.566 |
Harding | -4.537 |
Anth | -4.404 |
Deng | -4.260 |
"> | -4.193 |
Token | tem |
Token ID | 2169 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
entary | +1.847 |
itary | +1.769 |
itialized | +1.704 |
Feder | +1.651 |
FIG | +1.644 |
Neg logit contributions | |
Harding | -1.492 |
Typhoon | -1.485 |
Anth | -1.436 |
Deng | -1.410 |
ype | -1.392 |
Token | ü |
Token ID | 9116 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
entary | +5.093 |
itary | +4.842 |
itialized | +4.620 |
igned | +4.499 |
FIG | +4.472 |
Neg logit contributions | |
Typhoon | -4.456 |
Harding | -4.440 |
Anth | -4.278 |
Deng | -4.125 |
+. | -4.073 |
Token | jin |
Token ID | 18594 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
entary | +7.350 |
itary | +7.033 |
itialized | +6.775 |
igned | +6.442 |
Feder | +6.428 |
Neg logit contributions | |
Harding | -7.370 |
Typhoon | -7.310 |
Anth | -7.202 |
ype | -6.853 |
Deng | -6.789 |
Token | ' |
Token ID | 705 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
entary | +7.261 |
itary | +7.104 |
itialized | +6.515 |
igned | +6.400 |
Feder | +6.291 |
Neg logit contributions | |
Typhoon | -6.728 |
Harding | -6.693 |
Anth | -6.485 |
Deng | -6.203 |
"> | -6.146 |
Token | smith |
Token ID | 21453 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Harding | +1.297 |
Typhoon | +1.293 |
Anth | +1.262 |
Deng | +1.238 |
+. | +1.228 |
Neg logit contributions | |
entary | -1.206 |
itary | -1.138 |
itialized | -1.111 |
Feder | -1.065 |
FIG | -1.051 |
Token | '. |
Token ID | 4458 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
entary | +0.351 |
itary | +0.337 |
itialized | +0.328 |
FIG | +0.317 |
Feder | +0.316 |
Neg logit contributions | |
Harding | -0.228 |
Typhoon | -0.227 |
Anth | -0.217 |
Deng | -0.215 |
+. | -0.210 |
Token |
|
Token ID | 198 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
entary | +1.794 |
itary | +1.718 |
itialized | +1.656 |
Feder | +1.621 |
FIG | +1.618 |
Neg logit contributions | |
Harding | -1.435 |
Typhoon | -1.434 |
Anth | -1.393 |
Deng | -1.357 |
ype | -1.346 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
entary | +5.171 |
itary | +4.991 |
Feder | +4.667 |
itialized | +4.621 |
igned | +4.587 |
Neg logit contributions | |
Typhoon | -5.511 |
Harding | -5.481 |
Anth | -5.350 |
Deng | -5.181 |
ype | -5.088 |
Token | female |
Token ID | 4048 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
Harding | +0.929 |
Typhoon | +0.925 |
Anth | +0.893 |
Deng | +0.887 |
+. | +0.869 |
Neg logit contributions | |
entary | -1.011 |
itary | -0.962 |
itialized | -0.937 |
FIG | -0.897 |
Feder | -0.887 |
Token | - |
Token ID | 12 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
entary | +3.351 |
itary | +3.175 |
itialized | +3.050 |
Feder | +3.037 |
wastes | +2.976 |
Neg logit contributions | |
Typhoon | -3.626 |
Harding | -3.606 |
Anth | -3.539 |
ype | -3.513 |
Deng | -3.462 |
Token | centric |
Token ID | 28577 |
Feature activation | +7.98e+00 |
Pos logit contributions | |
entary | +3.317 |
itary | +3.121 |
itialized | +2.978 |
FIG | +2.940 |
igned | +2.900 |
Neg logit contributions | |
Typhoon | -4.767 |
Harding | -4.723 |
Anth | -4.546 |
Deng | -4.536 |
ype | -4.490 |
Token | stories |
Token ID | 3923 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
entary | +5.175 |
itary | +4.894 |
Feder | +4.760 |
wastes | +4.657 |
itialized | +4.637 |
Neg logit contributions | |
Harding | -5.838 |
Typhoon | -5.834 |
Anth | -5.716 |
ype | -5.671 |
Deng | -5.586 |
Token | are |
Token ID | 389 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
entary | +3.789 |
itary | +3.619 |
itialized | +3.468 |
Feder | +3.436 |
wastes | +3.412 |
Neg logit contributions | |
Typhoon | -3.640 |
Harding | -3.607 |
Anth | -3.525 |
Deng | -3.441 |
+. | -3.427 |
Token | often |
Token ID | 1690 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
entary | +4.075 |
itary | +3.879 |
Feder | +3.736 |
igned | +3.672 |
wastes | +3.638 |
Neg logit contributions | |
Harding | -3.904 |
Typhoon | -3.872 |
Anth | -3.752 |
ype | -3.724 |
+. | -3.690 |
Token | pushed |
Token ID | 7121 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
entary | +6.706 |
itary | +6.447 |
Feder | +6.370 |
igned | +6.345 |
wastes | +6.239 |
Neg logit contributions | |
Harding | -7.022 |
Typhoon | -6.954 |
ype | -6.755 |
Anth | -6.719 |
+. | -6.672 |
Token | into |
Token ID | 656 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
entary | +2.552 |
itary | +2.419 |
itialized | +2.307 |
Feder | +2.290 |
wastes | +2.259 |
Neg logit contributions | |
Harding | -2.409 |
Typhoon | -2.397 |
Anth | -2.323 |
Deng | -2.291 |
ype | -2.264 |
Token | the |
Token ID | 262 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
Harding | +0.366 |
Typhoon | +0.365 |
Anth | +0.352 |
Deng | +0.349 |
+. | +0.343 |
Neg logit contributions | |
entary | -0.370 |
itary | -0.352 |
itialized | -0.341 |
FIG | -0.327 |
Feder | -0.326 |
Token | more |
Token ID | 517 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
entary | +0.445 |
itary | +0.422 |
itialized | +0.409 |
Feder | +0.392 |
FIG | +0.391 |
Neg logit contributions | |
Harding | -0.478 |
Typhoon | -0.478 |
Anth | -0.462 |
Deng | -0.457 |
+. | -0.451 |
Token | want |
Token ID | 765 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
entary | +6.653 |
itary | +6.310 |
itialized | +6.282 |
wastes | +6.170 |
FIG | +6.076 |
Neg logit contributions | |
Anth | -8.308 |
Harding | -8.250 |
Typhoon | -8.139 |
Deng | -7.821 |
+. | -7.600 |
Token | a |
Token ID | 257 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
entary | +2.289 |
itary | +2.185 |
itialized | +2.119 |
Feder | +2.023 |
FIG | +2.016 |
Neg logit contributions | |
Harding | -2.258 |
Typhoon | -2.251 |
Anth | -2.201 |
Deng | -2.143 |
ype | -2.106 |
Token | graph |
Token ID | 4823 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
Harding | +3.863 |
Typhoon | +3.856 |
Deng | +3.713 |
+. | +3.673 |
Anth | +3.648 |
Neg logit contributions | |
entary | -3.812 |
itary | -3.602 |
itialized | -3.489 |
FIG | -3.363 |
Feder | -3.295 |
Token | so |
Token ID | 523 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
entary | +2.594 |
itary | +2.493 |
itialized | +2.413 |
FIG | +2.299 |
Feder | +2.284 |
Neg logit contributions | |
Typhoon | -2.622 |
Harding | -2.618 |
Anth | -2.556 |
Deng | -2.489 |
ype | -2.439 |
Token | that |
Token ID | 326 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
Harding | +0.270 |
Typhoon | +0.269 |
Anth | +0.260 |
Deng | +0.258 |
+. | +0.254 |
Neg logit contributions | |
entary | -0.271 |
itary | -0.258 |
itialized | -0.250 |
FIG | -0.240 |
Feder | -0.239 |
Token | we |
Token ID | 356 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
Harding | +0.492 |
Typhoon | +0.491 |
Anth | +0.473 |
Deng | +0.471 |
+. | +0.463 |
Neg logit contributions | |
entary | -0.468 |
itary | -0.443 |
itialized | -0.429 |
FIG | -0.411 |
Feder | -0.410 |
Token | may |
Token ID | 743 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
entary | +3.642 |
itary | +3.467 |
itialized | +3.360 |
FIG | +3.297 |
Feder | +3.286 |
Neg logit contributions | |
Harding | -3.848 |
Typhoon | -3.828 |
Anth | -3.790 |
Deng | -3.650 |
ype | -3.612 |
Token | take |
Token ID | 1011 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
entary | +2.399 |
itary | +2.286 |
itialized | +2.203 |
FIG | +2.154 |
Feder | +2.134 |
Neg logit contributions | |
Harding | -2.477 |
Typhoon | -2.464 |
Anth | -2.426 |
Deng | -2.349 |
ype | -2.314 |
Token | advantage |
Token ID | 4621 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
Harding | +0.973 |
Typhoon | +0.967 |
Anth | +0.929 |
Deng | +0.926 |
+. | +0.912 |
Neg logit contributions | |
entary | -1.064 |
itary | -1.011 |
itialized | -0.983 |
FIG | -0.944 |
Feder | -0.939 |
Token | of |
Token ID | 286 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
Typhoon | +4.126 |
Harding | +4.059 |
Deng | +3.868 |
+. | +3.855 |
Anth | +3.820 |
Neg logit contributions | |
entary | -5.651 |
itary | -5.446 |
itialized | -5.295 |
Feder | -5.116 |
FIG | -5.089 |
Token | its |
Token ID | 663 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
Typhoon | +7.048 |
Harding | +7.003 |
Deng | +6.703 |
+. | +6.645 |
"> | +6.452 |
Neg logit contributions | |
entary | -8.341 |
itary | -7.730 |
itialized | -7.493 |
FIG | -7.306 |
igned | -7.180 |
Token | yesterday |
Token ID | 7415 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
entary | +2.094 |
itary | +2.006 |
itialized | +1.918 |
Feder | +1.883 |
FIG | +1.851 |
Neg logit contributions | |
Typhoon | -2.175 |
Harding | -2.168 |
Anth | -2.128 |
Deng | -2.076 |
+. | -2.036 |
Token | . |
Token ID | 13 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
entary | +2.555 |
itary | +2.448 |
itialized | +2.341 |
Feder | +2.323 |
FIG | +2.278 |
Neg logit contributions | |
Typhoon | -2.414 |
Harding | -2.396 |
Anth | -2.354 |
Deng | -2.291 |
ype | -2.252 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
entary | +4.879 |
Feder | +4.563 |
itary | +4.544 |
FIG | +4.402 |
itialized | +4.387 |
Neg logit contributions | |
Harding | -4.940 |
Typhoon | -4.936 |
Anth | -4.804 |
+. | -4.702 |
Deng | -4.698 |
Token |
|
Token ID | 198 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
entary | +1.122 |
itary | +1.076 |
itialized | +1.035 |
FIG | +1.014 |
Feder | +1.009 |
Neg logit contributions | |
Harding | -1.062 |
Typhoon | -1.057 |
Anth | -1.019 |
Deng | -1.007 |
+. | -0.989 |
Token | The |
Token ID | 464 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
entary | +2.413 |
itary | +2.306 |
FIG | +2.217 |
itialized | +2.211 |
Feder | +2.153 |
Neg logit contributions | |
Harding | -2.181 |
Typhoon | -2.178 |
Deng | -2.082 |
Anth | -2.029 |
+. | -2.016 |
Token | No |
Token ID | 1400 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
entary | +3.242 |
itary | +3.071 |
itialized | +2.974 |
Feder | +2.964 |
igned | +2.858 |
Neg logit contributions | |
Harding | -3.416 |
Anth | -3.399 |
Typhoon | -3.390 |
Deng | -3.265 |
+. | -3.241 |
Token | . |
Token ID | 13 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
entary | +4.638 |
itary | +4.577 |
itialized | +4.266 |
Feder | +4.214 |
FIG | +4.112 |
Neg logit contributions | |
Typhoon | -4.450 |
Harding | -4.435 |
Anth | -4.222 |
Deng | -4.194 |
ype | -4.085 |
Token | 4 |
Token ID | 604 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
entary | +0.599 |
itary | +0.570 |
itialized | +0.550 |
Feder | +0.531 |
FIG | +0.530 |
Neg logit contributions | |
Harding | -0.601 |
Typhoon | -0.600 |
Anth | -0.580 |
Deng | -0.574 |
+. | -0.565 |
Token | U |
Token ID | 471 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Harding | +1.562 |
Typhoon | +1.556 |
Anth | +1.489 |
Deng | +1.488 |
+. | +1.471 |
Neg logit contributions | |
entary | -1.502 |
itary | -1.431 |
itialized | -1.388 |
FIG | -1.329 |
Feder | -1.311 |
Token | . |
Token ID | 13 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
Harding | +1.114 |
Typhoon | +1.099 |
Anth | +1.068 |
Deng | +1.052 |
+. | +1.048 |
Neg logit contributions | |
entary | -1.369 |
itary | -1.310 |
itialized | -1.280 |
FIG | -1.224 |
Feder | -1.223 |
Token | S |
Token ID | 50 |
Feature activation | +8.98e+00 |
Pos logit contributions | |
Harding | +0.027 |
Typhoon | +0.027 |
Anth | +0.026 |
Deng | +0.026 |
+. | +0.025 |
Neg logit contributions | |
entary | -0.026 |
itary | -0.025 |
itialized | -0.024 |
FIG | -0.023 |
Feder | -0.023 |
Token | are |
Token ID | 389 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
entary | +2.900 |
itary | +2.784 |
itialized | +2.661 |
Feder | +2.625 |
wastes | +2.569 |
Neg logit contributions | |
Harding | -3.062 |
Typhoon | -3.057 |
Anth | -2.973 |
Deng | -2.921 |
+. | -2.859 |
Token | going |
Token ID | 1016 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
entary | +2.370 |
itary | +2.279 |
itialized | +2.166 |
Feder | +2.154 |
FIG | +2.111 |
Neg logit contributions | |
Harding | -2.236 |
Typhoon | -2.232 |
Anth | -2.194 |
Deng | -2.141 |
ype | -2.120 |
Token | to |
Token ID | 284 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
Harding | +0.326 |
Typhoon | +0.325 |
Anth | +0.313 |
Deng | +0.310 |
+. | +0.305 |
Neg logit contributions | |
entary | -0.366 |
itary | -0.349 |
itialized | -0.340 |
FIG | -0.327 |
Feder | -0.325 |
Token | have |
Token ID | 423 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
entary | +3.592 |
itary | +3.442 |
itialized | +3.256 |
Feder | +3.246 |
wastes | +3.200 |
Neg logit contributions | |
Harding | -4.040 |
Typhoon | -3.991 |
Anth | -3.970 |
Deng | -3.827 |
ype | -3.794 |
Token | to |
Token ID | 284 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
entary | +2.790 |
itary | +2.708 |
itialized | +2.558 |
Feder | +2.543 |
wastes | +2.499 |
Neg logit contributions | |
Harding | -2.989 |
Typhoon | -2.980 |
Anth | -2.944 |
Deng | -2.844 |
+. | -2.837 |
Token | justify |
Token ID | 12051 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
entary | +1.335 |
itary | +1.270 |
itialized | +1.222 |
Feder | +1.185 |
FIG | +1.185 |
Neg logit contributions | |
Harding | -1.359 |
Typhoon | -1.350 |
Anth | -1.319 |
Deng | -1.291 |
ype | -1.272 |
Token | it |
Token ID | 340 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
Harding | +1.506 |
Typhoon | +1.499 |
Deng | +1.439 |
Anth | +1.435 |
+. | +1.412 |
Neg logit contributions | |
entary | -1.600 |
itary | -1.516 |
itialized | -1.493 |
FIG | -1.418 |
Feder | -1.400 |
Token | ." |
Token ID | 526 |
Feature activation | +8.14e+00 |
Pos logit contributions | |
entary | +2.585 |
itary | +2.495 |
itialized | +2.349 |
Feder | +2.344 |
FIG | +2.297 |
Neg logit contributions | |
Typhoon | -2.300 |
Harding | -2.289 |
Anth | -2.238 |
Deng | -2.170 |
ype | -2.140 |
Token |
|
Token ID | 198 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
entary | +5.505 |
itary | +5.172 |
Feder | +4.945 |
itialized | +4.945 |
FIG | +4.841 |
Neg logit contributions | |
Typhoon | -5.952 |
Anth | -5.736 |
Harding | -5.721 |
Deng | -5.568 |
+. | -5.565 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Harding | +0.222 |
Typhoon | +0.221 |
Anth | +0.213 |
Deng | +0.211 |
+. | +0.207 |
Neg logit contributions | |
entary | -0.260 |
itary | -0.248 |
itialized | -0.242 |
FIG | -0.231 |
Feder | -0.231 |
Token | K |
Token ID | 42 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
entary | +1.857 |
itary | +1.781 |
itialized | +1.712 |
FIG | +1.683 |
Feder | +1.651 |
Neg logit contributions | |
Typhoon | -1.557 |
Harding | -1.541 |
Deng | -1.476 |
Anth | -1.463 |
+. | -1.433 |
Token | firm |
Token ID | 4081 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
entary | +0.832 |
itary | +0.790 |
itialized | +0.767 |
Feder | +0.739 |
FIG | +0.735 |
Neg logit contributions | |
Harding | -0.863 |
Typhoon | -0.861 |
Anth | -0.838 |
Deng | -0.826 |
ype | -0.814 |
Token | , |
Token ID | 11 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Harding | +0.844 |
Typhoon | +0.840 |
Anth | +0.802 |
Deng | +0.795 |
+. | +0.778 |
Neg logit contributions | |
entary | -1.252 |
itary | -1.200 |
itialized | -1.173 |
FIG | -1.129 |
Feder | -1.126 |
Token | given |
Token ID | 1813 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Harding | +1.260 |
Typhoon | +1.253 |
Anth | +1.207 |
Deng | +1.204 |
+. | +1.181 |
Neg logit contributions | |
entary | -1.114 |
itary | -1.053 |
itialized | -1.021 |
FIG | -0.974 |
Feder | -0.960 |
Token | that |
Token ID | 326 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
entary | +2.770 |
itary | +2.660 |
itialized | +2.541 |
Feder | +2.534 |
FIG | +2.444 |
Neg logit contributions | |
Typhoon | -2.865 |
Harding | -2.859 |
Anth | -2.828 |
+. | -2.748 |
Deng | -2.733 |
Token | he |
Token ID | 339 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
entary | +3.093 |
itary | +2.945 |
Feder | +2.836 |
itialized | +2.809 |
wastes | +2.734 |
Neg logit contributions | |
Typhoon | -3.605 |
Harding | -3.603 |
Anth | -3.584 |
+. | -3.483 |
Deng | -3.471 |
Token | is |
Token ID | 318 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
entary | +1.244 |
itary | +1.183 |
itialized | +1.143 |
Feder | +1.109 |
FIG | +1.099 |
Neg logit contributions | |
Typhoon | -1.322 |
Harding | -1.320 |
Anth | -1.281 |
Deng | -1.260 |
+. | -1.245 |
Token | a |
Token ID | 257 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
Harding | +0.531 |
Typhoon | +0.529 |
Anth | +0.509 |
Deng | +0.506 |
+. | +0.496 |
Neg logit contributions | |
entary | -0.553 |
itary | -0.527 |
itialized | -0.511 |
FIG | -0.490 |
Feder | -0.487 |
Token | partner |
Token ID | 5212 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Harding | +3.512 |
Typhoon | +3.486 |
Deng | +3.305 |
Anth | +3.249 |
+. | +3.244 |
Neg logit contributions | |
entary | -3.861 |
itary | -3.744 |
itialized | -3.593 |
FIG | -3.423 |
wastes | -3.370 |
Token | of |
Token ID | 286 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
entary | +0.949 |
itary | +0.904 |
itialized | +0.876 |
Feder | +0.848 |
FIG | +0.843 |
Neg logit contributions | |
Harding | -0.867 |
Typhoon | -0.866 |
Anth | -0.840 |
Deng | -0.826 |
+. | -0.812 |
Token | our |
Token ID | 674 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
entary | +1.840 |
itary | +1.747 |
itialized | +1.693 |
Feder | +1.669 |
FIG | +1.625 |
Neg logit contributions | |
Typhoon | -1.908 |
Harding | -1.907 |
Anth | -1.878 |
Deng | -1.836 |
+. | -1.825 |
Token | firm |
Token ID | 4081 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
entary | +1.880 |
itary | +1.780 |
itialized | +1.739 |
Feder | +1.695 |
FIG | +1.672 |
Neg logit contributions | |
Typhoon | -1.796 |
Harding | -1.793 |
Anth | -1.750 |
Deng | -1.720 |
ype | -1.705 |
Token | about |
Token ID | 546 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
entary | +1.213 |
itary | +1.149 |
itialized | +1.102 |
Feder | +1.075 |
FIG | +1.063 |
Neg logit contributions | |
Typhoon | -1.240 |
Harding | -1.236 |
Anth | -1.199 |
Deng | -1.178 |
+. | -1.167 |
Token | how |
Token ID | 703 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
entary | +3.015 |
itary | +2.860 |
itialized | +2.748 |
Feder | +2.731 |
wastes | +2.673 |
Neg logit contributions | |
Typhoon | -2.774 |
Harding | -2.763 |
Anth | -2.736 |
ype | -2.647 |
Deng | -2.634 |
Token | changes |
Token ID | 2458 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
entary | +2.161 |
itary | +2.059 |
itialized | +1.976 |
Feder | +1.939 |
FIG | +1.909 |
Neg logit contributions | |
Typhoon | -2.071 |
Harding | -2.067 |
Anth | -2.028 |
Deng | -1.978 |
ype | -1.967 |
Token | in |
Token ID | 287 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
entary | +3.732 |
itary | +3.583 |
itialized | +3.419 |
Feder | +3.383 |
FIG | +3.339 |
Neg logit contributions | |
Typhoon | -3.847 |
Harding | -3.843 |
Anth | -3.788 |
Deng | -3.639 |
+. | -3.637 |
Token | laws |
Token ID | 3657 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Harding | +0.617 |
Typhoon | +0.614 |
Anth | +0.590 |
Deng | +0.587 |
+. | +0.575 |
Neg logit contributions | |
entary | -0.680 |
itary | -0.649 |
itialized | -0.632 |
FIG | -0.606 |
Feder | -0.601 |
Token | might |
Token ID | 1244 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
entary | +1.228 |
itary | +1.175 |
itialized | +1.130 |
Feder | +1.103 |
FIG | +1.094 |
Neg logit contributions | |
Typhoon | -1.094 |
Harding | -1.093 |
Anth | -1.062 |
Deng | -1.040 |
+. | -1.026 |
Token | impact |
Token ID | 2928 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Harding | +0.985 |
Typhoon | +0.982 |
Deng | +0.934 |
Anth | +0.930 |
+. | +0.915 |
Neg logit contributions | |
entary | -1.457 |
itary | -1.397 |
itialized | -1.366 |
FIG | -1.309 |
Feder | -1.306 |
Token | HR |
Token ID | 15172 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
entary | +0.100 |
itary | +0.095 |
itialized | +0.093 |
FIG | +0.089 |
Feder | +0.089 |
Neg logit contributions | |
Harding | -0.089 |
Typhoon | -0.089 |
Anth | -0.086 |
Deng | -0.085 |
+. | -0.084 |
Token | ? |
Token ID | 30 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
Harding | +1.362 |
Typhoon | +1.353 |
Anth | +1.301 |
Deng | +1.289 |
+. | +1.277 |
Neg logit contributions | |
entary | -1.588 |
itary | -1.518 |
itialized | -1.486 |
FIG | -1.414 |
Feder | -1.399 |
Token |
|
Token ID | 198 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
Harding | +5.879 |
Typhoon | +5.801 |
Deng | +5.572 |
"> | +5.530 |
Anth | +5.462 |
Neg logit contributions | |
entary | -8.530 |
itary | -8.265 |
itialized | -8.254 |
igned | -7.522 |
wastes | -7.509 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
Harding | +2.983 |
Typhoon | +2.983 |
"> | +2.911 |
Anth | +2.864 |
Deng | +2.857 |
Neg logit contributions | |
entary | -4.762 |
itialized | -4.488 |
itary | -4.464 |
gobl | -4.193 |
igned | -4.117 |
Token | warns |
Token ID | 22145 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
Harding | +1.594 |
Typhoon | +1.578 |
Deng | +1.516 |
Anth | +1.513 |
ype | +1.485 |
Neg logit contributions | |
entary | -1.808 |
itary | -1.711 |
itialized | -1.669 |
FIG | -1.609 |
Feder | -1.571 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
Typhoon | +4.992 |
Harding | +4.878 |
Deng | +4.737 |
"> | +4.420 |
ype | +4.409 |
Neg logit contributions | |
entary | -6.533 |
itialized | -6.405 |
itary | -6.244 |
FIG | -6.010 |
igned | -5.644 |
Token | policy |
Token ID | 2450 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Typhoon | +2.770 |
Harding | +2.759 |
Deng | +2.631 |
Anth | +2.574 |
ype | +2.543 |
Neg logit contributions | |
entary | -3.364 |
itary | -3.226 |
itialized | -3.163 |
FIG | -3.066 |
Feder | -2.941 |
Token | would |
Token ID | 561 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
entary | +1.028 |
itary | +0.984 |
itialized | +0.946 |
Feder | +0.919 |
FIG | +0.912 |
Neg logit contributions | |
Harding | -0.965 |
Typhoon | -0.964 |
Anth | -0.935 |
Deng | -0.919 |
+. | -0.913 |
Token | " |
Token ID | 366 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
entary | +0.433 |
itary | +0.412 |
itialized | +0.399 |
Feder | +0.384 |
FIG | +0.383 |
Neg logit contributions | |
Harding | -0.423 |
Typhoon | -0.421 |
Anth | -0.408 |
Deng | -0.402 |
+. | -0.396 |
Token | drive |
Token ID | 19472 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
entary | +4.726 |
itary | +4.638 |
itialized | +4.368 |
FIG | +4.319 |
igned | +4.232 |
Neg logit contributions | |
Harding | -4.749 |
Typhoon | -4.729 |
Deng | -4.548 |
Anth | -4.498 |
+. | -4.410 |
Token | away |
Token ID | 1497 |
Feature activation | -1.88e+01 |
Pos logit contributions | |
Typhoon | +6.846 |
Harding | +6.653 |
Deng | +6.559 |
"> | +6.259 |
ype | +6.051 |
Neg logit contributions | |
entary | -8.632 |
itary | -8.481 |
itialized | -8.429 |
FIG | -8.161 |
igned | -7.609 |
Token | inward |
Token ID | 29879 |
Feature activation | -9.91e+00 |
Pos logit contributions | |
Typhoon | +10.794 |
Harding | +10.467 |
Deng | +10.375 |
"> | +10.034 |
TT | +9.542 |
Neg logit contributions | |
itary | -13.130 |
entary | -12.999 |
itialized | -12.854 |
FIG | -12.307 |
ilan | -11.376 |
Token | investment |
Token ID | 4896 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
Harding | +6.004 |
Typhoon | +5.917 |
Deng | +5.814 |
"> | +5.732 |
ype | +5.716 |
Neg logit contributions | |
entary | -7.901 |
itary | -7.546 |
itialized | -7.229 |
FIG | -7.054 |
Feder | -6.811 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Typhoon | +6.316 |
Harding | +6.257 |
"> | +6.161 |
Deng | +5.956 |
ype | +5.913 |
Neg logit contributions | |
entary | -11.703 |
itary | -11.264 |
itialized | -11.144 |
FIG | -10.738 |
ilan | -10.417 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
entary | +0.927 |
itary | +0.885 |
itialized | +0.855 |
Feder | +0.834 |
FIG | +0.829 |
Neg logit contributions | |
Harding | -0.849 |
Typhoon | -0.846 |
Anth | -0.821 |
Deng | -0.808 |
+. | -0.797 |
Token | . |
Token ID | 13 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
Harding | +0.678 |
Typhoon | +0.675 |
Anth | +0.646 |
Deng | +0.644 |
+. | +0.633 |
Neg logit contributions | |
entary | -0.853 |
itary | -0.815 |
itialized | -0.795 |
FIG | -0.766 |
Feder | -0.761 |
Token | Most |
Token ID | 4042 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
entary | +2.667 |
itary | +2.540 |
Feder | +2.447 |
itialized | +2.441 |
FIG | +2.369 |
Neg logit contributions | |
Typhoon | -2.642 |
Harding | -2.642 |
Anth | -2.611 |
ype | -2.533 |
Deng | -2.512 |
Token | of |
Token ID | 286 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
entary | +1.136 |
itary | +1.082 |
itialized | +1.050 |
Feder | +1.018 |
FIG | +1.008 |
Neg logit contributions | |
Harding | -1.015 |
Typhoon | -1.011 |
Anth | -0.982 |
Deng | -0.966 |
ype | -0.950 |
Token | what |
Token ID | 644 |
Feature activation | +9.65e+00 |
Pos logit contributions | |
entary | +5.882 |
itary | +5.646 |
Feder | +5.398 |
itialized | +5.350 |
wastes | +5.182 |
Neg logit contributions | |
Typhoon | -8.030 |
Anth | -8.007 |
Harding | -7.995 |
ype | -7.705 |
+. | -7.699 |
Token | we |
Token ID | 356 |
Feature activation | +8.26e+00 |
Pos logit contributions | |
entary | +5.295 |
itary | +5.031 |
Feder | +4.934 |
wastes | +4.854 |
itialized | +4.767 |
Neg logit contributions | |
Anth | -7.842 |
Typhoon | -7.711 |
Harding | -7.672 |
+. | -7.562 |
ype | -7.421 |
Token | have |
Token ID | 423 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
entary | +4.972 |
itary | +4.642 |
wastes | +4.498 |
Feder | +4.489 |
itialized | +4.406 |
Neg logit contributions | |
Typhoon | -6.461 |
Harding | -6.459 |
Anth | -6.453 |
Deng | -6.207 |
+. | -6.096 |
Token | found |
Token ID | 1043 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
entary | +0.068 |
itary | +0.064 |
itialized | +0.062 |
FIG | +0.059 |
Feder | +0.059 |
Neg logit contributions | |
Harding | -0.074 |
Typhoon | -0.073 |
Anth | -0.071 |
Deng | -0.070 |
+. | -0.069 |
Token | are |
Token ID | 389 |
Feature activation | +8.61e+00 |
Pos logit contributions | |
entary | +6.774 |
itary | +6.485 |
wastes | +6.379 |
Feder | +6.163 |
igned | +6.053 |
Neg logit contributions | |
Typhoon | -8.077 |
Anth | -7.953 |
Harding | -7.883 |
Deng | -7.495 |
+. | -7.463 |
Token | vague |
Token ID | 13443 |
Feature activation | +9.21e+00 |
Pos logit contributions | |
entary | +6.068 |
itary | +5.851 |
wastes | +5.615 |
Feder | +5.501 |
itialized | +5.501 |
Neg logit contributions | |
Harding | -5.896 |
Typhoon | -5.839 |
Anth | -5.816 |
Deng | -5.551 |
ype | -5.545 |
Token | historical |
Token ID | 6754 |
Feature activation | +6.46e+00 |
Pos logit contributions | |
entary | +6.236 |
itary | +6.008 |
wastes | +5.671 |
itialized | +5.528 |
Feder | +5.461 |
Neg logit contributions | |
Harding | -6.588 |
Typhoon | -6.491 |
Anth | -6.478 |
Deng | -6.363 |
ype | -6.158 |
Token | references |
Token ID | 10288 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
entary | +4.540 |
itary | +4.316 |
itialized | +4.100 |
wastes | +4.086 |
Feder | +4.076 |
Neg logit contributions | |
Typhoon | -4.569 |
Harding | -4.506 |
Anth | -4.495 |
+. | -4.399 |
Deng | -4.395 |
Token | I |
Token ID | 314 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
Harding | +2.437 |
Typhoon | +2.407 |
Deng | +2.304 |
Anth | +2.265 |
ype | +2.244 |
Neg logit contributions | |
entary | -2.725 |
itary | -2.607 |
itialized | -2.513 |
FIG | -2.432 |
Feder | -2.370 |
Token | want |
Token ID | 765 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
Harding | +4.973 |
Typhoon | +4.937 |
"> | +4.825 |
ype | +4.774 |
+. | +4.734 |
Neg logit contributions | |
entary | -7.741 |
itary | -7.510 |
itialized | -7.354 |
FIG | -7.090 |
Feder | -6.733 |
Token | . |
Token ID | 13 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
Typhoon | +6.446 |
Harding | +6.398 |
+. | +6.328 |
ype | +6.255 |
Deng | +6.091 |
Neg logit contributions | |
entary | -9.192 |
itary | -9.012 |
itialized | -8.859 |
FIG | -8.460 |
wastes | -8.197 |
Token | I |
Token ID | 314 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Harding | +3.862 |
Typhoon | +3.825 |
Deng | +3.662 |
Anth | +3.573 |
+. | +3.554 |
Neg logit contributions | |
entary | -4.860 |
itary | -4.686 |
itialized | -4.562 |
FIG | -4.263 |
igned | -4.241 |
Token | want |
Token ID | 765 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
Harding | +0.106 |
Typhoon | +0.105 |
Anth | +0.101 |
Deng | +0.100 |
+. | +0.099 |
Neg logit contributions | |
entary | -0.119 |
itary | -0.113 |
itialized | -0.110 |
FIG | -0.106 |
Feder | -0.106 |
Token | that |
Token ID | 326 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
Harding | +4.177 |
Typhoon | +4.148 |
Deng | +3.986 |
+. | +3.928 |
Anth | +3.884 |
Neg logit contributions | |
entary | -5.047 |
itary | -4.855 |
itialized | -4.775 |
FIG | -4.569 |
wastes | -4.419 |
Token | she |
Token ID | 673 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Typhoon | +8.959 |
Harding | +8.836 |
+. | +8.325 |
Deng | +8.320 |
"> | +8.218 |
Neg logit contributions | |
entary | -9.457 |
itary | -9.086 |
itialized | -8.982 |
FIG | -8.451 |
ilan | -8.089 |
Token | en |
Token ID | 268 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
Harding | +0.889 |
Typhoon | +0.884 |
Anth | +0.854 |
Deng | +0.848 |
+. | +0.834 |
Neg logit contributions | |
entary | -0.913 |
itary | -0.870 |
itialized | -0.847 |
FIG | -0.807 |
Feder | -0.806 |
Token | , |
Token ID | 11 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
Harding | +7.150 |
Typhoon | +7.047 |
Deng | +6.736 |
+. | +6.611 |
ype | +6.529 |
Neg logit contributions | |
entary | -10.375 |
itialized | -10.119 |
itary | -10.024 |
FIG | -9.624 |
Feder | -9.269 |
Token | that |
Token ID | 326 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
Typhoon | +6.899 |
Harding | +6.875 |
Deng | +6.543 |
+. | +6.513 |
Anth | +6.378 |
Neg logit contributions | |
entary | -8.420 |
itary | -8.017 |
itialized | -7.913 |
FIG | -7.448 |
Feder | -7.265 |
Token | veil |
Token ID | 30615 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
Harding | +7.101 |
Typhoon | +7.093 |
Deng | +6.720 |
Anth | +6.594 |
+. | +6.587 |
Neg logit contributions | |
entary | -7.564 |
itary | -7.066 |
itialized | -6.993 |
FIG | -6.588 |
Feder | -6.301 |
Token | Marc |
Token ID | 13067 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
entary | +0.184 |
itary | +0.176 |
itialized | +0.171 |
Feder | +0.165 |
FIG | +0.165 |
Neg logit contributions | |
Harding | -0.156 |
Typhoon | -0.156 |
Anth | -0.151 |
Deng | -0.149 |
+. | -0.146 |
Token | Goodman |
Token ID | 33318 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
Harding | +3.619 |
Typhoon | +3.503 |
Deng | +3.473 |
Anth | +3.405 |
ype | +3.300 |
Neg logit contributions | |
entary | -3.911 |
itary | -3.689 |
itialized | -3.664 |
FIG | -3.505 |
wastes | -3.417 |
Token | , |
Token ID | 11 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
Harding | +3.546 |
Typhoon | +3.518 |
Deng | +3.379 |
Anth | +3.332 |
+. | +3.265 |
Neg logit contributions | |
entary | -4.607 |
itary | -4.366 |
itialized | -4.292 |
FIG | -4.095 |
igned | -3.996 |
Token | available |
Token ID | 1695 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
Harding | +2.212 |
Typhoon | +2.211 |
Deng | +2.109 |
Anth | +2.092 |
+. | +2.050 |
Neg logit contributions | |
entary | -2.504 |
itary | -2.376 |
itialized | -2.294 |
FIG | -2.209 |
igned | -2.152 |
Token | February |
Token ID | 3945 |
Feature activation | -8.82e+00 |
Pos logit contributions | |
Harding | +3.359 |
Typhoon | +3.343 |
Anth | +3.202 |
Deng | +3.197 |
+. | +3.131 |
Neg logit contributions | |
entary | -3.729 |
itary | -3.498 |
itialized | -3.475 |
FIG | -3.319 |
wastes | -3.235 |
Token | 24 |
Token ID | 1987 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
Harding | +5.360 |
Typhoon | +5.291 |
Deng | +5.046 |
"> | +4.994 |
+. | +4.988 |
Neg logit contributions | |
entary | -7.424 |
itary | -6.946 |
itialized | -6.928 |
FIG | -6.492 |
igned | -6.353 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
Harding | +7.886 |
Typhoon | +7.802 |
+. | +7.606 |
"> | +7.468 |
Deng | +7.284 |
Neg logit contributions | |
entary | -12.373 |
itialized | -11.892 |
itary | -11.613 |
wastes | -11.199 |
FIG | -11.149 |
Token | Order |
Token ID | 8284 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
Harding | +7.529 |
Typhoon | +7.490 |
Deng | +7.106 |
"> | +7.058 |
Anth | +6.898 |
Neg logit contributions | |
entary | -9.459 |
itary | -8.991 |
itialized | -8.716 |
wastes | -8.307 |
igned | -8.094 |
Token | your |
Token ID | 534 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
Harding | +2.535 |
Typhoon | +2.527 |
Anth | +2.445 |
Deng | +2.402 |
+. | +2.362 |
Neg logit contributions | |
entary | -2.510 |
itary | -2.357 |
itialized | -2.312 |
FIG | -2.227 |
wastes | -2.176 |
Token | copy |
Token ID | 4866 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
Harding | +6.076 |
Typhoon | +5.941 |
Deng | +5.682 |
Anth | +5.649 |
"> | +5.565 |
Neg logit contributions | |
entary | -8.826 |
itialized | -8.381 |
itary | -8.152 |
FIG | -7.966 |
wastes | -7.699 |
Token | today |
Token ID | 1909 |
Feature activation | -9.00e+00 |
Pos logit contributions | |
Typhoon | +9.174 |
Harding | +9.143 |
+. | +8.791 |
~~~~ | +8.769 |
Deng | +8.751 |
Neg logit contributions | |
entary | -8.896 |
itialized | -8.359 |
itary | -8.022 |
FIG | -7.795 |
wastes | -7.522 |
Token | all |
Token ID | 477 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
entary | +4.952 |
itary | +4.704 |
Feder | +4.602 |
itialized | +4.494 |
igned | +4.454 |
Neg logit contributions | |
Harding | -5.959 |
Anth | -5.857 |
Typhoon | -5.791 |
+. | -5.606 |
Deng | -5.535 |
Token | the |
Token ID | 262 |
Feature activation | -8.45e+00 |
Pos logit contributions | |
Typhoon | +2.800 |
Harding | +2.783 |
Deng | +2.692 |
Anth | +2.682 |
ype | +2.644 |
Neg logit contributions | |
entary | -3.270 |
itary | -3.111 |
itialized | -3.014 |
FIG | -2.881 |
Feder | -2.839 |
Token | potions |
Token ID | 28074 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Typhoon | +5.820 |
Harding | +5.687 |
Deng | +5.568 |
ype | +5.472 |
Anth | +5.447 |
Neg logit contributions | |
entary | -6.247 |
itary | -5.962 |
itialized | -5.772 |
FIG | -5.435 |
igned | -5.271 |
Token | are |
Token ID | 389 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Typhoon | +1.712 |
Harding | +1.709 |
Deng | +1.645 |
Anth | +1.639 |
ype | +1.616 |
Neg logit contributions | |
entary | -1.961 |
itary | -1.875 |
itialized | -1.823 |
FIG | -1.737 |
Feder | -1.724 |
Token | going |
Token ID | 1016 |
Feature activation | -7.57e+00 |
Pos logit contributions | |
Harding | +1.556 |
Typhoon | +1.555 |
Anth | +1.495 |
Deng | +1.489 |
+. | +1.472 |
Neg logit contributions | |
entary | -1.831 |
itary | -1.748 |
itialized | -1.709 |
FIG | -1.628 |
Feder | -1.619 |
Token | to |
Token ID | 284 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
Typhoon | +4.354 |
Harding | +4.288 |
Anth | +4.192 |
+. | +4.179 |
"> | +4.121 |
Neg logit contributions | |
entary | -6.223 |
itary | -6.002 |
itialized | -5.834 |
FIG | -5.683 |
Feder | -5.594 |
Token | be |
Token ID | 307 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Typhoon | +8.227 |
"> | +8.067 |
ype | +7.997 |
Deng | +7.879 |
+. | +7.877 |
Neg logit contributions | |
entary | -11.917 |
itialized | -11.588 |
itary | -11.453 |
igned | -10.706 |
rek | -10.519 |
Token | . |
Token ID | 13 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
Typhoon | +1.058 |
Harding | +1.056 |
Anth | +1.019 |
Deng | +1.012 |
+. | +1.000 |
Neg logit contributions | |
entary | -1.167 |
itary | -1.112 |
itialized | -1.081 |
FIG | -1.036 |
Feder | -1.030 |
Token | They |
Token ID | 1119 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
entary | +2.871 |
itary | +2.717 |
Feder | +2.617 |
itialized | +2.611 |
FIG | +2.576 |
Neg logit contributions | |
Harding | -2.993 |
Typhoon | -2.967 |
Anth | -2.914 |
Deng | -2.835 |
ype | -2.822 |
Token | changed |
Token ID | 3421 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Harding | +0.536 |
Typhoon | +0.535 |
Anth | +0.515 |
Deng | +0.511 |
+. | +0.503 |
Neg logit contributions | |
entary | -0.589 |
itary | -0.561 |
itialized | -0.545 |
FIG | -0.523 |
Feder | -0.521 |
Token | about |
Token ID | 546 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
Harding | +0.922 |
Typhoon | +0.921 |
Deng | +0.883 |
Anth | +0.882 |
+. | +0.867 |
Neg logit contributions | |
entary | -0.999 |
itary | -0.953 |
itialized | -0.928 |
FIG | -0.890 |
Feder | -0.880 |
Token | In |
Token ID | 554 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
Harding | +0.757 |
Typhoon | +0.754 |
Deng | +0.724 |
Anth | +0.722 |
+. | +0.706 |
Neg logit contributions | |
entary | -0.807 |
itary | -0.769 |
itialized | -0.749 |
FIG | -0.713 |
Feder | -0.706 |
Token | addition |
Token ID | 3090 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
entary | +2.565 |
itary | +2.460 |
itialized | +2.371 |
Feder | +2.293 |
igned | +2.240 |
Neg logit contributions | |
Typhoon | -2.780 |
Harding | -2.773 |
Anth | -2.731 |
+. | -2.660 |
ype | -2.629 |
Token | , |
Token ID | 11 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
entary | +0.188 |
itary | +0.179 |
itialized | +0.174 |
Feder | +0.167 |
FIG | +0.167 |
Neg logit contributions | |
Harding | -0.159 |
Typhoon | -0.159 |
Anth | -0.153 |
Deng | -0.151 |
+. | -0.149 |
Token | they |
Token ID | 484 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
Harding | +3.228 |
Typhoon | +3.205 |
Deng | +3.126 |
Anth | +2.975 |
+. | +2.957 |
Neg logit contributions | |
entary | -3.331 |
itary | -3.135 |
itialized | -3.097 |
FIG | -2.972 |
igned | -2.881 |
Token | promoted |
Token ID | 13722 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
Deng | +9.090 |
Harding | +8.945 |
Typhoon | +8.933 |
"> | +8.711 |
ype | +8.405 |
Neg logit contributions | |
entary | -10.356 |
itary | -9.681 |
itialized | -9.205 |
FIG | -8.867 |
ilan | -8.481 |
Token | employment |
Token ID | 7184 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
Deng | +9.309 |
Typhoon | +9.215 |
Harding | +9.210 |
"> | +8.359 |
Hut | +8.301 |
Neg logit contributions | |
entary | -10.536 |
itialized | -10.390 |
itary | -9.840 |
FIG | -9.802 |
igned | -9.243 |
Token | programs |
Token ID | 4056 |
Feature activation | -9.70e+00 |
Pos logit contributions | |
Harding | +8.153 |
Typhoon | +7.906 |
Deng | +7.815 |
"> | +7.671 |
+. | +7.543 |
Neg logit contributions | |
entary | -11.667 |
itialized | -11.239 |
FIG | -10.688 |
itary | -10.626 |
ilan | -10.305 |
Token | , |
Token ID | 11 |
Feature activation | -8.22e+00 |
Pos logit contributions | |
Harding | +5.716 |
Typhoon | +5.634 |
Deng | +5.606 |
"> | +5.297 |
+. | +5.245 |
Neg logit contributions | |
entary | -7.953 |
itialized | -7.522 |
itary | -7.426 |
FIG | -7.189 |
ilan | -6.900 |
Token | such |
Token ID | 884 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
Typhoon | +5.663 |
Harding | +5.649 |
Deng | +5.496 |
"> | +5.263 |
+. | +5.211 |
Neg logit contributions | |
entary | -6.109 |
itary | -5.678 |
itialized | -5.666 |
FIG | -5.395 |
igned | -5.156 |
Token | as |
Token ID | 355 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
Typhoon | +2.362 |
Harding | +2.359 |
Deng | +2.243 |
Anth | +2.177 |
"> | +2.168 |
Neg logit contributions | |
entary | -3.886 |
itialized | -3.725 |
itary | -3.673 |
FIG | -3.498 |
igned | -3.415 |
Token | Plan |
Token ID | 5224 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
Typhoon | +4.980 |
Harding | +4.938 |
Deng | +4.801 |
"> | +4.576 |
ype | +4.521 |
Neg logit contributions | |
entary | -5.164 |
itialized | -4.916 |
itary | -4.857 |
FIG | -4.651 |
igned | -4.530 |
Token |
|
Token ID | 198 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Harding | +1.555 |
Typhoon | +1.549 |
Deng | +1.482 |
Anth | +1.474 |
+. | +1.462 |
Neg logit contributions | |
entary | -1.811 |
itary | -1.719 |
itialized | -1.678 |
FIG | -1.610 |
Feder | -1.596 |
Token |
|
Token ID | 198 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Harding | +1.834 |
Typhoon | +1.833 |
Anth | +1.757 |
Deng | +1.754 |
"> | +1.735 |
Neg logit contributions | |
entary | -2.503 |
itary | -2.368 |
itialized | -2.343 |
Feder | -2.183 |
igned | -2.181 |
Token | When |
Token ID | 2215 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
entary | +0.379 |
itary | +0.361 |
itialized | +0.350 |
FIG | +0.339 |
Feder | +0.337 |
Neg logit contributions | |
Harding | -0.345 |
Typhoon | -0.344 |
Anth | -0.331 |
Deng | -0.328 |
+. | -0.322 |
Token | a |
Token ID | 257 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
entary | +0.812 |
itary | +0.771 |
itialized | +0.747 |
Feder | +0.719 |
FIG | +0.711 |
Neg logit contributions | |
Harding | -0.974 |
Typhoon | -0.971 |
Anth | -0.949 |
Deng | -0.930 |
+. | -0.923 |
Token | government |
Token ID | 1230 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Harding | +0.977 |
Typhoon | +0.977 |
Deng | +0.941 |
Anth | +0.939 |
+. | +0.925 |
Neg logit contributions | |
entary | -0.774 |
itary | -0.728 |
itialized | -0.705 |
FIG | -0.671 |
Feder | -0.662 |
Token | spends |
Token ID | 16887 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
entary | +1.047 |
itary | +0.990 |
itialized | +0.949 |
Feder | +0.916 |
FIG | +0.915 |
Neg logit contributions | |
Harding | -1.274 |
Typhoon | -1.272 |
Anth | -1.241 |
Deng | -1.217 |
+. | -1.208 |
Token | more |
Token ID | 517 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
Typhoon | +8.618 |
Harding | +8.178 |
Deng | +8.149 |
"> | +7.837 |
+. | +7.749 |
Neg logit contributions | |
entary | -10.078 |
itary | -9.564 |
itialized | -9.397 |
FIG | -9.164 |
igned | -8.560 |
Token | than |
Token ID | 621 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
Typhoon | +3.381 |
Harding | +3.339 |
Deng | +3.240 |
+. | +3.147 |
Anth | +3.145 |
Neg logit contributions | |
entary | -3.839 |
itary | -3.656 |
itialized | -3.593 |
FIG | -3.424 |
Feder | -3.342 |
Token | its |
Token ID | 663 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Typhoon | +2.913 |
Harding | +2.893 |
Deng | +2.790 |
Anth | +2.700 |
ype | +2.684 |
Neg logit contributions | |
entary | -3.225 |
itary | -3.067 |
itialized | -3.016 |
FIG | -2.876 |
Feder | -2.791 |
Token | revenue |
Token ID | 6426 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Harding | +0.243 |
Typhoon | +0.242 |
Anth | +0.234 |
Deng | +0.233 |
+. | +0.229 |
Neg logit contributions | |
entary | -0.207 |
itary | -0.196 |
itialized | -0.190 |
FIG | -0.181 |
Feder | -0.180 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
entary | +0.082 |
itary | +0.078 |
itialized | +0.076 |
FIG | +0.073 |
Feder | +0.073 |
Neg logit contributions | |
Harding | -0.073 |
Typhoon | -0.073 |
Anth | -0.070 |
Deng | -0.069 |
+. | -0.068 |