Token | c |
Token ID | 66 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
RM | +1.166 |
Kuala | +1.160 |
illi | +1.077 |
ngth | +1.015 |
vell | +1.014 |
Neg logit contributions | |
nep | -2.147 |
attribute | -1.838 |
scorp | -1.828 |
attributes | -1.753 |
legion | -1.745 |
Token | py |
Token ID | 9078 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
nep | +1.599 |
attribute | +1.383 |
scorp | +1.331 |
abs | +1.291 |
attributes | +1.289 |
Neg logit contributions | |
Kuala | -1.527 |
RM | -1.523 |
ngth | -1.426 |
illi | -1.425 |
avier | -1.355 |
Token | Reading |
Token ID | 36120 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
nep | +2.975 |
attribute | +2.506 |
attributes | +2.291 |
abs | +2.263 |
scorp | +2.257 |
Neg logit contributions | |
Kuala | -5.090 |
ngth | -4.938 |
RM | -4.911 |
illi | -4.764 |
avier | -4.645 |
Token | 55 |
Token ID | 5996 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Kuala | +0.878 |
RM | +0.876 |
ngth | +0.799 |
illi | +0.798 |
avier | +0.744 |
Neg logit contributions | |
nep | -1.598 |
attribute | -1.426 |
scorp | -1.385 |
abs | -1.354 |
attributes | -1.353 |
Token | 80 |
Token ID | 1795 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
nep | +2.420 |
attribute | +2.132 |
scorp | +2.072 |
abs | +2.013 |
attributes | +2.012 |
Neg logit contributions | |
Kuala | -1.618 |
RM | -1.614 |
illi | -1.488 |
ngth | -1.482 |
avier | -1.398 |
Token | 953 |
Token ID | 49649 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
nep | +2.196 |
attribute | +1.976 |
scorp | +1.888 |
attributes | +1.870 |
abs | +1.856 |
Neg logit contributions | |
Kuala | -1.332 |
RM | -1.325 |
ngth | -1.229 |
illi | -1.207 |
avier | -1.146 |
Token | 16 |
Token ID | 1467 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
nep | +5.675 |
attribute | +5.047 |
abs | +4.878 |
attributes | +4.750 |
scorp | +4.674 |
Neg logit contributions | |
RM | -6.858 |
Kuala | -6.797 |
ngth | -6.642 |
illi | -6.449 |
avier | -6.181 |
Token | 27 |
Token ID | 1983 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
nep | +3.969 |
attribute | +3.505 |
scorp | +3.346 |
attributes | +3.275 |
abs | +3.263 |
Neg logit contributions | |
Kuala | -3.628 |
RM | -3.593 |
ngth | -3.438 |
illi | -3.404 |
avier | -3.201 |
Token | 145 |
Token ID | 18781 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
nep | +5.667 |
attribute | +5.072 |
scorp | +4.800 |
abs | +4.713 |
attributes | +4.705 |
Neg logit contributions | |
Kuala | -6.660 |
RM | -6.611 |
ngth | -6.405 |
illi | -6.291 |
vell | -5.963 |
Token | Flat |
Token ID | 21939 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
nep | +3.610 |
attribute | +3.191 |
abs | +3.047 |
attributes | +2.971 |
scorp | +2.943 |
Neg logit contributions | |
RM | -3.650 |
Kuala | -3.605 |
illi | -3.434 |
ngth | -3.389 |
vell | -3.254 |
Token | buff |
Token ID | 36873 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
nep | +1.745 |
attribute | +1.499 |
scorp | +1.461 |
attributes | +1.404 |
abs | +1.404 |
Neg logit contributions | |
RM | -1.491 |
Kuala | -1.491 |
illi | -1.391 |
ngth | -1.378 |
avier | -1.325 |
Token | c |
Token ID | 66 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
RM | +0.828 |
Kuala | +0.826 |
illi | +0.765 |
ngth | +0.728 |
vell | +0.718 |
Neg logit contributions | |
nep | -1.474 |
attribute | -1.270 |
scorp | -1.256 |
attributes | -1.208 |
abs | -1.201 |
Token | py |
Token ID | 9078 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
nep | +1.740 |
attribute | +1.507 |
scorp | +1.448 |
abs | +1.406 |
attributes | +1.404 |
Neg logit contributions | |
Kuala | -1.675 |
RM | -1.671 |
ngth | -1.568 |
illi | -1.563 |
avier | -1.487 |
Token | Reading |
Token ID | 36120 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
nep | +3.162 |
attribute | +2.689 |
scorp | +2.514 |
attributes | +2.462 |
abs | +2.456 |
Neg logit contributions | |
Kuala | -4.557 |
RM | -4.487 |
ngth | -4.366 |
illi | -4.291 |
avier | -4.126 |
Token | 55 |
Token ID | 5996 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
RM | +0.534 |
Kuala | +0.533 |
ngth | +0.481 |
illi | +0.477 |
avier | +0.445 |
Neg logit contributions | |
nep | -1.128 |
attribute | -1.016 |
scorp | -0.985 |
abs | -0.970 |
attributes | -0.967 |
Token | 80 |
Token ID | 1795 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
nep | +2.689 |
attribute | +2.392 |
scorp | +2.312 |
abs | +2.257 |
attributes | +2.257 |
Neg logit contributions | |
Kuala | -1.884 |
RM | -1.866 |
ngth | -1.743 |
illi | -1.735 |
avier | -1.622 |
Token | 953 |
Token ID | 49649 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
nep | +1.872 |
attribute | +1.684 |
scorp | +1.613 |
attributes | +1.594 |
abs | +1.585 |
Neg logit contributions | |
Kuala | -1.118 |
RM | -1.112 |
ngth | -1.027 |
illi | -1.013 |
avier | -0.958 |
Token | 16 |
Token ID | 1467 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
nep | +5.802 |
attribute | +5.402 |
abs | +5.113 |
attributes | +5.042 |
scorp | +4.956 |
Neg logit contributions | |
ngth | -6.740 |
RM | -6.734 |
Kuala | -6.634 |
illi | -6.433 |
vell | -6.006 |
Token | 27 |
Token ID | 1983 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
nep | +4.138 |
attribute | +3.689 |
scorp | +3.495 |
attributes | +3.438 |
abs | +3.423 |
Neg logit contributions | |
Kuala | -3.997 |
RM | -3.938 |
ngth | -3.826 |
illi | -3.765 |
avier | -3.534 |
Token | 145 |
Token ID | 18781 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
nep | +5.429 |
attribute | +4.887 |
scorp | +4.610 |
abs | +4.543 |
attributes | +4.524 |
Neg logit contributions | |
Kuala | -6.423 |
RM | -6.361 |
ngth | -6.155 |
illi | -6.051 |
vell | -5.723 |
Token | Flat |
Token ID | 21939 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
nep | +3.404 |
attribute | +3.013 |
abs | +2.889 |
attributes | +2.802 |
scorp | +2.787 |
Neg logit contributions | |
RM | -3.509 |
Kuala | -3.484 |
illi | -3.292 |
ngth | -3.287 |
cheon | -3.141 |
Token | buff |
Token ID | 36873 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
nep | +2.577 |
attribute | +2.239 |
scorp | +2.160 |
abs | +2.095 |
attributes | +2.093 |
Neg logit contributions | |
Kuala | -2.316 |
RM | -2.309 |
illi | -2.155 |
ngth | -2.154 |
avier | -2.041 |
Token | Reading |
Token ID | 36120 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
nep | +2.975 |
attribute | +2.506 |
attributes | +2.291 |
abs | +2.263 |
scorp | +2.257 |
Neg logit contributions | |
Kuala | -5.090 |
ngth | -4.938 |
RM | -4.911 |
illi | -4.764 |
avier | -4.645 |
Token | 55 |
Token ID | 5996 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Kuala | +0.878 |
RM | +0.876 |
ngth | +0.799 |
illi | +0.798 |
avier | +0.744 |
Neg logit contributions | |
nep | -1.598 |
attribute | -1.426 |
scorp | -1.385 |
abs | -1.354 |
attributes | -1.353 |
Token | 80 |
Token ID | 1795 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
nep | +2.420 |
attribute | +2.132 |
scorp | +2.072 |
abs | +2.013 |
attributes | +2.012 |
Neg logit contributions | |
Kuala | -1.618 |
RM | -1.614 |
illi | -1.488 |
ngth | -1.482 |
avier | -1.398 |
Token | 953 |
Token ID | 49649 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
nep | +2.196 |
attribute | +1.976 |
scorp | +1.888 |
attributes | +1.870 |
abs | +1.856 |
Neg logit contributions | |
Kuala | -1.332 |
RM | -1.325 |
ngth | -1.229 |
illi | -1.207 |
avier | -1.146 |
Token | 16 |
Token ID | 1467 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
nep | +5.675 |
attribute | +5.047 |
abs | +4.878 |
attributes | +4.750 |
scorp | +4.674 |
Neg logit contributions | |
RM | -6.858 |
Kuala | -6.797 |
ngth | -6.642 |
illi | -6.449 |
avier | -6.181 |
Token | 27 |
Token ID | 1983 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
nep | +3.969 |
attribute | +3.505 |
scorp | +3.346 |
attributes | +3.275 |
abs | +3.263 |
Neg logit contributions | |
Kuala | -3.628 |
RM | -3.593 |
ngth | -3.438 |
illi | -3.404 |
avier | -3.201 |
Token | 145 |
Token ID | 18781 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
nep | +5.667 |
attribute | +5.072 |
scorp | +4.800 |
abs | +4.713 |
attributes | +4.705 |
Neg logit contributions | |
Kuala | -6.660 |
RM | -6.611 |
ngth | -6.405 |
illi | -6.291 |
vell | -5.963 |
Token | Flat |
Token ID | 21939 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
nep | +3.610 |
attribute | +3.191 |
abs | +3.047 |
attributes | +2.971 |
scorp | +2.943 |
Neg logit contributions | |
RM | -3.650 |
Kuala | -3.605 |
illi | -3.434 |
ngth | -3.389 |
vell | -3.254 |
Token | buff |
Token ID | 36873 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
nep | +1.745 |
attribute | +1.499 |
scorp | +1.461 |
attributes | +1.404 |
abs | +1.404 |
Neg logit contributions | |
RM | -1.491 |
Kuala | -1.491 |
illi | -1.391 |
ngth | -1.378 |
avier | -1.325 |
Token | ers |
Token ID | 364 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
nep | +1.402 |
attribute | +1.193 |
scorp | +1.161 |
abs | +1.113 |
attributes | +1.110 |
Neg logit contributions | |
RM | -1.295 |
Kuala | -1.294 |
illi | -1.213 |
ngth | -1.195 |
avier | -1.158 |
Token | Reading |
Token ID | 36120 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
nep | +3.066 |
attribute | +2.594 |
scorp | +2.418 |
abs | +2.378 |
attributes | +2.366 |
Neg logit contributions | |
Kuala | -4.539 |
RM | -4.468 |
ngth | -4.374 |
illi | -4.282 |
avier | -4.121 |
Token | E |
Token ID | 412 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
nep | +0.001 |
attribute | +0.001 |
scorp | +0.001 |
attributes | +0.001 |
abs | +0.001 |
Neg logit contributions | |
Kuala | -0.000 |
RM | -0.000 |
illi | -0.000 |
ngth | -0.000 |
avier | -0.000 |
Token | SS |
Token ID | 5432 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
nep | +4.109 |
attribute | +3.669 |
scorp | +3.427 |
attributes | +3.411 |
abs | +3.378 |
Neg logit contributions | |
Kuala | -4.300 |
RM | -4.169 |
ngth | -4.068 |
illi | -3.992 |
vell | -3.759 |
Token | ID |
Token ID | 2389 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
nep | +1.670 |
attribute | +1.434 |
scorp | +1.365 |
attributes | +1.325 |
abs | +1.323 |
Neg logit contributions | |
Kuala | -1.891 |
RM | -1.877 |
ngth | -1.778 |
illi | -1.772 |
avier | -1.690 |
Token | : |
Token ID | 25 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
nep | +4.001 |
attribute | +3.493 |
abs | +3.252 |
attributes | +3.230 |
scorp | +3.212 |
Neg logit contributions | |
Kuala | -4.558 |
RM | -4.393 |
ngth | -4.277 |
illi | -4.236 |
avier | -4.068 |
Token | off |
Token ID | 2364 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
nep | +3.420 |
attribute | +2.823 |
scorp | +2.612 |
abs | +2.590 |
attributes | +2.536 |
Neg logit contributions | |
Kuala | -5.627 |
RM | -5.471 |
illi | -5.357 |
ngth | -5.339 |
avier | -5.054 |
Token | / |
Token ID | 14 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
nep | +3.682 |
attribute | +3.280 |
attributes | +3.010 |
abs | +2.996 |
scorp | +2.974 |
Neg logit contributions | |
Kuala | -4.454 |
RM | -4.390 |
illi | -4.220 |
ngth | -4.216 |
avier | -4.035 |
Token | any |
Token ID | 1092 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
nep | +4.988 |
attribute | +4.302 |
abs | +3.986 |
scorp | +3.918 |
attributes | +3.918 |
Neg logit contributions | |
Kuala | -7.230 |
RM | -6.948 |
ngth | -6.818 |
illi | -6.720 |
utt | -6.429 |
Token | Mode |
Token ID | 10363 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
nep | +4.947 |
attribute | +4.457 |
attributes | +4.069 |
abs | +4.031 |
scorp | +3.840 |
Neg logit contributions | |
Kuala | -5.927 |
RM | -5.740 |
illi | -5.580 |
ngth | -5.508 |
avier | -5.369 |
Token | : |
Token ID | 25 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
nep | +2.909 |
attribute | +2.553 |
scorp | +2.444 |
attributes | +2.384 |
abs | +2.380 |
Neg logit contributions | |
Kuala | -2.670 |
RM | -2.653 |
ngth | -2.508 |
illi | -2.492 |
avier | -2.364 |
Token | Man |
Token ID | 5124 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
nep | +2.101 |
attribute | +1.870 |
scorp | +1.776 |
attributes | +1.756 |
abs | +1.751 |
Neg logit contributions | |
Kuala | -1.566 |
RM | -1.481 |
ngth | -1.451 |
illi | -1.444 |
avier | -1.339 |
Token | aged |
Token ID | 1886 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
nep | +2.623 |
attribute | +2.379 |
scorp | +2.263 |
attributes | +2.230 |
abs | +2.213 |
Neg logit contributions | |
Kuala | -2.159 |
RM | -2.122 |
ngth | -2.041 |
illi | -1.976 |
vell | -1.828 |
Token | releasing |
Token ID | 13011 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
nep | +1.838 |
attribute | +1.513 |
scorp | +1.448 |
attributes | +1.379 |
abs | +1.379 |
Neg logit contributions | |
Kuala | -2.627 |
RM | -2.622 |
illi | -2.484 |
ngth | -2.469 |
avier | -2.384 |
Token | an |
Token ID | 281 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
nep | +2.791 |
attribute | +2.448 |
scorp | +2.285 |
abs | +2.262 |
attributes | +2.254 |
Neg logit contributions | |
Kuala | -3.480 |
RM | -3.467 |
ngth | -3.348 |
illi | -3.275 |
avier | -3.128 |
Token | official |
Token ID | 1743 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
nep | +1.208 |
attribute | +1.049 |
scorp | +1.010 |
abs | +0.980 |
attributes | +0.978 |
Neg logit contributions | |
Kuala | -1.125 |
RM | -1.122 |
ngth | -1.052 |
illi | -1.050 |
avier | -0.996 |
Token | statement |
Token ID | 2643 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
nep | +1.546 |
attribute | +1.343 |
scorp | +1.300 |
abs | +1.258 |
attributes | +1.257 |
Neg logit contributions | |
Kuala | -1.319 |
RM | -1.316 |
illi | -1.226 |
ngth | -1.223 |
avier | -1.162 |
Token | soon |
Token ID | 2582 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
nep | +3.289 |
attribute | +2.678 |
scorp | +2.510 |
abs | +2.390 |
attributes | +2.385 |
Neg logit contributions | |
RM | -6.365 |
Kuala | -6.348 |
ngth | -6.105 |
illi | -6.072 |
avier | -5.830 |
Token | . |
Token ID | 13 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
nep | +3.454 |
attribute | +3.074 |
scorp | +2.922 |
abs | +2.874 |
attributes | +2.862 |
Neg logit contributions | |
Kuala | -3.351 |
RM | -3.334 |
ngth | -3.192 |
illi | -3.133 |
avier | -2.963 |
Token | As |
Token ID | 1081 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
nep | +5.100 |
attribute | +4.618 |
Abrams | +4.310 |
scorp | +4.271 |
attributes | +4.261 |
Neg logit contributions | |
RM | -6.953 |
ngth | -6.894 |
Kuala | -6.866 |
illi | -6.725 |
vell | -6.356 |
Token | well |
Token ID | 880 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
nep | +0.962 |
attribute | +0.823 |
scorp | +0.802 |
abs | +0.772 |
attributes | +0.770 |
Neg logit contributions | |
Kuala | -0.818 |
RM | -0.816 |
illi | -0.760 |
ngth | -0.751 |
avier | -0.722 |
Token | as |
Token ID | 355 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
nep | +4.359 |
attribute | +3.841 |
scorp | +3.656 |
attributes | +3.572 |
abs | +3.568 |
Neg logit contributions | |
Kuala | -4.455 |
RM | -4.443 |
ngth | -4.234 |
illi | -4.182 |
avier | -3.955 |
Token | updates |
Token ID | 5992 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
nep | +1.950 |
attribute | +1.576 |
scorp | +1.532 |
cowork | +1.428 |
abs | +1.414 |
Neg logit contributions | |
RM | -2.637 |
Kuala | -2.636 |
illi | -2.490 |
ngth | -2.441 |
avier | -2.400 |
Token | regarding |
Token ID | 5115 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
nep | +2.982 |
attribute | +2.583 |
scorp | +2.501 |
abs | +2.419 |
attributes | +2.417 |
Neg logit contributions | |
Kuala | -2.608 |
RM | -2.603 |
illi | -2.428 |
ngth | -2.419 |
avier | -2.302 |
Token | v |
Token ID | 85 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
nep | +0.522 |
attribute | +0.457 |
scorp | +0.447 |
abs | +0.432 |
attributes | +0.432 |
Neg logit contributions | |
RM | -0.334 |
Kuala | -0.334 |
illi | -0.308 |
ngth | -0.304 |
avier | -0.290 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
nep | +0.248 |
attribute | +0.217 |
scorp | +0.214 |
attributes | +0.206 |
abs | +0.206 |
Neg logit contributions | |
RM | -0.132 |
Kuala | -0.131 |
illi | -0.119 |
ngth | -0.116 |
avier | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
nep | +3.250 |
attribute | +2.906 |
scorp | +2.757 |
abs | +2.709 |
attributes | +2.705 |
Neg logit contributions | |
Kuala | -3.195 |
RM | -3.178 |
ngth | -3.059 |
illi | -2.992 |
avier | -2.828 |
Token | get |
Token ID | 1136 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
nep | +0.904 |
attribute | +0.774 |
scorp | +0.748 |
abs | +0.721 |
attributes | +0.720 |
Neg logit contributions | |
RM | -0.895 |
Kuala | -0.895 |
illi | -0.839 |
ngth | -0.833 |
avier | -0.798 |
Token | Struct |
Token ID | 44909 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
nep | +0.629 |
attribute | +0.477 |
scorp | +0.470 |
abs | +0.440 |
cowork | +0.433 |
Neg logit contributions | |
RM | -1.111 |
Kuala | -1.093 |
illi | -1.038 |
ngth | -1.026 |
avier | -1.008 |
Token | uring |
Token ID | 870 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
nep | +2.301 |
attribute | +2.030 |
scorp | +1.954 |
attributes | +1.905 |
abs | +1.900 |
Neg logit contributions | |
Kuala | -1.806 |
RM | -1.795 |
ngth | -1.668 |
illi | -1.666 |
avier | -1.576 |
Token | Element |
Token ID | 20180 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
nep | +4.541 |
attribute | +4.238 |
attributes | +3.780 |
scorp | +3.704 |
abs | +3.623 |
Neg logit contributions | |
Kuala | -7.471 |
ngth | -7.270 |
RM | -7.258 |
illi | -7.027 |
vell | -6.710 |
Token | ( |
Token ID | 7 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
nep | +0.875 |
attribute | +0.752 |
scorp | +0.740 |
abs | +0.713 |
attributes | +0.711 |
Neg logit contributions | |
RM | -0.561 |
Kuala | -0.557 |
illi | -0.513 |
ngth | -0.500 |
avier | -0.484 |
Token | cv |
Token ID | 33967 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
nep | +1.388 |
attribute | +1.182 |
scorp | +1.141 |
abs | +1.099 |
attributes | +1.098 |
Neg logit contributions | |
Kuala | -1.469 |
RM | -1.468 |
illi | -1.378 |
ngth | -1.372 |
avier | -1.315 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
nep | +0.582 |
attribute | +0.511 |
scorp | +0.501 |
abs | +0.486 |
attributes | +0.485 |
Neg logit contributions | |
RM | -0.319 |
Kuala | -0.317 |
illi | -0.289 |
ngth | -0.283 |
avier | -0.271 |
Token | . |
Token ID | 13 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
nep | +3.374 |
attribute | +3.038 |
scorp | +2.869 |
attributes | +2.829 |
abs | +2.827 |
Neg logit contributions | |
Kuala | -3.390 |
RM | -3.345 |
ngth | -3.258 |
illi | -3.175 |
avier | -2.995 |
Token | Reading |
Token ID | 36120 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
nep | +3.162 |
attribute | +2.689 |
scorp | +2.514 |
attributes | +2.462 |
abs | +2.456 |
Neg logit contributions | |
Kuala | -4.557 |
RM | -4.487 |
ngth | -4.366 |
illi | -4.291 |
avier | -4.126 |
Token | 55 |
Token ID | 5996 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
RM | +0.534 |
Kuala | +0.533 |
ngth | +0.481 |
illi | +0.477 |
avier | +0.445 |
Neg logit contributions | |
nep | -1.128 |
attribute | -1.016 |
scorp | -0.985 |
abs | -0.970 |
attributes | -0.967 |
Token | 80 |
Token ID | 1795 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
nep | +2.689 |
attribute | +2.392 |
scorp | +2.312 |
abs | +2.257 |
attributes | +2.257 |
Neg logit contributions | |
Kuala | -1.884 |
RM | -1.866 |
ngth | -1.743 |
illi | -1.735 |
avier | -1.622 |
Token | 953 |
Token ID | 49649 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
nep | +1.872 |
attribute | +1.684 |
scorp | +1.613 |
attributes | +1.594 |
abs | +1.585 |
Neg logit contributions | |
Kuala | -1.118 |
RM | -1.112 |
ngth | -1.027 |
illi | -1.013 |
avier | -0.958 |
Token | 16 |
Token ID | 1467 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
nep | +5.802 |
attribute | +5.402 |
abs | +5.113 |
attributes | +5.042 |
scorp | +4.956 |
Neg logit contributions | |
ngth | -6.740 |
RM | -6.734 |
Kuala | -6.634 |
illi | -6.433 |
vell | -6.006 |
Token | 27 |
Token ID | 1983 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
nep | +4.138 |
attribute | +3.689 |
scorp | +3.495 |
attributes | +3.438 |
abs | +3.423 |
Neg logit contributions | |
Kuala | -3.997 |
RM | -3.938 |
ngth | -3.826 |
illi | -3.765 |
avier | -3.534 |
Token | 145 |
Token ID | 18781 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
nep | +5.429 |
attribute | +4.887 |
scorp | +4.610 |
abs | +4.543 |
attributes | +4.524 |
Neg logit contributions | |
Kuala | -6.423 |
RM | -6.361 |
ngth | -6.155 |
illi | -6.051 |
vell | -5.723 |
Token | Flat |
Token ID | 21939 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
nep | +3.404 |
attribute | +3.013 |
abs | +2.889 |
attributes | +2.802 |
scorp | +2.787 |
Neg logit contributions | |
RM | -3.509 |
Kuala | -3.484 |
illi | -3.292 |
ngth | -3.287 |
cheon | -3.141 |
Token | buff |
Token ID | 36873 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
nep | +2.577 |
attribute | +2.239 |
scorp | +2.160 |
abs | +2.095 |
attributes | +2.093 |
Neg logit contributions | |
Kuala | -2.316 |
RM | -2.309 |
illi | -2.155 |
ngth | -2.154 |
avier | -2.041 |
Token | ers |
Token ID | 364 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
nep | +1.556 |
attribute | +1.326 |
scorp | +1.288 |
abs | +1.236 |
attributes | +1.233 |
Neg logit contributions | |
RM | -1.450 |
Kuala | -1.450 |
illi | -1.358 |
ngth | -1.341 |
avier | -1.295 |
Token | Reading |
Token ID | 36120 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
nep | +3.093 |
attribute | +2.618 |
scorp | +2.448 |
abs | +2.402 |
attributes | +2.391 |
Neg logit contributions | |
Kuala | -4.536 |
RM | -4.472 |
ngth | -4.367 |
illi | -4.280 |
avier | -4.118 |
Token | s |
Token ID | 82 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
RM | +1.243 |
Kuala | +1.195 |
illi | +1.077 |
vell | +1.013 |
avier | +1.009 |
Neg logit contributions | |
nep | -2.869 |
attribute | -2.444 |
scorp | -2.440 |
cowork | -2.352 |
legion | -2.345 |
Token | stack |
Token ID | 8931 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Kuala | +0.884 |
RM | +0.880 |
illi | +0.827 |
ngth | +0.826 |
avier | +0.789 |
Neg logit contributions | |
nep | -0.869 |
attribute | -0.748 |
scorp | -0.719 |
abs | -0.696 |
attributes | -0.695 |
Token | frame |
Token ID | 5739 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
nep | +1.047 |
attribute | +0.837 |
scorp | +0.730 |
abs | +0.714 |
attributes | +0.705 |
Neg logit contributions | |
Kuala | -2.782 |
RM | -2.746 |
illi | -2.648 |
ngth | -2.630 |
avier | -2.546 |
Token | | |
Token ID | 930 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
nep | +2.484 |
attribute | +2.155 |
scorp | +2.032 |
attributes | +1.991 |
abs | +1.981 |
Neg logit contributions | |
Kuala | -3.217 |
RM | -3.187 |
ngth | -3.040 |
illi | -3.033 |
vell | -2.881 |
Token | void |
Token ID | 7951 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
RM | +1.819 |
Kuala | +1.817 |
illi | +1.705 |
ngth | +1.687 |
avier | +1.626 |
Neg logit contributions | |
nep | -1.548 |
attribute | -1.288 |
scorp | -1.248 |
attributes | -1.193 |
abs | -1.189 |
Token | * |
Token ID | 1635 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
Kuala | +0.322 |
RM | +0.320 |
illi | +0.299 |
ngth | +0.298 |
avier | +0.283 |
Neg logit contributions | |
nep | -0.378 |
attribute | -0.334 |
scorp | -0.319 |
abs | -0.313 |
attributes | -0.312 |
Token | arg |
Token ID | 853 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
nep | +5.176 |
attribute | +4.764 |
abs | +4.363 |
attributes | +4.338 |
scorp | +4.263 |
Neg logit contributions | |
Kuala | -6.393 |
RM | -6.110 |
ngth | -5.774 |
illi | -5.772 |
vell | -5.523 |
Token | | |
Token ID | 930 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
nep | +1.266 |
attribute | +1.092 |
scorp | +1.024 |
abs | +1.006 |
attributes | +1.001 |
Neg logit contributions | |
Kuala | -1.644 |
RM | -1.615 |
ngth | -1.547 |
illi | -1.540 |
avier | -1.468 |
Token | + |
Token ID | 1343 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
nep | +1.668 |
attribute | +1.464 |
scorp | +1.405 |
abs | +1.371 |
attributes | +1.368 |
Neg logit contributions | |
Kuala | -1.499 |
RM | -1.489 |
ngth | -1.408 |
illi | -1.401 |
avier | -1.331 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
nep | +0.814 |
attribute | +0.698 |
scorp | +0.671 |
abs | +0.649 |
attributes | +0.648 |
Neg logit contributions | |
Kuala | -0.849 |
RM | -0.845 |
ngth | -0.794 |
illi | -0.794 |
avier | -0.757 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
nep | +2.501 |
attribute | +2.035 |
scorp | +1.910 |
abs | +1.824 |
attributes | +1.822 |
Neg logit contributions | |
Kuala | -4.489 |
RM | -4.483 |
ngth | -4.267 |
illi | -4.267 |
avier | -4.095 |
Token | ' |
Token ID | 6 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
RM | +0.471 |
Kuala | +0.466 |
illi | +0.425 |
ngth | +0.418 |
avier | +0.402 |
Neg logit contributions | |
nep | -0.743 |
attribute | -0.634 |
scorp | -0.632 |
abs | -0.602 |
attributes | -0.599 |
Token | s |
Token ID | 82 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
RM | +0.732 |
Kuala | +0.719 |
illi | +0.647 |
ngth | +0.610 |
vell | +0.604 |
Neg logit contributions | |
nep | -1.580 |
attribute | -1.364 |
scorp | -1.350 |
cowork | -1.300 |
abs | -1.297 |
Token | frame |
Token ID | 5739 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
RM | +0.150 |
Kuala | +0.150 |
illi | +0.142 |
ngth | +0.139 |
avier | +0.137 |
Neg logit contributions | |
nep | -0.087 |
attribute | -0.066 |
scorp | -0.066 |
attributes | -0.060 |
abs | -0.060 |
Token | | |
Token ID | 930 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
nep | +2.214 |
attribute | +1.875 |
scorp | +1.810 |
abs | +1.738 |
attributes | +1.737 |
Neg logit contributions | |
Kuala | -2.441 |
RM | -2.435 |
illi | -2.289 |
ngth | -2.280 |
avier | -2.187 |
Token | void |
Token ID | 7951 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
Kuala | +0.207 |
RM | +0.207 |
illi | +0.195 |
ngth | +0.194 |
avier | +0.186 |
Neg logit contributions | |
nep | -0.176 |
attribute | -0.149 |
scorp | -0.143 |
abs | -0.137 |
attributes | -0.137 |
Token | * |
Token ID | 1635 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
Kuala | +0.366 |
RM | +0.365 |
illi | +0.337 |
ngth | +0.335 |
avier | +0.319 |
Neg logit contributions | |
nep | -0.482 |
attribute | -0.417 |
scorp | -0.408 |
attributes | -0.393 |
abs | -0.392 |
Token | arg |
Token ID | 853 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
nep | +5.165 |
attribute | +4.706 |
abs | +4.369 |
attributes | +4.277 |
scorp | +4.198 |
Neg logit contributions | |
Kuala | -6.364 |
RM | -6.087 |
ngth | -5.735 |
illi | -5.721 |
vell | -5.477 |
Token | | |
Token ID | 930 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
nep | +1.906 |
attribute | +1.599 |
scorp | +1.554 |
attributes | +1.484 |
abs | +1.483 |
Neg logit contributions | |
Kuala | -2.057 |
RM | -2.055 |
illi | -1.927 |
ngth | -1.909 |
avier | -1.845 |
Token | + |
Token ID | 1343 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
nep | +2.437 |
attribute | +2.155 |
scorp | +2.051 |
abs | +2.031 |
attributes | +2.005 |
Neg logit contributions | |
Kuala | -2.360 |
RM | -2.347 |
ngth | -2.238 |
illi | -2.209 |
avier | -2.098 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
nep | +1.253 |
attribute | +0.975 |
scorp | +0.946 |
abs | +0.876 |
attributes | +0.872 |
Neg logit contributions | |
RM | -2.280 |
Kuala | -2.276 |
illi | -2.171 |
ngth | -2.141 |
avier | -2.093 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
nep | +2.575 |
attribute | +2.092 |
scorp | +1.969 |
abs | +1.877 |
attributes | +1.875 |
Neg logit contributions | |
Kuala | -4.572 |
RM | -4.566 |
ngth | -4.343 |
illi | -4.342 |
avier | -4.174 |
Token | try |
Token ID | 1949 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
nep | +0.485 |
attribute | +0.414 |
scorp | +0.397 |
abs | +0.385 |
attributes | +0.384 |
Neg logit contributions | |
RM | -0.543 |
Kuala | -0.536 |
ngth | -0.511 |
illi | -0.510 |
avier | -0.486 |
Token | Martin |
Token ID | 5780 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Kuala | +0.353 |
RM | +0.352 |
illi | +0.330 |
ngth | +0.329 |
avier | +0.315 |
Neg logit contributions | |
nep | -0.335 |
attribute | -0.286 |
scorp | -0.276 |
abs | -0.266 |
attributes | -0.266 |
Token | Randall |
Token ID | 29799 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
nep | +2.030 |
attribute | +1.822 |
scorp | +1.772 |
abs | +1.730 |
attributes | +1.728 |
Neg logit contributions | |
RM | -1.160 |
Kuala | -1.152 |
ngth | -1.080 |
illi | -1.047 |
avier | -0.976 |
Token | ( |
Token ID | 357 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
nep | +0.263 |
attribute | +0.233 |
scorp | +0.224 |
attributes | +0.219 |
abs | +0.219 |
Neg logit contributions | |
RM | -0.197 |
Kuala | -0.196 |
ngth | -0.184 |
illi | -0.183 |
avier | -0.173 |
Token | 020 |
Token ID | 33618 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Kuala | +0.249 |
RM | +0.246 |
ngth | +0.229 |
illi | +0.229 |
avier | +0.213 |
Neg logit contributions | |
nep | -0.361 |
attribute | -0.318 |
scorp | -0.308 |
abs | -0.301 |
attributes | -0.300 |
Token | 87 |
Token ID | 10083 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
Kuala | +0.869 |
RM | +0.869 |
illi | +0.797 |
ngth | +0.784 |
avier | +0.754 |
Neg logit contributions | |
nep | -1.169 |
attribute | -1.016 |
scorp | -0.991 |
abs | -0.957 |
attributes | -0.953 |
Token | 42 |
Token ID | 3682 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
nep | +6.607 |
attribute | +5.973 |
scorp | +5.731 |
attributes | +5.667 |
abs | +5.626 |
Neg logit contributions | |
Kuala | -4.849 |
RM | -4.790 |
ngth | -4.755 |
illi | -4.569 |
avier | -4.193 |
Token | 3 |
Token ID | 513 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
nep | +4.939 |
attribute | +4.394 |
scorp | +4.215 |
attributes | +4.135 |
abs | +4.132 |
Neg logit contributions | |
RM | -3.913 |
Kuala | -3.887 |
ngth | -3.831 |
illi | -3.720 |
avier | -3.477 |
Token | 355 |
Token ID | 28567 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
nep | +1.628 |
attribute | +1.434 |
scorp | +1.384 |
attributes | +1.348 |
abs | +1.346 |
Neg logit contributions | |
Kuala | -1.282 |
RM | -1.273 |
ngth | -1.195 |
illi | -1.188 |
avier | -1.119 |
Token | ; |
Token ID | 26 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Kuala | +0.680 |
RM | +0.680 |
illi | +0.632 |
ngth | +0.630 |
avier | +0.592 |
Neg logit contributions | |
nep | -0.947 |
attribute | -0.833 |
scorp | -0.808 |
abs | -0.786 |
attributes | -0.784 |
Token | mart |
Token ID | 11277 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Kuala | +2.776 |
RM | +2.765 |
ngth | +2.559 |
illi | +2.558 |
avier | +2.468 |
Neg logit contributions | |
nep | -2.918 |
attribute | -2.500 |
scorp | -2.433 |
attributes | -2.339 |
abs | -2.332 |
Token | signed |
Token ID | 4488 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
nep | +0.322 |
attribute | +0.285 |
scorp | +0.276 |
abs | +0.270 |
attributes | +0.269 |
Neg logit contributions | |
Kuala | -0.231 |
RM | -0.230 |
ngth | -0.214 |
illi | -0.214 |
avier | -0.201 |
Token | in |
Token ID | 287 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
Kuala | +0.696 |
RM | +0.694 |
illi | +0.643 |
ngth | +0.642 |
avier | +0.606 |
Neg logit contributions | |
nep | -0.953 |
attribute | -0.837 |
scorp | -0.811 |
abs | -0.789 |
attributes | -0.788 |
Token | March |
Token ID | 2805 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
nep | +0.578 |
attribute | +0.491 |
scorp | +0.474 |
attributes | +0.456 |
abs | +0.454 |
Neg logit contributions | |
Kuala | -0.617 |
RM | -0.612 |
illi | -0.575 |
ngth | -0.571 |
avier | -0.548 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
Kuala | +0.232 |
RM | +0.231 |
illi | +0.213 |
ngth | +0.212 |
avier | +0.201 |
Neg logit contributions | |
nep | -0.323 |
attribute | -0.282 |
scorp | -0.275 |
attributes | -0.265 |
abs | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
nep | +1.964 |
attribute | +1.704 |
abs | +1.633 |
scorp | +1.629 |
attributes | +1.591 |
Neg logit contributions | |
Kuala | -2.004 |
RM | -1.968 |
ngth | -1.873 |
illi | -1.861 |
vell | -1.783 |
Token |
|
Token ID | 198 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
nep | +3.422 |
attribute | +3.121 |
scorp | +2.943 |
abs | +2.918 |
attributes | +2.910 |
Neg logit contributions | |
Kuala | -3.491 |
RM | -3.468 |
ngth | -3.413 |
illi | -3.275 |
avier | -3.097 |
Token | Average |
Token ID | 26287 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
nep | +4.212 |
attribute | +3.733 |
abs | +3.504 |
attributes | +3.371 |
scorp | +3.351 |
Neg logit contributions | |
Kuala | -7.126 |
ngth | -6.579 |
RM | -6.434 |
illi | -6.417 |
cheon | -6.079 |
Token | annual |
Token ID | 5079 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
nep | +4.088 |
attribute | +3.672 |
scorp | +3.432 |
abs | +3.420 |
attributes | +3.382 |
Neg logit contributions | |
Kuala | -4.530 |
RM | -4.498 |
ngth | -4.371 |
illi | -4.289 |
avier | -4.062 |
Token | value |
Token ID | 1988 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
nep | +2.446 |
attribute | +2.121 |
scorp | +2.046 |
abs | +1.982 |
attributes | +1.979 |
Neg logit contributions | |
Kuala | -2.286 |
RM | -2.281 |
ngth | -2.136 |
illi | -2.136 |
avier | -2.027 |
Token | : |
Token ID | 25 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
nep | +1.375 |
attribute | +1.183 |
scorp | +1.150 |
abs | +1.108 |
attributes | +1.108 |
Neg logit contributions | |
Kuala | -1.171 |
RM | -1.169 |
illi | -1.086 |
ngth | -1.076 |
avier | -1.031 |
Token | $ |
Token ID | 720 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
nep | +1.603 |
attribute | +1.406 |
scorp | +1.355 |
abs | +1.320 |
attributes | +1.317 |
Neg logit contributions | |
Kuala | -1.377 |
RM | -1.373 |
ngth | -1.290 |
illi | -1.289 |
avier | -1.216 |
Token | ]] |
Token ID | 11907 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
nep | +1.783 |
attribute | +1.521 |
scorp | +1.401 |
abs | +1.391 |
attributes | +1.375 |
Neg logit contributions | |
Kuala | -2.549 |
RM | -2.489 |
illi | -2.405 |
ngth | -2.402 |
vell | -2.299 |
Token | ], |
Token ID | 4357 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Kuala | +0.365 |
RM | +0.363 |
illi | +0.342 |
ngth | +0.340 |
avier | +0.324 |
Neg logit contributions | |
nep | -0.366 |
attribute | -0.316 |
scorp | -0.302 |
abs | -0.294 |
attributes | -0.294 |
Token | Keys |
Token ID | 26363 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
nep | +0.908 |
attribute | +0.797 |
scorp | +0.758 |
abs | +0.746 |
attributes | +0.745 |
Neg logit contributions | |
RM | -0.771 |
Kuala | -0.766 |
illi | -0.722 |
ngth | -0.720 |
avier | -0.687 |
Token | [ |
Token ID | 58 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
nep | +0.548 |
attribute | +0.481 |
scorp | +0.457 |
abs | +0.449 |
attributes | +0.448 |
Neg logit contributions | |
Kuala | -0.512 |
RM | -0.501 |
ngth | -0.475 |
illi | -0.474 |
avier | -0.446 |
Token | search |
Token ID | 12947 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
nep | +1.697 |
attribute | +1.469 |
scorp | +1.381 |
abs | +1.370 |
attributes | +1.362 |
Neg logit contributions | |
Kuala | -1.544 |
RM | -1.531 |
illi | -1.465 |
ngth | -1.444 |
avier | -1.400 |
Token | Space |
Token ID | 14106 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
nep | +4.105 |
attribute | +3.678 |
scorp | +3.467 |
attributes | +3.433 |
abs | +3.422 |
Neg logit contributions | |
Kuala | -3.765 |
RM | -3.655 |
ngth | -3.609 |
illi | -3.547 |
avier | -3.296 |
Token | ]] |
Token ID | 11907 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
nep | +4.536 |
attribute | +3.981 |
scorp | +3.613 |
abs | +3.580 |
attributes | +3.575 |
Neg logit contributions | |
Kuala | -6.791 |
RM | -6.631 |
illi | -6.468 |
ngth | -6.460 |
avier | -6.188 |
Token | }, |
Token ID | 8964 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
nep | +1.228 |
attribute | +1.086 |
scorp | +1.043 |
abs | +1.022 |
attributes | +1.022 |
Neg logit contributions | |
Kuala | -0.903 |
RM | -0.900 |
illi | -0.841 |
ngth | -0.838 |
avier | -0.789 |
Token | { |
Token ID | 1391 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Kuala | +1.418 |
RM | +1.410 |
illi | +1.305 |
ngth | +1.301 |
avier | +1.236 |
Neg logit contributions | |
nep | -1.738 |
attribute | -1.507 |
scorp | -1.471 |
abs | -1.414 |
attributes | -1.412 |
Token | i |
Token ID | 72 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
nep | +2.755 |
attribute | +2.440 |
attributes | +2.307 |
abs | +2.292 |
scorp | +2.290 |
Neg logit contributions | |
RM | -2.275 |
Kuala | -2.270 |
ngth | -2.142 |
illi | -2.128 |
avier | -2.025 |
Token | , |
Token ID | 11 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
nep | +2.322 |
attribute | +2.047 |
attributes | +1.905 |
scorp | +1.902 |
abs | +1.902 |
Neg logit contributions | |
Kuala | -2.283 |
RM | -2.230 |
ngth | -2.141 |
illi | -2.131 |
vell | -2.007 |
Token | c |
Token ID | 66 |
Feature activation | -5.28e-03 |
Pos logit contributions | |
RM | +1.695 |
Kuala | +1.680 |
illi | +1.571 |
vell | +1.478 |
avier | +1.463 |
Neg logit contributions | |
nep | -3.273 |
attribute | -2.794 |
scorp | -2.790 |
legion | -2.676 |
attributes | -2.674 |
Token | py |
Token ID | 9078 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Kuala | +0.035 |
RM | +0.035 |
illi | +0.033 |
ngth | +0.032 |
avier | +0.031 |
Neg logit contributions | |
nep | -0.041 |
attribute | -0.035 |
scorp | -0.034 |
attributes | -0.033 |
abs | -0.033 |
Token | Reading |
Token ID | 36120 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
nep | +2.578 |
attribute | +2.178 |
attributes | +1.990 |
scorp | +1.978 |
abs | +1.972 |
Neg logit contributions | |
Kuala | -4.202 |
RM | -4.057 |
ngth | -4.045 |
illi | -3.948 |
avier | -3.839 |
Token | 55 |
Token ID | 5996 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Kuala | +1.177 |
RM | +1.174 |
illi | +1.066 |
ngth | +1.062 |
avier | +0.990 |
Neg logit contributions | |
nep | -2.262 |
attribute | -2.020 |
scorp | -1.967 |
abs | -1.919 |
attributes | -1.918 |
Token | 80 |
Token ID | 1795 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
nep | +1.565 |
attribute | +1.359 |
scorp | +1.332 |
abs | +1.285 |
attributes | +1.283 |
Neg logit contributions | |
RM | -0.978 |
Kuala | -0.970 |
illi | -0.889 |
ngth | -0.872 |
avier | -0.843 |
Token | 953 |
Token ID | 49649 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
nep | +0.950 |
attribute | +0.848 |
scorp | +0.823 |
attributes | +0.804 |
abs | +0.803 |
Neg logit contributions | |
Kuala | -0.525 |
RM | -0.524 |
ngth | -0.477 |
illi | -0.477 |
avier | -0.446 |
Token | 16 |
Token ID | 1467 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
nep | +5.100 |
attribute | +4.497 |
abs | +4.329 |
attributes | +4.255 |
scorp | +4.196 |
Neg logit contributions | |
RM | -6.146 |
Kuala | -5.982 |
ngth | -5.850 |
illi | -5.791 |
avier | -5.518 |
Token | 27 |
Token ID | 1983 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
nep | +2.608 |
attribute | +2.267 |
scorp | +2.193 |
abs | +2.124 |
attributes | +2.123 |
Neg logit contributions | |
Kuala | -2.227 |
RM | -2.221 |
illi | -2.072 |
ngth | -2.067 |
avier | -1.962 |
Token | 145 |
Token ID | 18781 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
nep | +4.644 |
attribute | +4.071 |
scorp | +3.893 |
attributes | +3.787 |
abs | +3.786 |
Neg logit contributions | |
Kuala | -4.893 |
RM | -4.872 |
ngth | -4.634 |
illi | -4.602 |
vell | -4.362 |
Token | Flat |
Token ID | 21939 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
nep | +2.703 |
attribute | +2.383 |
abs | +2.258 |
scorp | +2.246 |
attributes | +2.230 |
Neg logit contributions | |
RM | -2.533 |
Kuala | -2.505 |
illi | -2.371 |
ngth | -2.371 |
avier | -2.254 |
Token | buff |
Token ID | 36873 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
nep | +1.835 |
attribute | +1.585 |
scorp | +1.538 |
abs | +1.484 |
attributes | +1.483 |
Neg logit contributions | |
Kuala | -1.581 |
RM | -1.579 |
illi | -1.473 |
ngth | -1.464 |
avier | -1.399 |
Token | ") |
Token ID | 4943 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
nep | +4.027 |
attribute | +3.633 |
scorp | +3.504 |
abs | +3.439 |
attributes | +3.434 |
Neg logit contributions | |
Kuala | -2.373 |
RM | -2.352 |
ngth | -2.202 |
illi | -2.168 |
avier | -2.021 |
Token | args |
Token ID | 26498 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
nep | +0.663 |
attribute | +0.561 |
scorp | +0.539 |
abs | +0.520 |
attributes | +0.519 |
Neg logit contributions | |
Kuala | -0.786 |
RM | -0.784 |
illi | -0.739 |
ngth | -0.738 |
avier | -0.707 |
Token | = |
Token ID | 796 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
nep | +0.496 |
attribute | +0.430 |
scorp | +0.425 |
attributes | +0.409 |
abs | +0.408 |
Neg logit contributions | |
RM | -0.281 |
Kuala | -0.279 |
illi | -0.255 |
ngth | -0.245 |
avier | -0.238 |
Token | v |
Token ID | 410 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
nep | +0.266 |
attribute | +0.225 |
scorp | +0.219 |
attributes | +0.209 |
abs | +0.207 |
Neg logit contributions | |
Kuala | -0.270 |
RM | -0.268 |
illi | -0.251 |
ngth | -0.247 |
avier | -0.241 |
Token | ars |
Token ID | 945 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
nep | +1.407 |
attribute | +1.216 |
scorp | +1.190 |
cowork | +1.147 |
abs | +1.143 |
Neg logit contributions | |
RM | -0.864 |
Kuala | -0.861 |
illi | -0.792 |
ngth | -0.768 |
avier | -0.753 |
Token | ( |
Token ID | 7 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
nep | +2.351 |
attribute | +2.085 |
scorp | +2.017 |
abs | +1.966 |
attributes | +1.965 |
Neg logit contributions | |
Kuala | -1.660 |
RM | -1.655 |
ngth | -1.536 |
illi | -1.531 |
avier | -1.438 |
Token | ap |
Token ID | 499 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
nep | +5.237 |
attribute | +4.660 |
scorp | +4.367 |
abs | +4.359 |
attributes | +4.291 |
Neg logit contributions | |
Kuala | -5.985 |
RM | -5.910 |
ngth | -5.672 |
illi | -5.574 |
avier | -5.268 |
Token | . |
Token ID | 13 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
nep | +1.686 |
attribute | +1.452 |
scorp | +1.411 |
abs | +1.361 |
attributes | +1.360 |
Neg logit contributions | |
Kuala | -1.432 |
RM | -1.430 |
illi | -1.332 |
ngth | -1.320 |
avier | -1.263 |
Token | parse |
Token ID | 29572 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
nep | +2.467 |
attribute | +2.206 |
scorp | +2.133 |
abs | +2.088 |
attributes | +2.087 |
Neg logit contributions | |
Kuala | -1.492 |
RM | -1.478 |
ngth | -1.367 |
illi | -1.364 |
avier | -1.273 |
Token | _ |
Token ID | 62 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
nep | +1.319 |
attribute | +1.103 |
scorp | +1.067 |
abs | +1.021 |
attributes | +1.019 |
Neg logit contributions | |
RM | -1.524 |
Kuala | -1.524 |
illi | -1.433 |
ngth | -1.420 |
avier | -1.370 |
Token | args |
Token ID | 22046 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
RM | +1.027 |
Kuala | +1.013 |
illi | +0.960 |
ngth | +0.906 |
avier | +0.892 |
Neg logit contributions | |
nep | -1.612 |
attribute | -1.376 |
scorp | -1.346 |
cowork | -1.295 |
attributes | -1.279 |
Token | ' |
Token ID | 6 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Kuala | +0.772 |
RM | +0.766 |
illi | +0.712 |
ngth | +0.709 |
avier | +0.671 |
Neg logit contributions | |
nep | -1.058 |
attribute | -0.932 |
scorp | -0.902 |
attributes | -0.877 |
abs | -0.877 |
Token | s |
Token ID | 82 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
RM | +0.960 |
Kuala | +0.936 |
illi | +0.842 |
vell | +0.789 |
ngth | +0.787 |
Neg logit contributions | |
nep | -2.143 |
attribute | -1.838 |
scorp | -1.826 |
cowork | -1.760 |
legion | -1.752 |
Token | frame |
Token ID | 5739 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Kuala | +0.153 |
RM | +0.153 |
illi | +0.143 |
ngth | +0.143 |
avier | +0.136 |
Neg logit contributions | |
nep | -0.161 |
attribute | -0.139 |
scorp | -0.134 |
abs | -0.130 |
attributes | -0.130 |
Token | | |
Token ID | 930 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
nep | +1.757 |
attribute | +1.536 |
scorp | +1.439 |
attributes | +1.419 |
abs | +1.406 |
Neg logit contributions | |
Kuala | -2.198 |
RM | -2.186 |
ngth | -2.073 |
illi | -2.067 |
avier | -1.962 |
Token | void |
Token ID | 7951 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
Kuala | +0.087 |
RM | +0.087 |
illi | +0.081 |
ngth | +0.081 |
avier | +0.078 |
Neg logit contributions | |
nep | -0.075 |
attribute | -0.063 |
scorp | -0.061 |
abs | -0.058 |
attributes | -0.058 |
Token | * |
Token ID | 1635 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
Kuala | +0.397 |
RM | +0.396 |
illi | +0.367 |
ngth | +0.365 |
avier | +0.347 |
Neg logit contributions | |
nep | -0.519 |
attribute | -0.450 |
scorp | -0.439 |
attributes | -0.423 |
abs | -0.423 |
Token | arg |
Token ID | 853 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
nep | +5.017 |
attribute | +4.556 |
abs | +4.195 |
attributes | +4.141 |
scorp | +4.100 |
Neg logit contributions | |
Kuala | -6.075 |
RM | -5.814 |
ngth | -5.496 |
illi | -5.484 |
avier | -5.239 |
Token | | |
Token ID | 930 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
nep | +1.889 |
attribute | +1.582 |
scorp | +1.540 |
attributes | +1.469 |
abs | +1.468 |
Neg logit contributions | |
Kuala | -2.022 |
RM | -2.020 |
illi | -1.892 |
ngth | -1.872 |
avier | -1.813 |
Token | + |
Token ID | 1343 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
nep | +2.874 |
attribute | +2.538 |
scorp | +2.422 |
abs | +2.383 |
attributes | +2.365 |
Neg logit contributions | |
Kuala | -2.754 |
RM | -2.736 |
ngth | -2.610 |
illi | -2.583 |
avier | -2.453 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
nep | +1.340 |
attribute | +1.043 |
scorp | +1.010 |
abs | +0.937 |
attributes | +0.932 |
Neg logit contributions | |
RM | -2.455 |
Kuala | -2.451 |
illi | -2.338 |
ngth | -2.307 |
avier | -2.254 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
nep | +2.691 |
attribute | +2.191 |
scorp | +2.057 |
abs | +1.963 |
attributes | +1.961 |
Neg logit contributions | |
Kuala | -4.829 |
RM | -4.821 |
ngth | -4.592 |
illi | -4.588 |
avier | -4.407 |
Token | address |
Token ID | 2209 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
nep | +2.557 |
attribute | +2.260 |
scorp | +2.144 |
abs | +2.106 |
attributes | +2.093 |
Neg logit contributions | |
Kuala | -2.595 |
RM | -2.576 |
ngth | -2.463 |
illi | -2.430 |
avier | -2.310 |
Token | ] |
Token ID | 60 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
nep | +1.287 |
attribute | +1.101 |
scorp | +1.077 |
abs | +1.034 |
attributes | +1.034 |
Neg logit contributions | |
Kuala | -1.055 |
RM | -1.054 |
illi | -0.978 |
ngth | -0.963 |
avier | -0.929 |
Token | | |
Token ID | 930 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
nep | +1.326 |
attribute | +1.106 |
scorp | +1.079 |
abs | +1.028 |
attributes | +1.027 |
Neg logit contributions | |
Kuala | -1.405 |
RM | -1.402 |
illi | -1.313 |
ngth | -1.293 |
avier | -1.259 |
Token | + |
Token ID | 1343 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
nep | +1.013 |
attribute | +0.856 |
scorp | +0.844 |
abs | +0.807 |
attributes | +0.806 |
Neg logit contributions | |
Kuala | -0.748 |
RM | -0.743 |
illi | -0.681 |
ngth | -0.660 |
avier | -0.649 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
nep | +2.175 |
attribute | +1.719 |
scorp | +1.606 |
abs | +1.521 |
attributes | +1.519 |
Neg logit contributions | |
Kuala | -4.479 |
RM | -4.467 |
ngth | -4.264 |
illi | -4.259 |
avier | -4.109 |
Token | --+ |
Token ID | 44785 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
nep | +3.307 |
attribute | +2.766 |
scorp | +2.522 |
attributes | +2.447 |
abs | +2.443 |
Neg logit contributions | |
Kuala | -6.494 |
RM | -6.488 |
ngth | -6.245 |
illi | -6.191 |
vell | -5.938 |
Token | + |
Token ID | 1343 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
nep | +5.421 |
attribute | +5.054 |
scorp | +4.712 |
abs | +4.710 |
attributes | +4.704 |
Neg logit contributions | |
RM | -5.510 |
ngth | -5.480 |
Kuala | -5.469 |
illi | -5.237 |
vell | -4.936 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
nep | +2.796 |
attribute | +2.264 |
scorp | +2.024 |
abs | +1.980 |
attributes | +1.974 |
Neg logit contributions | |
Kuala | -6.490 |
RM | -6.427 |
ngth | -6.244 |
illi | -6.149 |
avier | -5.939 |
Token | --+ |
Token ID | 44785 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
nep | +2.813 |
attribute | +2.301 |
scorp | +2.151 |
abs | +2.057 |
attributes | +2.056 |
Neg logit contributions | |
Kuala | -5.110 |
RM | -5.102 |
ngth | -4.866 |
illi | -4.857 |
avier | -4.663 |
Token | < |
Token ID | 1279 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
nep | +3.200 |
attribute | +2.827 |
scorp | +2.662 |
abs | +2.660 |
attributes | +2.632 |
Neg logit contributions | |
Kuala | -3.703 |
RM | -3.663 |
ngth | -3.596 |
illi | -3.504 |
vell | -3.355 |
Token | -- |
Token ID | 438 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
RM | +1.759 |
Kuala | +1.699 |
illi | +1.557 |
vell | +1.472 |
avier | +1.469 |
Neg logit contributions | |
nep | -3.444 |
scorp | -2.917 |
attribute | -2.912 |
legion | -2.796 |
cowork | -2.794 |
Token | signed |
Token ID | 4488 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
Kuala | +0.659 |
RM | +0.657 |
ngth | +0.609 |
illi | +0.608 |
avier | +0.571 |
Neg logit contributions | |
nep | -0.955 |
attribute | -0.846 |
scorp | -0.820 |
abs | -0.802 |
attributes | -0.798 |
Token | in |
Token ID | 287 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Kuala | +0.538 |
RM | +0.537 |
ngth | +0.499 |
illi | +0.498 |
avier | +0.469 |
Neg logit contributions | |
nep | -0.721 |
attribute | -0.635 |
scorp | -0.614 |
abs | -0.601 |
attributes | -0.599 |
Token | March |
Token ID | 2805 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
nep | +1.157 |
attribute | +0.988 |
scorp | +0.953 |
abs | +0.918 |
attributes | +0.918 |
Neg logit contributions | |
Kuala | -1.225 |
RM | -1.223 |
illi | -1.149 |
ngth | -1.146 |
avier | -1.095 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
nep | +0.301 |
attribute | +0.262 |
scorp | +0.255 |
abs | +0.247 |
attributes | +0.247 |
Neg logit contributions | |
Kuala | -0.228 |
RM | -0.227 |
illi | -0.210 |
ngth | -0.209 |
avier | -0.199 |
Token |
|
Token ID | 198 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
nep | +2.366 |
attribute | +2.051 |
abs | +1.971 |
scorp | +1.962 |
attributes | +1.917 |
Neg logit contributions | |
Kuala | -2.446 |
RM | -2.402 |
ngth | -2.279 |
illi | -2.266 |
vell | -2.180 |
Token |
|
Token ID | 198 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
nep | +3.580 |
attribute | +3.273 |
scorp | +3.080 |
abs | +3.061 |
attributes | +3.050 |
Neg logit contributions | |
Kuala | -3.688 |
RM | -3.662 |
ngth | -3.615 |
illi | -3.462 |
avier | -3.272 |
Token | Average |
Token ID | 26287 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
nep | +4.041 |
attribute | +3.545 |
abs | +3.340 |
scorp | +3.202 |
attributes | +3.198 |
Neg logit contributions | |
Kuala | -6.790 |
ngth | -6.276 |
RM | -6.151 |
illi | -6.108 |
vell | -5.797 |
Token | annual |
Token ID | 5079 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
nep | +4.138 |
attribute | +3.708 |
scorp | +3.472 |
abs | +3.454 |
attributes | +3.418 |
Neg logit contributions | |
Kuala | -4.561 |
RM | -4.528 |
ngth | -4.393 |
illi | -4.312 |
avier | -4.085 |
Token | value |
Token ID | 1988 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
nep | +2.704 |
attribute | +2.352 |
scorp | +2.264 |
abs | +2.198 |
attributes | +2.192 |
Neg logit contributions | |
Kuala | -2.558 |
RM | -2.553 |
ngth | -2.398 |
illi | -2.392 |
avier | -2.270 |
Token | : |
Token ID | 25 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
nep | +1.726 |
attribute | +1.489 |
scorp | +1.445 |
abs | +1.395 |
attributes | +1.394 |
Neg logit contributions | |
Kuala | -1.488 |
RM | -1.485 |
illi | -1.383 |
ngth | -1.374 |
avier | -1.312 |
Token | $ |
Token ID | 720 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
nep | +1.360 |
attribute | +1.194 |
scorp | +1.150 |
abs | +1.123 |
attributes | +1.119 |
Neg logit contributions | |
Kuala | -1.180 |
RM | -1.176 |
ngth | -1.107 |
illi | -1.106 |
avier | -1.044 |
Token | SS |
Token ID | 5432 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
nep | +4.109 |
attribute | +3.669 |
scorp | +3.427 |
attributes | +3.411 |
abs | +3.378 |
Neg logit contributions | |
Kuala | -4.300 |
RM | -4.169 |
ngth | -4.068 |
illi | -3.992 |
vell | -3.759 |
Token | ID |
Token ID | 2389 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
nep | +1.670 |
attribute | +1.434 |
scorp | +1.365 |
attributes | +1.325 |
abs | +1.323 |
Neg logit contributions | |
Kuala | -1.891 |
RM | -1.877 |
ngth | -1.778 |
illi | -1.772 |
avier | -1.690 |
Token | : |
Token ID | 25 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
nep | +4.001 |
attribute | +3.493 |
abs | +3.252 |
attributes | +3.230 |
scorp | +3.212 |
Neg logit contributions | |
Kuala | -4.558 |
RM | -4.393 |
ngth | -4.277 |
illi | -4.236 |
avier | -4.068 |
Token | off |
Token ID | 2364 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
nep | +3.420 |
attribute | +2.823 |
scorp | +2.612 |
abs | +2.590 |
attributes | +2.536 |
Neg logit contributions | |
Kuala | -5.627 |
RM | -5.471 |
illi | -5.357 |
ngth | -5.339 |
avier | -5.054 |
Token | / |
Token ID | 14 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
nep | +3.682 |
attribute | +3.280 |
attributes | +3.010 |
abs | +2.996 |
scorp | +2.974 |
Neg logit contributions | |
Kuala | -4.454 |
RM | -4.390 |
illi | -4.220 |
ngth | -4.216 |
avier | -4.035 |
Token | any |
Token ID | 1092 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
nep | +4.988 |
attribute | +4.302 |
abs | +3.986 |
scorp | +3.918 |
attributes | +3.918 |
Neg logit contributions | |
Kuala | -7.230 |
RM | -6.948 |
ngth | -6.818 |
illi | -6.720 |
utt | -6.429 |
Token | Mode |
Token ID | 10363 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
nep | +4.947 |
attribute | +4.457 |
attributes | +4.069 |
abs | +4.031 |
scorp | +3.840 |
Neg logit contributions | |
Kuala | -5.927 |
RM | -5.740 |
illi | -5.580 |
ngth | -5.508 |
avier | -5.369 |
Token | : |
Token ID | 25 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
nep | +2.909 |
attribute | +2.553 |
scorp | +2.444 |
attributes | +2.384 |
abs | +2.380 |
Neg logit contributions | |
Kuala | -2.670 |
RM | -2.653 |
ngth | -2.508 |
illi | -2.492 |
avier | -2.364 |
Token | Man |
Token ID | 5124 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
nep | +2.101 |
attribute | +1.870 |
scorp | +1.776 |
attributes | +1.756 |
abs | +1.751 |
Neg logit contributions | |
Kuala | -1.566 |
RM | -1.481 |
ngth | -1.451 |
illi | -1.444 |
avier | -1.339 |
Token | aged |
Token ID | 1886 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
nep | +2.623 |
attribute | +2.379 |
scorp | +2.263 |
attributes | +2.230 |
abs | +2.213 |
Neg logit contributions | |
Kuala | -2.159 |
RM | -2.122 |
ngth | -2.041 |
illi | -1.976 |
vell | -1.828 |
Token | Access |
Token ID | 8798 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
nep | +2.395 |
attribute | +2.014 |
scorp | +1.899 |
attributes | +1.833 |
abs | +1.832 |
Neg logit contributions | |
Kuala | -3.543 |
RM | -3.539 |
ngth | -3.375 |
illi | -3.368 |
avier | -3.227 |
Token | IV |
Token ID | 3824 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
nep | +1.510 |
attribute | +1.321 |
scorp | +1.267 |
abs | +1.246 |
attributes | +1.236 |
Neg logit contributions | |
Kuala | -1.305 |
RM | -1.279 |
ngth | -1.212 |
illi | -1.179 |
avier | -1.130 |
Token | IDE |
Token ID | 14114 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
nep | +0.357 |
attribute | +0.310 |
scorp | +0.304 |
abs | +0.293 |
attributes | +0.293 |
Neg logit contributions | |
RM | -0.251 |
Kuala | -0.251 |
illi | -0.232 |
ngth | -0.229 |
avier | -0.219 |
Token | AND |
Token ID | 5357 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
nep | +4.066 |
attribute | +3.634 |
scorp | +3.406 |
abs | +3.394 |
attributes | +3.389 |
Neg logit contributions | |
Kuala | -4.133 |
RM | -4.086 |
ngth | -3.923 |
illi | -3.873 |
avier | -3.730 |
Token | CON |
Token ID | 7102 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
nep | +1.104 |
attribute | +0.989 |
scorp | +0.961 |
attributes | +0.939 |
abs | +0.938 |
Neg logit contributions | |
Kuala | -0.597 |
RM | -0.595 |
ngth | -0.546 |
illi | -0.544 |
avier | -0.505 |
Token | QU |
Token ID | 10917 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
nep | +1.482 |
attribute | +1.273 |
scorp | +1.217 |
attributes | +1.177 |
abs | +1.177 |
Neg logit contributions | |
Kuala | -1.682 |
RM | -1.668 |
ngth | -1.585 |
illi | -1.583 |
avier | -1.506 |
Token | ER |
Token ID | 1137 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
nep | +0.930 |
attribute | +0.808 |
scorp | +0.775 |
abs | +0.751 |
attributes | +0.751 |
Neg logit contributions | |
Kuala | -0.918 |
RM | -0.910 |
ngth | -0.864 |
illi | -0.859 |
avier | -0.814 |
Token | ? |
Token ID | 30 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
nep | +5.659 |
attribute | +5.016 |
scorp | +4.742 |
abs | +4.704 |
attributes | +4.701 |
Neg logit contributions | |
Kuala | -5.130 |
RM | -5.117 |
ngth | -4.989 |
illi | -4.827 |
avier | -4.657 |
Token |
|
Token ID | 198 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
nep | +1.442 |
attribute | +1.272 |
scorp | +1.219 |
abs | +1.190 |
Abrams | +1.188 |
Neg logit contributions | |
Kuala | -1.397 |
RM | -1.390 |
ngth | -1.330 |
illi | -1.307 |
avier | -1.249 |
Token |
|
Token ID | 198 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
RM | +1.607 |
Kuala | +1.587 |
illi | +1.445 |
avier | +1.378 |
vell | +1.364 |
Neg logit contributions | |
nep | -2.463 |
scorp | -2.017 |
attribute | -2.007 |
cowork | -1.911 |
legion | -1.903 |
Token | David |
Token ID | 11006 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Kuala | +1.512 |
RM | +1.482 |
ngth | +1.367 |
illi | +1.361 |
avier | +1.264 |
Neg logit contributions | |
nep | -2.727 |
attribute | -2.436 |
scorp | -2.367 |
abs | -2.315 |
attributes | -2.309 |
Token | : |
Token ID | 25 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
RM | +2.051 |
Kuala | +2.037 |
illi | +1.831 |
avier | +1.768 |
ngth | +1.729 |
Neg logit contributions | |
nep | -2.947 |
attribute | -2.436 |
scorp | -2.418 |
cowork | -2.299 |
abs | -2.281 |
Token | ' |
Token ID | 6 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
RM | +0.396 |
Kuala | +0.393 |
illi | +0.356 |
ngth | +0.344 |
avier | +0.337 |
Neg logit contributions | |
nep | -0.642 |
attribute | -0.544 |
scorp | -0.543 |
abs | -0.517 |
cowork | -0.515 |
Token | s |
Token ID | 82 |
Feature activation | -9.11e-02 |
Pos logit contributions | |
RM | +0.427 |
Kuala | +0.421 |
illi | +0.380 |
ngth | +0.361 |
avier | +0.354 |
Neg logit contributions | |
nep | -0.894 |
attribute | -0.776 |
scorp | -0.766 |
attributes | -0.737 |
cowork | -0.737 |
Token | frame |
Token ID | 5739 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
RM | +0.848 |
Kuala | +0.847 |
illi | +0.804 |
ngth | +0.786 |
avier | +0.775 |
Neg logit contributions | |
nep | -0.463 |
scorp | -0.340 |
attribute | -0.338 |
Abrams | -0.305 |
attributes | -0.305 |
Token | | |
Token ID | 930 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
nep | +1.851 |
attribute | +1.553 |
scorp | +1.509 |
abs | +1.442 |
attributes | +1.439 |
Neg logit contributions | |
Kuala | -1.996 |
RM | -1.989 |
illi | -1.866 |
ngth | -1.846 |
avier | -1.787 |
Token | void |
Token ID | 7951 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
nep | +0.309 |
attribute | +0.264 |
scorp | +0.252 |
abs | +0.245 |
attributes | +0.244 |
Neg logit contributions | |
Kuala | -0.363 |
RM | -0.362 |
illi | -0.341 |
ngth | -0.341 |
avier | -0.326 |
Token | * |
Token ID | 1635 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
Kuala | +0.159 |
RM | +0.157 |
illi | +0.144 |
ngth | +0.140 |
avier | +0.137 |
Neg logit contributions | |
nep | -0.234 |
scorp | -0.197 |
attribute | -0.197 |
attributes | -0.187 |
cowork | -0.186 |
Token | arg |
Token ID | 853 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
nep | +5.192 |
attribute | +4.766 |
abs | +4.433 |
scorp | +4.384 |
attributes | +4.380 |
Neg logit contributions | |
Kuala | -5.567 |
RM | -5.458 |
ngth | -5.192 |
illi | -5.107 |
avier | -4.818 |
Token | | |
Token ID | 930 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
nep | +1.658 |
attribute | +1.387 |
scorp | +1.350 |
attributes | +1.288 |
abs | +1.287 |
Neg logit contributions | |
Kuala | -1.777 |
RM | -1.775 |
illi | -1.665 |
ngth | -1.645 |
avier | -1.594 |
Token | + |
Token ID | 1343 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
nep | +2.300 |
attribute | +2.045 |
scorp | +1.945 |
abs | +1.923 |
attributes | +1.898 |
Neg logit contributions | |
Kuala | -2.248 |
RM | -2.235 |
ngth | -2.136 |
illi | -2.106 |
avier | -1.995 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
nep | +1.216 |
attribute | +0.943 |
scorp | +0.917 |
abs | +0.848 |
attributes | +0.845 |
Neg logit contributions | |
RM | -2.208 |
Kuala | -2.202 |
illi | -2.102 |
ngth | -2.073 |
avier | -2.026 |
Token | --+ |
Token ID | 44785 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
nep | +2.522 |
attribute | +2.036 |
scorp | +1.930 |
abs | +1.832 |
attributes | +1.830 |
Neg logit contributions | |
Kuala | -4.370 |
RM | -4.363 |
illi | -4.147 |
ngth | -4.140 |
avier | -3.992 |
Token | { |
Token ID | 1391 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
RM | +1.374 |
Kuala | +1.373 |
illi | +1.255 |
ngth | +1.246 |
avier | +1.169 |
Neg logit contributions | |
nep | -2.243 |
attribute | -1.982 |
scorp | -1.935 |
attributes | -1.874 |
abs | -1.873 |
Token | if |
Token ID | 611 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
Kuala | +1.671 |
RM | +1.667 |
illi | +1.545 |
ngth | +1.530 |
avier | +1.458 |
Neg logit contributions | |
nep | -1.944 |
attribute | -1.676 |
scorp | -1.639 |
attributes | -1.570 |
abs | -1.568 |
Token | ($ |
Token ID | 7198 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
Kuala | +1.611 |
RM | +1.608 |
illi | +1.471 |
ngth | +1.461 |
avier | +1.376 |
Neg logit contributions | |
nep | -2.556 |
attribute | -2.247 |
scorp | -2.204 |
attributes | -2.129 |
abs | -2.113 |
Token | i |
Token ID | 72 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
Kuala | +0.308 |
RM | +0.304 |
ngth | +0.278 |
illi | +0.278 |
avier | +0.260 |
Neg logit contributions | |
nep | -0.543 |
attribute | -0.484 |
scorp | -0.469 |
abs | -0.460 |
attributes | -0.458 |
Token | - |
Token ID | 532 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
nep | +0.469 |
attribute | +0.411 |
scorp | +0.395 |
abs | +0.387 |
attributes | +0.385 |
Neg logit contributions | |
Kuala | -0.389 |
RM | -0.386 |
ngth | -0.361 |
illi | -0.360 |
avier | -0.341 |
Token | eq |
Token ID | 27363 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Kuala | +0.727 |
RM | +0.726 |
illi | +0.668 |
ngth | +0.665 |
avier | +0.626 |
Neg logit contributions | |
nep | -1.136 |
attribute | -1.003 |
scorp | -0.976 |
attributes | -0.948 |
abs | -0.948 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Kuala | +6.057 |
RM | +6.055 |
illi | +5.713 |
ngth | +5.384 |
vell | +5.329 |
Neg logit contributions | |
nep | -7.624 |
scorp | -6.651 |
attribute | -6.507 |
cowork | -6.242 |
attributes | -6.169 |
Token | ) |
Token ID | 8 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
RM | +0.897 |
Kuala | +0.896 |
illi | +0.825 |
ngth | +0.820 |
avier | +0.773 |
Neg logit contributions | |
nep | -1.368 |
attribute | -1.206 |
scorp | -1.173 |
abs | -1.139 |
attributes | -1.139 |
Token | { |
Token ID | 1391 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
RM | +2.841 |
Kuala | +2.800 |
illi | +2.544 |
ngth | +2.509 |
vell | +2.373 |
Neg logit contributions | |
nep | -4.869 |
attribute | -4.284 |
scorp | -4.238 |
attributes | -4.063 |
cowork | -4.056 |
Token | $ |
Token ID | 720 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
RM | +2.850 |
Kuala | +2.848 |
illi | +2.625 |
ngth | +2.597 |
vell | +2.481 |
Neg logit contributions | |
nep | -3.271 |
attribute | -2.806 |
scorp | -2.765 |
attributes | -2.624 |
abs | -2.614 |
Token | font |
Token ID | 10331 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
Kuala | +1.034 |
RM | +1.031 |
illi | +0.944 |
ngth | +0.941 |
avier | +0.882 |
Neg logit contributions | |
nep | -1.746 |
attribute | -1.548 |
scorp | -1.507 |
abs | -1.467 |
attributes | -1.466 |
Token | ce |
Token ID | 344 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
Kuala | +0.474 |
RM | +0.474 |
illi | +0.444 |
ngth | +0.442 |
vell | +0.424 |
Neg logit contributions | |
nep | -0.456 |
attribute | -0.387 |
scorp | -0.375 |
abs | -0.361 |
attributes | -0.359 |
Token | / |
Token ID | 14 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Kuala | +0.430 |
RM | +0.428 |
illi | +0.396 |
ngth | +0.391 |
vell | +0.378 |
Neg logit contributions | |
nep | -0.504 |
attribute | -0.430 |
scorp | -0.420 |
abs | -0.407 |
attributes | -0.403 |
Token | edd |
Token ID | 6048 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
nep | +2.679 |
attribute | +2.402 |
scorp | +2.318 |
abs | +2.281 |
attributes | +2.270 |
Neg logit contributions | |
Kuala | -1.659 |
RM | -1.640 |
ngth | -1.521 |
illi | -1.492 |
avier | -1.400 |
Token | 75 |
Token ID | 2425 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
RM | +1.295 |
Kuala | +1.288 |
illi | +1.197 |
ngth | +1.161 |
avier | +1.113 |
Neg logit contributions | |
nep | -2.289 |
attribute | -2.012 |
scorp | -1.972 |
abs | -1.908 |
attributes | -1.908 |
Token | / |
Token ID | 14 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
nep | +1.442 |
attribute | +1.259 |
scorp | +1.211 |
abs | +1.175 |
attributes | +1.175 |
Neg logit contributions | |
Kuala | -1.330 |
RM | -1.326 |
ngth | -1.246 |
illi | -1.238 |
avier | -1.175 |
Token | AUT |
Token ID | 39371 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
Kuala | +0.622 |
RM | +0.620 |
illi | +0.573 |
ngth | +0.572 |
avier | +0.538 |
Neg logit contributions | |
nep | -0.906 |
attribute | -0.798 |
scorp | -0.775 |
abs | -0.753 |
attributes | -0.753 |
Token | OC |
Token ID | 4503 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
RM | +5.015 |
Kuala | +4.641 |
illi | +4.426 |
avier | +3.982 |
utt | +3.921 |
Neg logit contributions | |
nep | -9.378 |
scorp | -8.105 |
attribute | -8.095 |
legion | -7.783 |
abs | -7.733 |
Token | R |
Token ID | 49 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
nep | +2.666 |
attribute | +2.397 |
scorp | +2.337 |
abs | +2.283 |
attributes | +2.283 |
Neg logit contributions | |
Kuala | -1.227 |
RM | -1.190 |
ngth | -1.116 |
illi | -1.100 |
avier | -1.022 |
Token | OP |
Token ID | 3185 |
Feature activation | +9.44e-03 |
Pos logit contributions | |
nep | +3.063 |
attribute | +2.742 |
abs | +2.590 |
scorp | +2.583 |
attributes | +2.549 |
Neg logit contributions | |
Kuala | -3.102 |
RM | -3.054 |
ngth | -3.017 |
illi | -2.817 |
avier | -2.812 |
Token | / |
Token ID | 14 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
nep | +0.063 |
attribute | +0.056 |
scorp | +0.053 |
abs | +0.052 |
attributes | +0.051 |
Neg logit contributions | |
Kuala | -0.070 |
RM | -0.069 |
ngth | -0.066 |
illi | -0.064 |
vell | -0.062 |
Token | h |
Token ID | 71 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
nep | +1.207 |
attribute | +1.082 |
abs | +1.025 |
scorp | +1.024 |
attributes | +1.011 |
Neg logit contributions | |
Kuala | -1.130 |
ngth | -1.102 |
RM | -1.091 |
illi | -1.060 |
avier | -1.007 |
Token | b |
Token ID | 65 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Kuala | +1.503 |
RM | +1.498 |
illi | +1.399 |
ngth | +1.396 |
avier | +1.327 |
Neg logit contributions | |
nep | -1.677 |
attribute | -1.453 |
scorp | -1.404 |
abs | -1.361 |
attributes | -1.358 |
Token | ] |
Token ID | 60 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
RM | +1.723 |
Kuala | +1.682 |
illi | +1.568 |
avier | +1.516 |
vell | +1.472 |
Neg logit contributions | |
nep | -2.482 |
scorp | -2.061 |
attribute | -2.054 |
cowork | -1.956 |
legion | -1.951 |
Token | Personal |
Token ID | 30228 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Kuala | +0.062 |
RM | +0.061 |
illi | +0.056 |
ngth | +0.056 |
avier | +0.053 |
Neg logit contributions | |
nep | -0.097 |
attribute | -0.086 |
scorp | -0.083 |
abs | -0.081 |
attributes | -0.081 |
Token | best |
Token ID | 1266 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
Kuala | +2.542 |
RM | +2.537 |
illi | +2.342 |
ngth | +2.333 |
avier | +2.205 |
Neg logit contributions | |
nep | -3.609 |
attribute | -3.164 |
scorp | -3.079 |
attributes | -2.983 |
abs | -2.983 |
Token | : |
Token ID | 25 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
nep | +0.369 |
attribute | +0.313 |
scorp | +0.308 |
abs | +0.294 |
attributes | +0.294 |
Neg logit contributions | |
RM | -0.296 |
Kuala | -0.296 |
illi | -0.273 |
ngth | -0.268 |
avier | -0.259 |
Token | [/ |
Token ID | 13412 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
Kuala | +0.599 |
RM | +0.597 |
illi | +0.520 |
ngth | +0.503 |
avier | +0.487 |
Neg logit contributions | |
nep | -1.401 |
attribute | -1.227 |
scorp | -1.214 |
abs | -1.172 |
attributes | -1.171 |
Token | b |
Token ID | 65 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
RM | +4.455 |
Kuala | +4.379 |
illi | +4.064 |
avier | +4.002 |
vell | +3.998 |
Neg logit contributions | |
nep | -9.481 |
scorp | -7.704 |
attribute | -7.464 |
legion | -7.402 |
cowork | -7.348 |
Token | ] |
Token ID | 60 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
RM | +0.998 |
Kuala | +0.990 |
illi | +0.910 |
ngth | +0.880 |
avier | +0.876 |
Neg logit contributions | |
nep | -1.368 |
attribute | -1.144 |
scorp | -1.135 |
cowork | -1.079 |
attributes | -1.077 |
Token | 00 |
Token ID | 3571 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
Kuala | +0.719 |
RM | +0.717 |
illi | +0.657 |
ngth | +0.652 |
avier | +0.616 |
Neg logit contributions | |
nep | -1.146 |
attribute | -1.012 |
scorp | -0.985 |
attributes | -0.957 |
abs | -0.956 |
Token | : |
Token ID | 25 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
RM | +2.060 |
Kuala | +2.037 |
illi | +1.845 |
avier | +1.766 |
vell | +1.754 |
Neg logit contributions | |
nep | -3.149 |
attribute | -2.575 |
scorp | -2.570 |
cowork | -2.454 |
legion | -2.439 |
Token | 47 |
Token ID | 2857 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
RM | +0.481 |
Kuala | +0.477 |
illi | +0.418 |
ngth | +0.390 |
avier | +0.379 |
Neg logit contributions | |
nep | -1.310 |
attribute | -1.163 |
scorp | -1.145 |
abs | -1.111 |
attributes | -1.110 |
Token | b |
Token ID | 65 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
RM | +1.209 |
Kuala | +1.208 |
illi | +1.120 |
ngth | +1.115 |
avier | +1.057 |
Neg logit contributions | |
nep | -1.620 |
attribute | -1.416 |
scorp | -1.377 |
abs | -1.333 |
attributes | -1.333 |
Token | ] |
Token ID | 60 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
nep | +0.467 |
attribute | +0.407 |
scorp | +0.388 |
attributes | +0.378 |
abs | +0.378 |
Neg logit contributions | |
Kuala | -0.453 |
RM | -0.444 |
illi | -0.419 |
ngth | -0.415 |
vell | -0.395 |
Token | Est |
Token ID | 22362 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
RM | +0.767 |
Kuala | +0.765 |
illi | +0.713 |
ngth | +0.709 |
avier | +0.677 |
Neg logit contributions | |
nep | -0.882 |
attribute | -0.764 |
scorp | -0.739 |
attributes | -0.715 |
abs | -0.715 |
Token | imate |
Token ID | 1920 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
nep | +1.402 |
attribute | +1.240 |
scorp | +1.206 |
abs | +1.175 |
attributes | +1.171 |
Neg logit contributions | |
Kuala | -0.898 |
RM | -0.895 |
ngth | -0.822 |
illi | -0.817 |
avier | -0.767 |
Token | : |
Token ID | 25 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
nep | +0.099 |
attribute | +0.087 |
scorp | +0.084 |
abs | +0.082 |
attributes | +0.082 |
Neg logit contributions | |
Kuala | -0.069 |
RM | -0.068 |
illi | -0.063 |
ngth | -0.063 |
avier | -0.060 |
Token | [/ |
Token ID | 13412 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
RM | +1.426 |
Kuala | +1.421 |
illi | +1.296 |
ngth | +1.294 |
avier | +1.222 |
Neg logit contributions | |
nep | -2.102 |
attribute | -1.843 |
scorp | -1.795 |
attributes | -1.739 |
abs | -1.738 |
Token | b |
Token ID | 65 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
RM | +4.762 |
Kuala | +4.577 |
illi | +4.541 |
avier | +4.302 |
vell | +4.269 |
Neg logit contributions | |
nep | -8.614 |
scorp | -7.115 |
attribute | -6.998 |
cowork | -6.878 |
legion | -6.850 |
Token | ] |
Token ID | 60 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
nep | +0.707 |
attribute | +0.623 |
scorp | +0.601 |
abs | +0.584 |
attributes | +0.584 |
Neg logit contributions | |
Kuala | -0.557 |
RM | -0.548 |
illi | -0.513 |
ngth | -0.504 |
vell | -0.480 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
RM | +1.034 |
Kuala | +1.032 |
illi | +0.956 |
ngth | +0.955 |
avier | +0.907 |
Neg logit contributions | |
nep | -1.248 |
attribute | -1.081 |
scorp | -1.049 |
attributes | -1.013 |
abs | -1.013 |
Token | : |
Token ID | 25 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
nep | +0.932 |
attribute | +0.812 |
scorp | +0.785 |
abs | +0.760 |
attributes | +0.758 |
Neg logit contributions | |
Kuala | -0.805 |
RM | -0.797 |
illi | -0.750 |
ngth | -0.747 |
avier | -0.709 |
Token | 20 |
Token ID | 1238 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
RM | +1.333 |
Kuala | +1.330 |
illi | +1.192 |
ngth | +1.178 |
avier | +1.120 |
Neg logit contributions | |
nep | -2.336 |
attribute | -2.062 |
scorp | -2.014 |
abs | -1.953 |
attributes | -1.951 |
Token | af |
Token ID | 1878 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
Kuala | +0.994 |
RM | +0.991 |
illi | +0.911 |
ngth | +0.906 |
avier | +0.855 |
Neg logit contributions | |
nep | -1.686 |
attribute | -1.490 |
scorp | -1.452 |
abs | -1.411 |
attributes | -1.410 |
Token | tea |
Token ID | 8887 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
Kuala | +2.931 |
RM | +2.903 |
illi | +2.727 |
ngth | +2.696 |
avier | +2.593 |
Neg logit contributions | |
nep | -2.873 |
attribute | -2.447 |
scorp | -2.368 |
attributes | -2.264 |
abs | -2.252 |
Token | ? |
Token ID | 30 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
nep | +0.173 |
attribute | +0.151 |
scorp | +0.146 |
abs | +0.142 |
attributes | +0.142 |
Neg logit contributions | |
Kuala | -0.140 |
RM | -0.140 |
illi | -0.130 |
ngth | -0.130 |
avier | -0.123 |
Token |
|
Token ID | 198 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
Kuala | +1.785 |
RM | +1.774 |
illi | +1.652 |
ngth | +1.638 |
avier | +1.562 |
Neg logit contributions | |
nep | -2.142 |
attribute | -1.856 |
scorp | -1.799 |
attributes | -1.740 |
abs | -1.738 |
Token |
|
Token ID | 198 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
RM | +2.641 |
Kuala | +2.618 |
illi | +2.353 |
avier | +2.233 |
vell | +2.222 |
Neg logit contributions | |
nep | -4.600 |
scorp | -3.724 |
attribute | -3.656 |
legion | -3.530 |
cowork | -3.524 |
Token | Jay |
Token ID | 30568 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
Kuala | +1.860 |
RM | +1.850 |
illi | +1.735 |
ngth | +1.735 |
avier | +1.651 |
Neg logit contributions | |
nep | -1.911 |
attribute | -1.646 |
scorp | -1.587 |
abs | -1.536 |
attributes | -1.533 |
Token | C |
Token ID | 327 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
Kuala | +4.180 |
RM | +3.964 |
illi | +3.507 |
avier | +3.457 |
vell | +3.210 |
Neg logit contributions | |
nep | -9.580 |
scorp | -7.988 |
attribute | -7.830 |
legion | -7.547 |
cowork | -7.510 |
Token | z |
Token ID | 89 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
RM | +0.167 |
Kuala | +0.166 |
illi | +0.153 |
ngth | +0.146 |
avier | +0.145 |
Neg logit contributions | |
nep | -0.283 |
attribute | -0.243 |
scorp | -0.240 |
attributes | -0.231 |
abs | -0.230 |
Token | ark |
Token ID | 668 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
RM | +1.075 |
Kuala | +1.048 |
illi | +0.965 |
avier | +0.938 |
ngth | +0.899 |
Neg logit contributions | |
nep | -2.579 |
attribute | -2.226 |
scorp | -2.205 |
abs | -2.131 |
attributes | -2.131 |
Token | owski |
Token ID | 12079 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
RM | +0.126 |
Kuala | +0.124 |
illi | +0.116 |
ngth | +0.112 |
avier | +0.111 |
Neg logit contributions | |
nep | -0.199 |
attribute | -0.172 |
scorp | -0.170 |
attributes | -0.163 |
abs | -0.163 |
Token | : |
Token ID | 25 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
RM | +0.244 |
Kuala | +0.244 |
illi | +0.225 |
avier | +0.214 |
ngth | +0.214 |
Neg logit contributions | |
nep | -0.323 |
attribute | -0.270 |
scorp | -0.268 |
cowork | -0.254 |
abs | -0.254 |
Token | b |
Token ID | 65 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
nep | +0.039 |
attribute | +0.034 |
scorp | +0.033 |
abs | +0.032 |
attributes | +0.032 |
Neg logit contributions | |
Kuala | -0.030 |
RM | -0.030 |
illi | -0.028 |
ngth | -0.028 |
avier | -0.026 |
Token | ] |
Token ID | 60 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
Kuala | +0.756 |
RM | +0.746 |
illi | +0.700 |
ngth | +0.697 |
avier | +0.661 |
Neg logit contributions | |
nep | -0.813 |
attribute | -0.705 |
scorp | -0.677 |
abs | -0.658 |
attributes | -0.658 |
Token | Personal |
Token ID | 30228 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
Kuala | +0.191 |
RM | +0.191 |
illi | +0.177 |
ngth | +0.176 |
avier | +0.167 |
Neg logit contributions | |
nep | -0.235 |
attribute | -0.205 |
scorp | -0.199 |
abs | -0.192 |
attributes | -0.192 |
Token | best |
Token ID | 1266 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
nep | +0.110 |
attribute | +0.095 |
scorp | +0.092 |
abs | +0.089 |
attributes | +0.089 |
Neg logit contributions | |
Kuala | -0.094 |
RM | -0.094 |
illi | -0.087 |
ngth | -0.087 |
avier | -0.083 |
Token | : |
Token ID | 25 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
nep | +0.986 |
attribute | +0.856 |
scorp | +0.823 |
attributes | +0.800 |
abs | +0.798 |
Neg logit contributions | |
Kuala | -0.906 |
RM | -0.902 |
illi | -0.845 |
ngth | -0.842 |
avier | -0.804 |
Token | [/ |
Token ID | 13412 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
Kuala | +0.110 |
RM | +0.109 |
illi | +0.100 |
ngth | +0.099 |
avier | +0.093 |
Neg logit contributions | |
nep | -0.207 |
attribute | -0.185 |
scorp | -0.180 |
abs | -0.175 |
attributes | -0.175 |
Token | b |
Token ID | 65 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
RM | +4.551 |
Kuala | +4.373 |
illi | +4.296 |
avier | +4.117 |
vell | +4.091 |
Neg logit contributions | |
nep | -8.643 |
scorp | -7.083 |
attribute | -6.929 |
legion | -6.844 |
cowork | -6.814 |
Token | ] |
Token ID | 60 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
Kuala | +0.629 |
RM | +0.623 |
illi | +0.584 |
ngth | +0.578 |
avier | +0.551 |
Neg logit contributions | |
nep | -0.710 |
attribute | -0.616 |
scorp | -0.596 |
abs | -0.578 |
attributes | -0.576 |
Token | 1 |
Token ID | 352 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
Kuala | +0.232 |
RM | +0.231 |
illi | +0.215 |
ngth | +0.215 |
avier | +0.204 |
Neg logit contributions | |
nep | -0.273 |
attribute | -0.237 |
scorp | -0.229 |
attributes | -0.222 |
abs | -0.222 |
Token | : |
Token ID | 25 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
nep | +0.614 |
attribute | +0.532 |
scorp | +0.516 |
abs | +0.499 |
attributes | +0.496 |
Neg logit contributions | |
Kuala | -0.582 |
RM | -0.571 |
illi | -0.542 |
ngth | -0.541 |
avier | -0.514 |
Token | 07 |
Token ID | 2998 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
RM | +1.089 |
Kuala | +1.077 |
illi | +0.971 |
ngth | +0.930 |
avier | +0.911 |
Neg logit contributions | |
nep | -2.063 |
attribute | -1.805 |
scorp | -1.774 |
abs | -1.713 |
attributes | -1.710 |
Token | Journalism |
Token ID | 37406 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Kuala | +0.864 |
RM | +0.860 |
illi | +0.766 |
ngth | +0.764 |
avier | +0.699 |
Neg logit contributions | |
nep | -2.150 |
attribute | -1.936 |
scorp | -1.892 |
abs | -1.848 |
attributes | -1.847 |
Token | The |
Token ID | 383 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
RM | +2.658 |
Kuala | +2.621 |
illi | +2.448 |
ngth | +2.375 |
utt | +2.331 |
Neg logit contributions | |
nep | -2.811 |
attribute | -2.385 |
scorp | -2.301 |
attributes | -2.213 |
cowork | -2.197 |
Token | Nation |
Token ID | 8741 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Kuala | +1.289 |
RM | +1.282 |
illi | +1.108 |
ngth | +1.052 |
avier | +1.003 |
Neg logit contributions | |
nep | -3.966 |
attribute | -3.559 |
scorp | -3.503 |
abs | -3.402 |
attributes | -3.389 |
Token | is |
Token ID | 318 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
RM | +0.854 |
Kuala | +0.842 |
illi | +0.782 |
ngth | +0.773 |
avier | +0.749 |
Neg logit contributions | |
nep | -0.979 |
attribute | -0.831 |
scorp | -0.812 |
abs | -0.779 |
attributes | -0.778 |
Token | reader |
Token ID | 9173 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
RM | +0.653 |
Kuala | +0.653 |
illi | +0.618 |
ngth | +0.607 |
avier | +0.597 |
Neg logit contributions | |
nep | -0.418 |
attribute | -0.345 |
scorp | -0.322 |
attributes | -0.313 |
abs | -0.306 |
Token | supported |
Token ID | 4855 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
RM | +2.937 |
Kuala | +2.931 |
ngth | +2.807 |
illi | +2.788 |
avier | +2.700 |
Neg logit contributions | |
nep | -1.519 |
attribute | -1.227 |
scorp | -1.158 |
abs | -1.100 |
attributes | -1.090 |
Token | : |
Token ID | 25 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
Kuala | +4.771 |
RM | +4.645 |
illi | +4.262 |
vell | +3.951 |
cheon | +3.931 |
Neg logit contributions | |
nep | -8.494 |
scorp | -7.052 |
attribute | -6.925 |
cowork | -6.741 |
abs | -6.732 |
Token | Chip |
Token ID | 17869 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Kuala | +1.713 |
RM | +1.624 |
illi | +1.475 |
avier | +1.359 |
vell | +1.313 |
Neg logit contributions | |
nep | -5.012 |
attribute | -4.462 |
scorp | -4.296 |
attributes | -4.254 |
abs | -4.189 |
Token | in |
Token ID | 287 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Kuala | +1.462 |
RM | +1.461 |
illi | +1.341 |
ngth | +1.327 |
avier | +1.269 |
Neg logit contributions | |
nep | -2.218 |
attribute | -1.951 |
scorp | -1.895 |
abs | -1.841 |
attributes | -1.835 |
Token | $ |
Token ID | 720 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
nep | +1.018 |
attribute | +0.888 |
scorp | +0.856 |
abs | +0.835 |
attributes | +0.831 |
Neg logit contributions | |
Kuala | -0.883 |
RM | -0.878 |
ngth | -0.832 |
illi | -0.826 |
avier | -0.779 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
nep | +3.005 |
attribute | +2.642 |
scorp | +2.552 |
abs | +2.511 |
attributes | +2.490 |
Neg logit contributions | |
Kuala | -2.283 |
RM | -2.217 |
ngth | -2.164 |
illi | -2.054 |
vell | -1.960 |
Token | ( |
Token ID | 7 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
nep | +1.444 |
attribute | +1.264 |
scorp | +1.231 |
abs | +1.193 |
attributes | +1.192 |
Neg logit contributions | |
RM | -0.981 |
Kuala | -0.981 |
illi | -0.903 |
ngth | -0.894 |
avier | -0.851 |
Token | 165 |
Token ID | 20986 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
nep | +1.461 |
attribute | +1.294 |
scorp | +1.255 |
attributes | +1.222 |
abs | +1.222 |
Neg logit contributions | |
Kuala | -0.955 |
RM | -0.951 |
ngth | -0.880 |
illi | -0.879 |
avier | -0.823 |
Token | s |
Token ID | 82 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
RM | +0.607 |
Kuala | +0.597 |
illi | +0.541 |
ngth | +0.515 |
avier | +0.503 |
Neg logit contributions | |
nep | -1.268 |
attribute | -1.112 |
scorp | -1.088 |
cowork | -1.054 |
attributes | -1.049 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
RM | +0.207 |
Kuala | +0.205 |
illi | +0.183 |
ngth | +0.179 |
avier | +0.167 |
Neg logit contributions | |
nep | -0.523 |
attribute | -0.468 |
scorp | -0.459 |
abs | -0.446 |
attributes | -0.446 |
Token | N |
Token ID | 399 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
Kuala | +1.140 |
RM | +1.136 |
illi | +1.053 |
ngth | +1.042 |
avier | +0.996 |
Neg logit contributions | |
nep | -1.399 |
attribute | -1.218 |
scorp | -1.180 |
attributes | -1.143 |
abs | -1.140 |
Token | ge |
Token ID | 469 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
RM | +3.097 |
Kuala | +2.981 |
illi | +2.810 |
ngth | +2.687 |
vell | +2.633 |
Neg logit contributions | |
nep | -5.407 |
attribute | -4.772 |
scorp | -4.673 |
attributes | -4.550 |
legion | -4.505 |
Token | 5 |
Token ID | 20 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
RM | +3.699 |
Kuala | +3.380 |
illi | +3.121 |
avier | +2.912 |
vell | +2.908 |
Neg logit contributions | |
nep | -9.007 |
attribute | -7.937 |
scorp | -7.784 |
Abrams | -7.622 |
attributes | -7.597 |
Token | { |
Token ID | 1391 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
Kuala | +0.288 |
RM | +0.283 |
illi | +0.267 |
ngth | +0.267 |
vell | +0.248 |
Neg logit contributions | |
nep | -0.405 |
attribute | -0.358 |
scorp | -0.348 |
abs | -0.340 |
attributes | -0.336 |
Token | ( |
Token ID | 7 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
nep | +0.669 |
attribute | +0.582 |
scorp | +0.569 |
abs | +0.550 |
attributes | +0.549 |
Neg logit contributions | |
RM | -0.442 |
Kuala | -0.440 |
illi | -0.404 |
ngth | -0.396 |
avier | -0.381 |
Token | 171 |
Token ID | 27192 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
nep | +2.776 |
attribute | +2.474 |
scorp | +2.393 |
attributes | +2.340 |
abs | +2.336 |
Neg logit contributions | |
Kuala | -1.767 |
RM | -1.750 |
ngth | -1.642 |
illi | -1.626 |
avier | -1.517 |
Token | s |
Token ID | 82 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
nep | +1.346 |
attribute | +1.191 |
scorp | +1.162 |
abs | +1.128 |
attributes | +1.128 |
Neg logit contributions | |
RM | -0.696 |
Kuala | -0.694 |
illi | -0.630 |
ngth | -0.617 |
avier | -0.585 |
Token | fact |
Token ID | 1109 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
RM | +0.816 |
Kuala | +0.815 |
ngth | +0.763 |
illi | +0.760 |
avier | +0.717 |
Neg logit contributions | |
nep | -0.993 |
attribute | -0.876 |
scorp | -0.841 |
abs | -0.820 |
attributes | -0.819 |
Token | that |
Token ID | 326 |
Feature activation | +9.68e-03 |
Pos logit contributions | |
RM | +3.187 |
Kuala | +3.141 |
illi | +2.861 |
uo | +2.786 |
avier | +2.753 |
Neg logit contributions | |
nep | -4.804 |
scorp | -3.979 |
attribute | -3.893 |
cowork | -3.760 |
legion | -3.728 |
Token | one |
Token ID | 530 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
nep | +0.067 |
attribute | +0.057 |
scorp | +0.055 |
attributes | +0.053 |
abs | +0.053 |
Neg logit contributions | |
Kuala | -0.071 |
RM | -0.071 |
illi | -0.067 |
ngth | -0.067 |
avier | -0.064 |
Token | is |
Token ID | 318 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
RM | +1.680 |
Kuala | +1.678 |
illi | +1.565 |
ngth | +1.559 |
avier | +1.493 |
Neg logit contributions | |
nep | -1.760 |
attribute | -1.489 |
scorp | -1.460 |
abs | -1.399 |
attributes | -1.391 |
Token | predominantly |
Token ID | 20736 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
RM | +2.483 |
Kuala | +2.482 |
illi | +2.293 |
ngth | +2.274 |
avier | +2.174 |
Neg logit contributions | |
nep | -3.432 |
attribute | -3.007 |
scorp | -2.947 |
abs | -2.838 |
attributes | -2.835 |
Token | used |
Token ID | 973 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
RM | +3.545 |
Kuala | +3.515 |
illi | +3.213 |
avier | +3.166 |
uo | +3.106 |
Neg logit contributions | |
nep | -3.863 |
scorp | -3.182 |
attribute | -3.121 |
legion | -2.978 |
cowork | -2.951 |
Token | for |
Token ID | 329 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Kuala | +4.236 |
RM | +4.183 |
illi | +3.758 |
avier | +3.607 |
vell | +3.577 |
Neg logit contributions | |
nep | -8.653 |
scorp | -7.122 |
attribute | -6.833 |
legion | -6.716 |
cowork | -6.703 |
Token | single |
Token ID | 2060 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
Kuala | +2.194 |
RM | +2.150 |
illi | +1.980 |
avier | +1.905 |
vell | +1.902 |
Neg logit contributions | |
nep | -2.762 |
scorp | -2.268 |
attribute | -2.223 |
Abrams | -2.146 |
abs | -2.124 |
Token | line |
Token ID | 1627 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
nep | +0.389 |
attribute | +0.333 |
scorp | +0.328 |
abs | +0.317 |
attributes | +0.317 |
Neg logit contributions | |
Kuala | -0.240 |
RM | -0.239 |
illi | -0.220 |
ngth | -0.211 |
avier | -0.206 |
Token | blocks |
Token ID | 7021 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Kuala | +2.839 |
RM | +2.808 |
illi | +2.626 |
avier | +2.537 |
utt | +2.526 |
Neg logit contributions | |
nep | -2.399 |
attribute | -1.834 |
scorp | -1.811 |
cowork | -1.744 |
legion | -1.712 |
Token | and |
Token ID | 290 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Kuala | +1.871 |
RM | +1.861 |
illi | +1.721 |
ngth | +1.648 |
avier | +1.632 |
Neg logit contributions | |
nep | -2.546 |
scorp | -2.108 |
attribute | -2.091 |
cowork | -1.997 |
abs | -1.990 |
Token | . |
Token ID | 13 |
Feature activation | +9.30e-03 |
Pos logit contributions | |
RM | +0.065 |
Kuala | +0.065 |
illi | +0.059 |
ngth | +0.057 |
avier | +0.057 |
Neg logit contributions | |
nep | -0.086 |
attribute | -0.072 |
scorp | -0.072 |
attributes | -0.068 |
abs | -0.068 |
Token | Count |
Token ID | 2764 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
nep | +0.072 |
attribute | +0.063 |
scorp | +0.061 |
abs | +0.059 |
attributes | +0.059 |
Neg logit contributions | |
RM | -0.060 |
Kuala | -0.060 |
illi | -0.056 |
ngth | -0.056 |
avier | -0.053 |
Token | below |
Token ID | 2174 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
Kuala | +2.318 |
RM | +2.317 |
ngth | +2.141 |
illi | +2.140 |
avier | +2.046 |
Neg logit contributions | |
nep | -2.561 |
attribute | -2.189 |
scorp | -2.133 |
attributes | -2.051 |
abs | -2.042 |
Token | one |
Token ID | 530 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Kuala | +0.039 |
RM | +0.039 |
illi | +0.036 |
ngth | +0.036 |
avier | +0.035 |
Neg logit contributions | |
nep | -0.038 |
attribute | -0.032 |
scorp | -0.031 |
abs | -0.030 |
attributes | -0.030 |
Token | thousand |
Token ID | 7319 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
Kuala | +1.700 |
RM | +1.698 |
illi | +1.551 |
ngth | +1.540 |
avier | +1.443 |
Neg logit contributions | |
nep | -3.026 |
attribute | -2.683 |
scorp | -2.616 |
attributes | -2.550 |
abs | -2.546 |
Token | is |
Token ID | 318 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
RM | +2.746 |
Kuala | +2.744 |
illi | +2.553 |
ngth | +2.545 |
avier | +2.426 |
Neg logit contributions | |
nep | -2.995 |
attribute | -2.575 |
scorp | -2.499 |
attributes | -2.402 |
abs | -2.394 |
Token | low |
Token ID | 1877 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
RM | +5.560 |
Kuala | +5.549 |
ngth | +4.970 |
illi | +4.963 |
avier | +4.811 |
Neg logit contributions | |
nep | -6.613 |
attribute | -5.631 |
scorp | -5.561 |
attributes | -5.330 |
cowork | -5.234 |
Token | ( |
Token ID | 357 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
Kuala | +3.189 |
RM | +3.185 |
ngth | +2.909 |
illi | +2.903 |
avier | +2.714 |
Neg logit contributions | |
nep | -5.412 |
attribute | -4.783 |
scorp | -4.678 |
attributes | -4.537 |
abs | -4.518 |
Token | 7 |
Token ID | 22 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
RM | +1.625 |
Kuala | +1.583 |
illi | +1.434 |
ngth | +1.389 |
avier | +1.328 |
Neg logit contributions | |
nep | -3.593 |
attribute | -3.181 |
scorp | -3.124 |
abs | -3.029 |
attributes | -3.026 |
Token | ) |
Token ID | 8 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
RM | +2.399 |
Kuala | +2.397 |
illi | +2.206 |
ngth | +2.199 |
avier | +2.077 |
Neg logit contributions | |
nep | -3.543 |
attribute | -3.116 |
scorp | -3.034 |
attributes | -2.938 |
abs | -2.934 |
Token | I |
Token ID | 314 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Kuala | +1.686 |
RM | +1.680 |
illi | +1.563 |
ngth | +1.560 |
avier | +1.479 |
Neg logit contributions | |
nep | -1.947 |
attribute | -1.682 |
scorp | -1.638 |
attributes | -1.576 |
abs | -1.571 |
Token | b |
Token ID | 65 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
Kuala | +1.373 |
RM | +1.367 |
illi | +1.277 |
ngth | +1.274 |
avier | +1.212 |
Neg logit contributions | |
nep | -1.517 |
attribute | -1.315 |
scorp | -1.270 |
abs | -1.231 |
attributes | -1.227 |
Token | ] |
Token ID | 60 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
nep | +0.141 |
attribute | +0.120 |
scorp | +0.118 |
attributes | +0.113 |
abs | +0.113 |
Neg logit contributions | |
RM | -0.113 |
Kuala | -0.112 |
illi | -0.104 |
ngth | -0.102 |
avier | -0.100 |
Token | Est |
Token ID | 22362 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
nep | +1.784 |
attribute | +1.586 |
scorp | +1.525 |
abs | +1.497 |
attributes | +1.493 |
Neg logit contributions | |
Kuala | -1.238 |
RM | -1.210 |
ngth | -1.143 |
illi | -1.136 |
avier | -1.068 |
Token | imate |
Token ID | 1920 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
nep | +1.896 |
attribute | +1.666 |
scorp | +1.607 |
abs | +1.563 |
attributes | +1.561 |
Neg logit contributions | |
Kuala | -1.515 |
RM | -1.507 |
ngth | -1.406 |
illi | -1.396 |
avier | -1.323 |
Token | : |
Token ID | 25 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
nep | +1.323 |
attribute | +1.141 |
scorp | +1.108 |
abs | +1.069 |
attributes | +1.068 |
Neg logit contributions | |
Kuala | -1.136 |
RM | -1.134 |
illi | -1.055 |
ngth | -1.049 |
avier | -1.002 |
Token | [/ |
Token ID | 13412 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
Kuala | +0.137 |
RM | +0.136 |
illi | +0.123 |
ngth | +0.122 |
avier | +0.114 |
Neg logit contributions | |
nep | -0.279 |
attribute | -0.249 |
scorp | -0.243 |
abs | -0.237 |
attributes | -0.237 |
Token | b |
Token ID | 65 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
RM | +4.178 |
Kuala | +4.100 |
illi | +3.842 |
vell | +3.758 |
avier | +3.751 |
Neg logit contributions | |
nep | -8.559 |
scorp | -6.969 |
attribute | -6.783 |
legion | -6.697 |
cowork | -6.646 |
Token | ] |
Token ID | 60 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
RM | +0.153 |
Kuala | +0.152 |
illi | +0.140 |
ngth | +0.138 |
avier | +0.134 |
Neg logit contributions | |
nep | -0.196 |
attribute | -0.166 |
scorp | -0.163 |
attributes | -0.156 |
abs | -0.156 |
Token | 00 |
Token ID | 3571 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
nep | +1.983 |
attribute | +1.720 |
scorp | +1.650 |
abs | +1.619 |
attributes | +1.595 |
Neg logit contributions | |
Kuala | -1.961 |
RM | -1.944 |
illi | -1.847 |
ngth | -1.841 |
avier | -1.744 |
Token | : |
Token ID | 25 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Kuala | +1.225 |
RM | +1.217 |
ngth | +1.142 |
illi | +1.140 |
avier | +1.083 |
Neg logit contributions | |
nep | -1.365 |
attribute | -1.184 |
scorp | -1.147 |
abs | -1.109 |
attributes | -1.108 |
Token | 55 |
Token ID | 2816 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
nep | +1.295 |
attribute | +1.166 |
scorp | +1.135 |
abs | +1.110 |
attributes | +1.110 |
Neg logit contributions | |
Kuala | -0.609 |
RM | -0.605 |
ngth | -0.555 |
illi | -0.549 |
avier | -0.505 |
Token | | |
Token ID | 930 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
nep | +2.464 |
attribute | +2.098 |
scorp | +2.015 |
abs | +1.942 |
attributes | +1.940 |
Neg logit contributions | |
Kuala | -2.800 |
RM | -2.795 |
illi | -2.632 |
ngth | -2.631 |
avier | -2.511 |
Token | int |
Token ID | 493 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
nep | +0.519 |
attribute | +0.443 |
scorp | +0.419 |
abs | +0.410 |
attributes | +0.407 |
Neg logit contributions | |
Kuala | -0.643 |
RM | -0.641 |
ngth | -0.610 |
illi | -0.605 |
avier | -0.580 |
Token | f |
Token ID | 277 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Kuala | +3.599 |
RM | +3.590 |
illi | +3.349 |
ngth | +3.340 |
avier | +3.183 |
Neg logit contributions | |
nep | -4.111 |
attribute | -3.542 |
scorp | -3.455 |
attributes | -3.320 |
abs | -3.299 |
Token | d |
Token ID | 67 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
nep | +1.995 |
attribute | +1.800 |
scorp | +1.743 |
abs | +1.711 |
attributes | +1.706 |
Neg logit contributions | |
Kuala | -1.002 |
RM | -0.996 |
ngth | -0.904 |
illi | -0.899 |
avier | -0.829 |
Token | | |
Token ID | 930 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
nep | +0.421 |
attribute | +0.351 |
scorp | +0.345 |
attributes | +0.327 |
abs | +0.326 |
Neg logit contributions | |
RM | -0.434 |
Kuala | -0.433 |
illi | -0.404 |
ngth | -0.399 |
avier | -0.388 |
Token | < |
Token ID | 1279 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
Kuala | +0.432 |
RM | +0.431 |
ngth | +0.403 |
illi | +0.402 |
avier | +0.380 |
Neg logit contributions | |
nep | -0.508 |
attribute | -0.444 |
scorp | -0.428 |
abs | -0.416 |
attributes | -0.416 |
Token | -- |
Token ID | 438 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
RM | +4.676 |
Kuala | +4.589 |
illi | +4.237 |
ngth | +4.206 |
avier | +3.968 |
Neg logit contributions | |
nep | -7.452 |
attribute | -6.535 |
scorp | -6.409 |
Abrams | -6.167 |
attributes | -6.167 |
Token | Stack |
Token ID | 23881 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
Kuala | +0.279 |
RM | +0.278 |
illi | +0.257 |
ngth | +0.257 |
avier | +0.243 |
Neg logit contributions | |
nep | -0.379 |
attribute | -0.333 |
scorp | -0.323 |
abs | -0.314 |
attributes | -0.314 |
Token | pointer |
Token ID | 17562 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
nep | +1.698 |
attribute | +1.432 |
scorp | +1.282 |
attributes | +1.257 |
abs | +1.239 |
Neg logit contributions | |
Kuala | -3.355 |
RM | -3.307 |
illi | -3.187 |
ngth | -3.158 |
avier | -3.048 |
Token | + |
Token ID | 1343 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
nep | +1.788 |
attribute | +1.579 |
scorp | +1.499 |
abs | +1.481 |
attributes | +1.471 |
Neg logit contributions | |
Kuala | -1.651 |
RM | -1.651 |
illi | -1.548 |
ngth | -1.547 |
avier | -1.468 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
nep | +2.167 |
attribute | +1.706 |
scorp | +1.606 |
abs | +1.513 |
attributes | +1.512 |
Neg logit contributions | |
Kuala | -4.362 |
RM | -4.354 |
illi | -4.150 |
ngth | -4.144 |
avier | -4.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Kuala | +0.740 |
RM | +0.739 |
illi | +0.686 |
ngth | +0.685 |
avier | +0.649 |
Neg logit contributions | |
nep | -0.929 |
attribute | -0.811 |
scorp | -0.785 |
abs | -0.762 |
attributes | -0.761 |
Token | no |
Token ID | 645 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Kuala | +1.600 |
RM | +1.569 |
illi | +1.471 |
ngth | +1.438 |
avier | +1.417 |
Neg logit contributions | |
nep | -1.544 |
attribute | -1.307 |
scorp | -1.251 |
attributes | -1.210 |
abs | -1.198 |
Token | ? |
Token ID | 30 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
Kuala | +1.574 |
RM | +1.563 |
illi | +1.454 |
ngth | +1.441 |
vell | +1.390 |
Neg logit contributions | |
nep | -2.003 |
attribute | -1.742 |
scorp | -1.683 |
attributes | -1.636 |
abs | -1.620 |
Token |
|
Token ID | 198 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Kuala | +2.452 |
RM | +2.409 |
illi | +2.255 |
ngth | +2.202 |
avier | +2.116 |
Neg logit contributions | |
nep | -3.077 |
attribute | -2.655 |
scorp | -2.578 |
attributes | -2.487 |
abs | -2.481 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
RM | +2.025 |
Kuala | +2.013 |
illi | +1.820 |
avier | +1.729 |
vell | +1.716 |
Neg logit contributions | |
nep | -3.290 |
scorp | -2.678 |
attribute | -2.654 |
cowork | -2.537 |
legion | -2.536 |
Token | Jay |
Token ID | 30568 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
Kuala | +0.888 |
RM | +0.876 |
ngth | +0.831 |
illi | +0.826 |
avier | +0.786 |
Neg logit contributions | |
nep | -0.869 |
attribute | -0.750 |
scorp | -0.719 |
abs | -0.700 |
attributes | -0.697 |
Token | C |
Token ID | 327 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Kuala | +3.885 |
RM | +3.721 |
illi | +3.312 |
avier | +3.263 |
vell | +3.061 |
Neg logit contributions | |
nep | -8.626 |
scorp | -7.176 |
attribute | -7.074 |
legion | -6.794 |
cowork | -6.789 |
Token | z |
Token ID | 89 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
RM | +0.099 |
Kuala | +0.099 |
illi | +0.091 |
ngth | +0.087 |
avier | +0.086 |
Neg logit contributions | |
nep | -0.167 |
attribute | -0.144 |
scorp | -0.142 |
attributes | -0.136 |
abs | -0.136 |
Token | ark |
Token ID | 668 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
RM | +0.899 |
Kuala | +0.879 |
illi | +0.808 |
avier | +0.783 |
ngth | +0.757 |
Neg logit contributions | |
nep | -2.121 |
attribute | -1.836 |
scorp | -1.815 |
attributes | -1.755 |
abs | -1.755 |
Token | owski |
Token ID | 12079 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
nep | +0.386 |
attribute | +0.335 |
scorp | +0.329 |
attributes | +0.317 |
abs | +0.316 |
Neg logit contributions | |
RM | -0.250 |
Kuala | -0.247 |
illi | -0.231 |
ngth | -0.225 |
avier | -0.219 |
Token | : |
Token ID | 25 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
RM | +0.027 |
Kuala | +0.027 |
illi | +0.025 |
ngth | +0.024 |
avier | +0.024 |
Neg logit contributions | |
nep | -0.035 |
attribute | -0.029 |
scorp | -0.029 |
abs | -0.027 |
cowork | -0.027 |
Token | hen |
Token ID | 831 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
RM | +0.624 |
Kuala | +0.617 |
illi | +0.576 |
ngth | +0.569 |
avier | +0.543 |
Neg logit contributions | |
nep | -0.809 |
attribute | -0.703 |
scorp | -0.685 |
attributes | -0.661 |
abs | -0.661 |
Token | ry |
Token ID | 563 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
Kuala | +0.577 |
RM | +0.576 |
illi | +0.532 |
ngth | +0.528 |
avier | +0.498 |
Neg logit contributions | |
nep | -0.890 |
attribute | -0.784 |
scorp | -0.763 |
abs | -0.742 |
attributes | -0.740 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
Kuala | +0.091 |
RM | +0.091 |
illi | +0.085 |
ngth | +0.085 |
avier | +0.080 |
Neg logit contributions | |
nep | -0.110 |
attribute | -0.095 |
scorp | -0.092 |
abs | -0.090 |
attributes | -0.089 |
Token | c |
Token ID | 66 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Kuala | +0.320 |
RM | +0.319 |
illi | +0.294 |
ngth | +0.294 |
avier | +0.278 |
Neg logit contributions | |
nep | -0.435 |
attribute | -0.382 |
scorp | -0.370 |
abs | -0.360 |
attributes | -0.359 |
Token | ordes |
Token ID | 35770 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
Kuala | +0.646 |
RM | +0.644 |
illi | +0.590 |
ngth | +0.590 |
avier | +0.553 |
Neg logit contributions | |
nep | -1.015 |
attribute | -0.899 |
scorp | -0.873 |
abs | -0.850 |
attributes | -0.849 |
Token | @ |
Token ID | 31 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
nep | +0.647 |
attribute | +0.566 |
scorp | +0.548 |
abs | +0.531 |
attributes | +0.531 |
Neg logit contributions | |
Kuala | -0.534 |
RM | -0.530 |
ngth | -0.494 |
illi | -0.491 |
avier | -0.466 |
Token | ow |
Token ID | 322 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
RM | +4.626 |
Kuala | +4.537 |
ngth | +4.255 |
illi | +4.231 |
vell | +3.986 |
Neg logit contributions | |
nep | -7.217 |
attribute | -6.445 |
scorp | -6.293 |
Abrams | -6.118 |
attributes | -6.109 |
Token | h |
Token ID | 71 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
RM | +0.530 |
Kuala | +0.527 |
illi | +0.486 |
ngth | +0.480 |
avier | +0.462 |
Neg logit contributions | |
nep | -0.749 |
attribute | -0.654 |
scorp | -0.636 |
attributes | -0.618 |
abs | -0.615 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Kuala | +1.313 |
RM | +1.307 |
illi | +1.234 |
ngth | +1.184 |
avier | +1.142 |
Neg logit contributions | |
nep | -1.786 |
attribute | -1.559 |
scorp | -1.524 |
attributes | -1.468 |
abs | -1.455 |
Token | com |
Token ID | 785 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
nep | +1.165 |
attribute | +1.053 |
scorp | +1.024 |
abs | +1.007 |
attributes | +1.004 |
Neg logit contributions | |
Kuala | -0.441 |
RM | -0.436 |
ngth | -0.391 |
illi | -0.385 |
avier | -0.350 |
Token | , |
Token ID | 11 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
nep | +0.449 |
attribute | +0.391 |
scorp | +0.378 |
abs | +0.367 |
attributes | +0.366 |
Neg logit contributions | |
Kuala | -0.370 |
RM | -0.369 |
illi | -0.343 |
ngth | -0.343 |
avier | -0.325 |
Token | i |
Token ID | 72 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
Kuala | +0.088 |
RM | +0.087 |
illi | +0.079 |
ngth | +0.079 |
avier | +0.073 |
Neg logit contributions | |
nep | -0.170 |
attribute | -0.151 |
scorp | -0.147 |
abs | -0.144 |
attributes | -0.144 |
Token | ; |
Token ID | 2162 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
Kuala | +0.062 |
RM | +0.061 |
illi | +0.057 |
ngth | +0.057 |
avier | +0.054 |
Neg logit contributions | |
nep | -0.088 |
attribute | -0.078 |
scorp | -0.074 |
abs | -0.073 |
attributes | -0.073 |
Token | $ |
Token ID | 720 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Kuala | +0.362 |
RM | +0.361 |
ngth | +0.336 |
illi | +0.336 |
avier | +0.320 |
Neg logit contributions | |
nep | -0.429 |
attribute | -0.374 |
scorp | -0.359 |
abs | -0.353 |
attributes | -0.351 |
Token | i |
Token ID | 72 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
Kuala | +0.874 |
RM | +0.872 |
illi | +0.790 |
ngth | +0.785 |
avier | +0.729 |
Neg logit contributions | |
nep | -1.798 |
attribute | -1.607 |
scorp | -1.569 |
abs | -1.528 |
attributes | -1.528 |
Token | - |
Token ID | 532 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
Kuala | +0.302 |
RM | +0.301 |
illi | +0.278 |
ngth | +0.277 |
avier | +0.261 |
Neg logit contributions | |
nep | -0.441 |
attribute | -0.389 |
scorp | -0.377 |
abs | -0.367 |
attributes | -0.367 |
Token | le |
Token ID | 293 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
nep | +0.443 |
attribute | +0.391 |
scorp | +0.377 |
abs | +0.370 |
attributes | +0.368 |
Neg logit contributions | |
Kuala | -0.308 |
RM | -0.306 |
ngth | -0.284 |
illi | -0.283 |
avier | -0.267 |
Token | $ |
Token ID | 720 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
RM | +5.265 |
Kuala | +5.165 |
ngth | +4.903 |
illi | +4.868 |
vell | +4.692 |
Neg logit contributions | |
nep | -6.599 |
attribute | -5.592 |
scorp | -5.561 |
Abrams | -5.288 |
cowork | -5.276 |
Token | art |
Token ID | 433 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Kuala | +0.848 |
RM | +0.846 |
illi | +0.775 |
ngth | +0.772 |
avier | +0.724 |
Neg logit contributions | |
nep | -1.416 |
attribute | -1.255 |
scorp | -1.222 |
abs | -1.188 |
attributes | -1.188 |
Token | ext |
Token ID | 2302 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
RM | +2.885 |
Kuala | +2.825 |
illi | +2.688 |
ngth | +2.612 |
vell | +2.605 |
Neg logit contributions | |
nep | -4.786 |
scorp | -4.036 |
attribute | -3.894 |
legion | -3.804 |
cowork | -3.802 |
Token | . |
Token ID | 13 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Kuala | +0.527 |
RM | +0.524 |
illi | +0.486 |
ngth | +0.485 |
avier | +0.458 |
Neg logit contributions | |
nep | -0.729 |
attribute | -0.643 |
scorp | -0.621 |
attributes | -0.606 |
abs | -0.606 |
Token | Count |
Token ID | 12332 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
RM | +1.785 |
Kuala | +1.765 |
illi | +1.655 |
ngth | +1.645 |
avier | +1.570 |
Neg logit contributions | |
nep | -2.021 |
attribute | -1.727 |
scorp | -1.700 |
abs | -1.615 |
attributes | -1.612 |
Token | 45 |
Token ID | 2231 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
nep | +0.134 |
attribute | +0.118 |
scorp | +0.115 |
abs | +0.112 |
attributes | +0.112 |
Neg logit contributions | |
RM | -0.077 |
Kuala | -0.077 |
illi | -0.070 |
ngth | -0.068 |
avier | -0.066 |
Token | 287 |
Token ID | 38721 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
nep | +1.074 |
attribute | +0.939 |
scorp | +0.909 |
abs | +0.882 |
attributes | +0.882 |
Neg logit contributions | |
Kuala | -0.871 |
RM | -0.869 |
ngth | -0.813 |
illi | -0.811 |
avier | -0.767 |
Token | 119 |
Token ID | 15136 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
nep | +2.890 |
attribute | +2.550 |
scorp | +2.458 |
attributes | +2.401 |
abs | +2.399 |
Neg logit contributions | |
RM | -2.284 |
Kuala | -2.282 |
ngth | -2.192 |
illi | -2.155 |
avier | -2.021 |
Token | 8 |
Token ID | 23 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
nep | +1.930 |
attribute | +1.729 |
scorp | +1.682 |
abs | +1.644 |
attributes | +1.642 |
Neg logit contributions | |
Kuala | -1.038 |
RM | -1.034 |
ngth | -0.964 |
illi | -0.949 |
avier | -0.883 |
Token | ; |
Token ID | 26 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
RM | +1.598 |
Kuala | +1.597 |
illi | +1.480 |
ngth | +1.478 |
avier | +1.390 |
Neg logit contributions | |
nep | -2.269 |
attribute | -1.997 |
scorp | -1.939 |
abs | -1.887 |
attributes | -1.883 |
Token | adventure |
Token ID | 8855 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
Kuala | +3.266 |
RM | +3.233 |
ngth | +3.043 |
illi | +3.012 |
utt | +2.933 |
Neg logit contributions | |
nep | -2.781 |
attribute | -2.313 |
scorp | -2.228 |
attributes | -2.137 |
cowork | -2.121 |
Token | company |
Token ID | 39722 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Kuala | +4.815 |
RM | +4.774 |
ngth | +4.518 |
illi | +4.512 |
vell | +4.292 |
Neg logit contributions | |
nep | -7.036 |
attribute | -6.075 |
scorp | -5.910 |
attributes | -5.726 |
Abrams | -5.712 |
Token | . |
Token ID | 13 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Kuala | +2.854 |
RM | +2.847 |
illi | +2.654 |
ngth | +2.646 |
avier | +2.516 |
Neg logit contributions | |
nep | -3.315 |
attribute | -2.877 |
scorp | -2.785 |
abs | -2.695 |
attributes | -2.693 |
Token | co |
Token ID | 1073 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Kuala | +1.735 |
RM | +1.728 |
illi | +1.551 |
ngth | +1.525 |
vell | +1.412 |
Neg logit contributions | |
nep | -4.323 |
attribute | -3.881 |
scorp | -3.801 |
abs | -3.705 |
attributes | -3.701 |
Token | . |
Token ID | 13 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Kuala | +2.373 |
RM | +2.334 |
illi | +2.158 |
avier | +2.106 |
vell | +2.077 |
Neg logit contributions | |
nep | -3.584 |
scorp | -2.966 |
attribute | -2.954 |
legion | -2.813 |
attributes | -2.793 |
Token | uk |
Token ID | 2724 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
Kuala | +0.673 |
RM | +0.656 |
illi | +0.501 |
vell | +0.457 |
uo | +0.442 |
Neg logit contributions | |
nep | -3.982 |
attribute | -3.571 |
scorp | -3.552 |
attributes | -3.451 |
abs | -3.429 |
Token |
|
Token ID | 198 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
RM | +0.245 |
Kuala | +0.245 |
illi | +0.230 |
ngth | +0.230 |
avier | +0.218 |
Neg logit contributions | |
nep | -0.266 |
attribute | -0.230 |
scorp | -0.223 |
abs | -0.217 |
attributes | -0.215 |
Token |
|
Token ID | 198 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
RM | +0.856 |
Kuala | +0.852 |
illi | +0.780 |
avier | +0.740 |
vell | +0.737 |
Neg logit contributions | |
nep | -1.256 |
attribute | -1.035 |
scorp | -1.034 |
cowork | -0.981 |
legion | -0.976 |
Token | 3 |
Token ID | 18 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
RM | +1.999 |
Kuala | +1.968 |
illi | +1.797 |
ngth | +1.770 |
avier | +1.687 |
Neg logit contributions | |
nep | -3.475 |
attribute | -3.078 |
scorp | -3.018 |
abs | -2.917 |
attributes | -2.914 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
RM | +2.647 |
Kuala | +2.617 |
illi | +2.320 |
avier | +2.299 |
cheon | +2.181 |
Neg logit contributions | |
nep | -4.314 |
scorp | -3.535 |
attribute | -3.481 |
cowork | -3.340 |
legion | -3.318 |
Token | Z |
Token ID | 1168 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Kuala | +0.911 |
RM | +0.908 |
illi | +0.848 |
ngth | +0.841 |
avier | +0.806 |
Neg logit contributions | |
nep | -1.020 |
attribute | -0.878 |
scorp | -0.851 |
abs | -0.819 |
attributes | -0.818 |
Token | ander |
Token ID | 4066 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
RM | +1.313 |
Kuala | +1.305 |
illi | +1.216 |
ngth | +1.171 |
avier | +1.156 |
Neg logit contributions | |
nep | -2.175 |
attribute | -1.895 |
scorp | -1.862 |
abs | -1.799 |
attributes | -1.795 |
Token | F |
Token ID | 376 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
Kuala | +3.180 |
RM | +2.964 |
illi | +2.763 |
ngth | +2.565 |
avier | +2.470 |
Neg logit contributions | |
nep | -8.656 |
scorp | -7.581 |
attribute | -7.555 |
cowork | -7.264 |
abs | -7.197 |
Token | ag |
Token ID | 363 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
RM | +1.288 |
Kuala | +1.284 |
illi | +1.200 |
avier | +1.123 |
ngth | +1.118 |
Neg logit contributions | |
nep | -2.957 |
attribute | -2.546 |
scorp | -2.541 |
attributes | -2.442 |
abs | -2.431 |
Token | erson |
Token ID | 882 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
RM | +0.929 |
Kuala | +0.924 |
illi | +0.877 |
ngth | +0.859 |
avier | +0.839 |
Neg logit contributions | |
nep | -0.853 |
attribute | -0.711 |
scorp | -0.692 |
abs | -0.662 |
attributes | -0.661 |
Token | ( |
Token ID | 357 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
Kuala | +0.402 |
RM | +0.399 |
illi | +0.361 |
ngth | +0.349 |
avier | +0.340 |
Neg logit contributions | |
nep | -0.745 |
attribute | -0.652 |
scorp | -0.641 |
attributes | -0.617 |
abs | -0.617 |
Token | 46 |
Token ID | 3510 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
RM | +0.311 |
Kuala | +0.307 |
illi | +0.280 |
ngth | +0.272 |
avier | +0.260 |
Neg logit contributions | |
nep | -0.597 |
attribute | -0.527 |
scorp | -0.516 |
abs | -0.501 |
attributes | -0.500 |
Token | talking |
Token ID | 3375 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
RM | +0.944 |
Kuala | +0.943 |
illi | +0.888 |
ngth | +0.871 |
avier | +0.834 |
Neg logit contributions | |
nep | -1.061 |
attribute | -0.907 |
scorp | -0.888 |
attributes | -0.850 |
abs | -0.846 |
Token | about |
Token ID | 546 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
Kuala | +1.836 |
RM | +1.818 |
illi | +1.707 |
ngth | +1.631 |
avier | +1.624 |
Neg logit contributions | |
nep | -1.765 |
attribute | -1.450 |
scorp | -1.443 |
attributes | -1.349 |
cowork | -1.333 |
Token | ? |
Token ID | 30 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
nep | +0.116 |
attribute | +0.101 |
scorp | +0.098 |
abs | +0.095 |
attributes | +0.095 |
Neg logit contributions | |
Kuala | -0.100 |
RM | -0.099 |
illi | -0.093 |
ngth | -0.093 |
avier | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
Kuala | +1.359 |
RM | +1.351 |
illi | +1.259 |
ngth | +1.248 |
avier | +1.191 |
Neg logit contributions | |
nep | -1.621 |
attribute | -1.402 |
scorp | -1.361 |
abs | -1.314 |
attributes | -1.314 |
Token |
|
Token ID | 198 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
RM | +2.270 |
Kuala | +2.244 |
illi | +2.025 |
avier | +1.926 |
vell | +1.908 |
Neg logit contributions | |
nep | -3.784 |
scorp | -3.075 |
attribute | -3.031 |
legion | -2.915 |
cowork | -2.908 |
Token | Jay |
Token ID | 30568 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
Kuala | +1.969 |
RM | +1.964 |
illi | +1.839 |
ngth | +1.834 |
avier | +1.748 |
Neg logit contributions | |
nep | -2.053 |
attribute | -1.768 |
scorp | -1.708 |
abs | -1.650 |
attributes | -1.648 |
Token | C |
Token ID | 327 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
Kuala | +3.759 |
RM | +3.590 |
illi | +3.214 |
avier | +3.133 |
vell | +2.938 |
Neg logit contributions | |
nep | -8.217 |
scorp | -6.881 |
attribute | -6.791 |
legion | -6.504 |
cowork | -6.483 |
Token | z |
Token ID | 89 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
nep | +0.176 |
attribute | +0.151 |
scorp | +0.149 |
attributes | +0.144 |
abs | +0.143 |
Neg logit contributions | |
RM | -0.106 |
Kuala | -0.106 |
illi | -0.098 |
ngth | -0.094 |
avier | -0.092 |
Token | ark |
Token ID | 668 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
RM | +0.913 |
Kuala | +0.890 |
illi | +0.821 |
avier | +0.792 |
ngth | +0.766 |
Neg logit contributions | |
nep | -2.148 |
attribute | -1.861 |
scorp | -1.839 |
abs | -1.780 |
attributes | -1.778 |
Token | owski |
Token ID | 12079 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
nep | +0.141 |
attribute | +0.122 |
scorp | +0.120 |
attributes | +0.115 |
abs | +0.115 |
Neg logit contributions | |
RM | -0.090 |
Kuala | -0.089 |
illi | -0.083 |
ngth | -0.081 |
avier | -0.079 |
Token | : |
Token ID | 25 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
RM | +0.259 |
Kuala | +0.257 |
illi | +0.237 |
avier | +0.226 |
ngth | +0.226 |
Neg logit contributions | |
nep | -0.340 |
attribute | -0.285 |
scorp | -0.283 |
abs | -0.268 |
cowork | -0.268 |
Token | z |
Token ID | 89 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
nep | +0.833 |
attribute | +0.730 |
scorp | +0.710 |
abs | +0.691 |
attributes | +0.688 |
Neg logit contributions | |
Kuala | -0.616 |
RM | -0.610 |
ngth | -0.569 |
illi | -0.568 |
avier | -0.536 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
Kuala | +0.637 |
RM | +0.636 |
illi | +0.595 |
ngth | +0.591 |
avier | +0.567 |
Neg logit contributions | |
nep | -0.630 |
attribute | -0.538 |
scorp | -0.520 |
attributes | -0.501 |
abs | -0.501 |
Token | GER |
Token ID | 44186 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
nep | +2.325 |
attribute | +2.044 |
scorp | +1.977 |
abs | +1.916 |
attributes | +1.914 |
Neg logit contributions | |
Kuala | -1.856 |
RM | -1.826 |
ngth | -1.730 |
illi | -1.719 |
avier | -1.625 |
Token | ON |
Token ID | 1340 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
Kuala | +0.118 |
RM | +0.117 |
ngth | +0.111 |
illi | +0.111 |
avier | +0.106 |
Neg logit contributions | |
nep | -0.106 |
attribute | -0.091 |
scorp | -0.087 |
attributes | -0.084 |
abs | -0.084 |
Token | IM |
Token ID | 3955 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
RM | +2.404 |
Kuala | +2.276 |
illi | +2.028 |
avier | +1.883 |
cheon | +1.848 |
Neg logit contributions | |
nep | -4.496 |
scorp | -3.870 |
attribute | -3.755 |
cowork | -3.652 |
legion | -3.647 |
Token | O |
Token ID | 46 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
RM | +1.797 |
Kuala | +1.723 |
illi | +1.563 |
avier | +1.511 |
uo | +1.458 |
Neg logit contributions | |
nep | -2.513 |
attribute | -2.117 |
scorp | -2.110 |
attributes | -1.999 |
abs | -1.992 |
Token | T |
Token ID | 309 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
RM | +3.906 |
Kuala | +3.904 |
illi | +3.506 |
ngth | +3.397 |
avier | +3.245 |
Neg logit contributions | |
nep | -7.444 |
attribute | -6.526 |
scorp | -6.385 |
abs | -6.219 |
attributes | -6.190 |
Token | OC |
Token ID | 4503 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
RM | +2.468 |
Kuala | +2.314 |
illi | +2.106 |
avier | +2.029 |
ngth | +1.989 |
Neg logit contributions | |
nep | -4.483 |
scorp | -3.820 |
attribute | -3.775 |
abs | -3.617 |
attributes | -3.611 |
Token | IN |
Token ID | 3268 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
RM | +0.352 |
Kuala | +0.352 |
illi | +0.326 |
ngth | +0.323 |
avier | +0.308 |
Neg logit contributions | |
nep | -0.440 |
attribute | -0.382 |
scorp | -0.371 |
abs | -0.358 |
attributes | -0.358 |
Token | IT |
Token ID | 2043 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Kuala | +0.801 |
RM | +0.799 |
illi | +0.739 |
ngth | +0.734 |
avier | +0.695 |
Neg logit contributions | |
nep | -1.055 |
attribute | -0.919 |
scorp | -0.894 |
abs | -0.865 |
attributes | -0.864 |
Token | I |
Token ID | 40 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Kuala | +1.426 |
RM | +1.426 |
illi | +1.325 |
ngth | +1.317 |
avier | +1.252 |
Neg logit contributions | |
nep | -1.756 |
attribute | -1.528 |
scorp | -1.482 |
abs | -1.435 |
attributes | -1.433 |
Token | M |
Token ID | 337 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Kuala | +1.980 |
RM | +1.937 |
illi | +1.735 |
ngth | +1.616 |
avier | +1.615 |
Neg logit contributions | |
nep | -3.640 |
attribute | -3.141 |
scorp | -3.095 |
abs | -3.000 |
cowork | -2.981 |
Token | ., |
Token ID | 1539 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Kuala | +2.284 |
RM | +2.280 |
illi | +2.132 |
ngth | +2.125 |
avier | +2.029 |
Neg logit contributions | |
nep | -2.431 |
attribute | -2.094 |
scorp | -2.023 |
attributes | -1.954 |
abs | -1.954 |
Token | Sch |
Token ID | 3059 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
Kuala | +2.583 |
RM | +2.553 |
illi | +2.383 |
ngth | +2.352 |
avier | +2.268 |
Neg logit contributions | |
nep | -3.004 |
attribute | -2.593 |
scorp | -2.515 |
abs | -2.427 |
attributes | -2.423 |
Token | ol |
Token ID | 349 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Kuala | +0.011 |
RM | +0.011 |
ngth | +0.010 |
illi | +0.010 |
avier | +0.009 |
Neg logit contributions | |
nep | -0.016 |
attribute | -0.015 |
scorp | -0.014 |
abs | -0.014 |
attributes | -0.014 |
Token | te |
Token ID | 660 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
nep | +1.837 |
attribute | +1.637 |
scorp | +1.575 |
abs | +1.544 |
attributes | +1.537 |
Neg logit contributions | |
RM | -1.362 |
Kuala | -1.360 |
ngth | -1.250 |
illi | -1.232 |
avier | -1.162 |
Token | , |
Token ID | 11 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
Kuala | +2.096 |
RM | +2.094 |
illi | +1.959 |
avier | +1.842 |
vell | +1.823 |
Neg logit contributions | |
nep | -3.153 |
scorp | -2.627 |
attribute | -2.616 |
cowork | -2.486 |
attributes | -2.476 |
Token | R |
Token ID | 371 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
Kuala | +3.337 |
RM | +3.322 |
illi | +2.919 |
ngth | +2.706 |
avier | +2.642 |
Neg logit contributions | |
nep | -8.029 |
attribute | -7.041 |
scorp | -6.933 |
abs | -6.733 |
attributes | -6.703 |
Token | ., |
Token ID | 1539 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
RM | +2.583 |
Kuala | +2.582 |
illi | +2.409 |
ngth | +2.400 |
avier | +2.294 |
Neg logit contributions | |
nep | -2.944 |
attribute | -2.540 |
scorp | -2.459 |
attributes | -2.376 |
abs | -2.374 |
Token | Sal |
Token ID | 4849 |
Feature activation | -5.71e-03 |
Pos logit contributions | |
Kuala | +2.141 |
RM | +2.120 |
illi | +1.980 |
ngth | +1.960 |
avier | +1.881 |
Neg logit contributions | |
nep | -2.517 |
attribute | -2.178 |
scorp | -2.114 |
abs | -2.039 |
attributes | -2.037 |
Token | m |
Token ID | 76 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Kuala | +0.035 |
RM | +0.034 |
ngth | +0.032 |
illi | +0.032 |
avier | +0.030 |
Neg logit contributions | |
nep | -0.047 |
attribute | -0.041 |
scorp | -0.040 |
abs | -0.039 |
attributes | -0.039 |
Token | iv |
Token ID | 452 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Kuala | +1.570 |
RM | +1.565 |
illi | +1.445 |
ngth | +1.434 |
avier | +1.350 |
Neg logit contributions | |
nep | -2.540 |
attribute | -2.244 |
scorp | -2.185 |
abs | -2.124 |
attributes | -2.122 |
Token | � |
Token ID | 447 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
nep | +0.412 |
attribute | +0.360 |
scorp | +0.347 |
attributes | +0.337 |
abs | +0.336 |
Neg logit contributions | |
RM | -0.374 |
Kuala | -0.374 |
ngth | -0.353 |
illi | -0.351 |
avier | -0.333 |
Token | � |
Token ID | 251 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
Kuala | +0.326 |
RM | +0.326 |
illi | +0.297 |
ngth | +0.294 |
avier | +0.277 |
Neg logit contributions | |
nep | -0.581 |
attribute | -0.516 |
scorp | -0.503 |
abs | -0.489 |
attributes | -0.488 |
Token |
|
Token ID | 198 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
nep | +0.289 |
attribute | +0.252 |
scorp | +0.243 |
attributes | +0.236 |
abs | +0.236 |
Neg logit contributions | |
Kuala | -0.250 |
RM | -0.249 |
illi | -0.233 |
ngth | -0.232 |
avier | -0.221 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
nep | +1.433 |
attribute | +1.229 |
scorp | +1.197 |
abs | +1.153 |
attributes | +1.152 |
Neg logit contributions | |
Kuala | -1.164 |
RM | -1.162 |
illi | -1.078 |
ngth | -1.060 |
avier | -1.022 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
nep | +0.772 |
attribute | +0.665 |
scorp | +0.641 |
abs | +0.620 |
attributes | +0.619 |
Neg logit contributions | |
Kuala | -0.769 |
RM | -0.763 |
ngth | -0.719 |
illi | -0.717 |
avier | -0.682 |
Token | Continue |
Token ID | 10054 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
nep | +1.068 |
attribute | +0.913 |
scorp | +0.886 |
attributes | +0.852 |
abs | +0.849 |
Neg logit contributions | |
Kuala | -1.064 |
RM | -1.057 |
illi | -0.994 |
ngth | -0.982 |
avier | -0.944 |
Token | reading |
Token ID | 3555 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
nep | +3.349 |
attribute | +2.799 |
scorp | +2.660 |
abs | +2.554 |
attributes | +2.550 |
Neg logit contributions | |
RM | -4.877 |
Kuala | -4.871 |
ngth | -4.637 |
illi | -4.615 |
avier | -4.426 |
Token | the |
Token ID | 262 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
Kuala | +0.219 |
RM | +0.218 |
illi | +0.203 |
avier | +0.193 |
ngth | +0.192 |
Neg logit contributions | |
nep | -0.232 |
attribute | -0.190 |
scorp | -0.188 |
attributes | -0.177 |
cowork | -0.177 |
Token | main |
Token ID | 1388 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
nep | +0.216 |
attribute | +0.184 |
scorp | +0.179 |
attributes | +0.172 |
abs | +0.172 |
Neg logit contributions | |
Kuala | -0.169 |
RM | -0.167 |
illi | -0.156 |
ngth | -0.150 |
avier | -0.149 |
Token | story |
Token ID | 1621 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
Kuala | +1.637 |
RM | +1.622 |
illi | +1.489 |
vell | +1.440 |
cheon | +1.428 |
Neg logit contributions | |
nep | -2.214 |
attribute | -1.802 |
scorp | -1.766 |
abs | -1.726 |
cowork | -1.713 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
RM | +1.929 |
Kuala | +1.917 |
illi | +1.732 |
avier | +1.639 |
cheon | +1.616 |
Neg logit contributions | |
nep | -2.922 |
scorp | -2.423 |
attribute | -2.421 |
cowork | -2.301 |
abs | -2.290 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
nep | +0.943 |
attribute | +0.803 |
scorp | +0.777 |
abs | +0.746 |
attributes | +0.745 |
Neg logit contributions | |
Kuala | -0.974 |
RM | -0.972 |
illi | -0.911 |
ngth | -0.906 |
avier | -0.869 |
Token | a |
Token ID | 257 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
nep | +0.843 |
attribute | +0.723 |
scorp | +0.702 |
abs | +0.677 |
attributes | +0.675 |
Neg logit contributions | |
Kuala | -0.785 |
RM | -0.783 |
illi | -0.732 |
ngth | -0.728 |
avier | -0.695 |
Token | block |
Token ID | 2512 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
nep | +0.861 |
attribute | +0.729 |
scorp | +0.709 |
abs | +0.681 |
attributes | +0.679 |
Neg logit contributions | |
Kuala | -0.882 |
RM | -0.878 |
illi | -0.823 |
ngth | -0.816 |
avier | -0.783 |
Token | ( |
Token ID | 357 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
nep | +1.600 |
attribute | +1.389 |
scorp | +1.334 |
attributes | +1.295 |
abs | +1.293 |
Neg logit contributions | |
Kuala | -1.503 |
RM | -1.499 |
illi | -1.404 |
ngth | -1.400 |
avier | -1.336 |
Token | e |
Token ID | 68 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
nep | +0.624 |
attribute | +0.547 |
scorp | +0.531 |
abs | +0.515 |
attributes | +0.515 |
Neg logit contributions | |
Kuala | -0.450 |
RM | -0.449 |
illi | -0.415 |
ngth | -0.413 |
avier | -0.391 |
Token | . |
Token ID | 13 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
nep | +1.599 |
attribute | +1.367 |
scorp | +1.338 |
abs | +1.284 |
attributes | +1.283 |
Neg logit contributions | |
RM | -1.308 |
Kuala | -1.306 |
illi | -1.219 |
ngth | -1.195 |
avier | -1.159 |
Token | g |
Token ID | 70 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
nep | +4.006 |
attribute | +3.659 |
scorp | +3.477 |
abs | +3.433 |
attributes | +3.428 |
Neg logit contributions | |
Kuala | -3.256 |
RM | -3.214 |
ngth | -3.116 |
illi | -2.988 |
avier | -2.808 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
nep | +0.572 |
attribute | +0.492 |
scorp | +0.472 |
abs | +0.457 |
attributes | +0.455 |
Neg logit contributions | |
Kuala | -0.628 |
RM | -0.624 |
ngth | -0.589 |
illi | -0.588 |
avier | -0.562 |
Token | print |
Token ID | 3601 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
nep | +1.599 |
attribute | +1.386 |
scorp | +1.335 |
abs | +1.294 |
attributes | +1.293 |
Neg logit contributions | |
Kuala | -1.502 |
RM | -1.496 |
illi | -1.402 |
ngth | -1.400 |
avier | -1.335 |
Token | it |
Token ID | 340 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
nep | +0.978 |
attribute | +0.856 |
scorp | +0.826 |
attributes | +0.802 |
abs | +0.802 |
Neg logit contributions | |
Kuala | -0.816 |
RM | -0.811 |
illi | -0.756 |
ngth | -0.755 |
avier | -0.719 |
Token | out |
Token ID | 503 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
nep | +1.501 |
attribute | +1.316 |
scorp | +1.267 |
attributes | +1.233 |
abs | +1.233 |
Neg logit contributions | |
Kuala | -1.264 |
RM | -1.259 |
ngth | -1.172 |
illi | -1.170 |
avier | -1.114 |
Token | , |
Token ID | 11 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Kuala | +0.961 |
RM | +0.955 |
illi | +0.889 |
ngth | +0.878 |
avier | +0.843 |
Neg logit contributions | |
nep | -1.060 |
attribute | -0.909 |
scorp | -0.889 |
abs | -0.848 |
attributes | -0.842 |
Token | out |
Token ID | 503 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
Kuala | +1.365 |
RM | +1.359 |
illi | +1.273 |
ngth | +1.264 |
avier | +1.217 |
Neg logit contributions | |
nep | -1.255 |
attribute | -1.060 |
scorp | -1.032 |
abs | -0.986 |
attributes | -0.982 |
Token | - |
Token ID | 12 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Kuala | +0.294 |
RM | +0.293 |
illi | +0.272 |
ngth | +0.272 |
avier | +0.257 |
Neg logit contributions | |
nep | -0.392 |
attribute | -0.344 |
scorp | -0.333 |
abs | -0.324 |
attributes | -0.324 |
Token | of |
Token ID | 1659 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
nep | +1.505 |
attribute | +1.322 |
scorp | +1.274 |
abs | +1.243 |
attributes | +1.239 |
Neg logit contributions | |
Kuala | -1.229 |
RM | -1.212 |
ngth | -1.143 |
illi | -1.132 |
avier | -1.077 |
Token | - |
Token ID | 12 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
nep | +0.636 |
attribute | +0.555 |
scorp | +0.542 |
abs | +0.524 |
attributes | +0.524 |
Neg logit contributions | |
Kuala | -0.420 |
RM | -0.420 |
illi | -0.386 |
ngth | -0.379 |
avier | -0.362 |
Token | the |
Token ID | 1169 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
nep | +2.009 |
attribute | +1.793 |
scorp | +1.729 |
abs | +1.698 |
attributes | +1.695 |
Neg logit contributions | |
Kuala | -1.271 |
RM | -1.236 |
ngth | -1.184 |
illi | -1.150 |
avier | -1.090 |
Token | - |
Token ID | 12 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
nep | +3.622 |
attribute | +3.234 |
scorp | +3.102 |
attributes | +3.037 |
abs | +3.033 |
Neg logit contributions | |
Kuala | -2.760 |
RM | -2.753 |
ngth | -2.595 |
illi | -2.568 |
avier | -2.403 |
Token | box |
Token ID | 3524 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
nep | +1.386 |
attribute | +1.224 |
scorp | +1.187 |
abs | +1.153 |
attributes | +1.152 |
Neg logit contributions | |
Kuala | -1.002 |
RM | -0.992 |
ngth | -0.926 |
illi | -0.919 |
avier | -0.864 |
Token | credit |
Token ID | 3884 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
nep | +0.823 |
attribute | +0.697 |
scorp | +0.668 |
attributes | +0.644 |
abs | +0.644 |
Neg logit contributions | |
Kuala | -0.981 |
RM | -0.980 |
illi | -0.925 |
ngth | -0.924 |
avier | -0.884 |
Token | card |
Token ID | 2657 |
Feature activation | +7.22e-04 |
Pos logit contributions | |
nep | +0.249 |
attribute | +0.213 |
scorp | +0.206 |
abs | +0.199 |
attributes | +0.198 |
Neg logit contributions | |
Kuala | -0.245 |
RM | -0.244 |
illi | -0.229 |
ngth | -0.228 |
avier | -0.218 |
Token | processing |
Token ID | 7587 |
Feature activation | -9.88e-03 |
Pos logit contributions | |
nep | +0.005 |
attribute | +0.004 |
scorp | +0.004 |
abs | +0.004 |
attributes | +0.004 |
Neg logit contributions | |
Kuala | -0.006 |
RM | -0.006 |
illi | -0.005 |
ngth | -0.005 |
avier | -0.005 |
Token | .. |
Token ID | 492 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
nep | +1.867 |
attribute | +1.597 |
scorp | +1.523 |
attributes | +1.467 |
abs | +1.467 |
Neg logit contributions | |
Kuala | -2.256 |
RM | -2.237 |
illi | -2.122 |
ngth | -2.117 |
avier | -2.026 |
Token | end |
Token ID | 437 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
nep | +2.323 |
attribute | +2.031 |
scorp | +1.961 |
abs | +1.907 |
attributes | +1.903 |
Neg logit contributions | |
Kuala | -1.896 |
RM | -1.880 |
illi | -1.757 |
ngth | -1.752 |
avier | -1.672 |
Token | syntax |
Token ID | 15582 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
nep | +1.226 |
attribute | +1.041 |
scorp | +1.002 |
abs | +0.964 |
attributes | +0.964 |
Neg logit contributions | |
Kuala | -1.383 |
RM | -1.380 |
illi | -1.299 |
ngth | -1.296 |
avier | -1.240 |
Token | e |
Token ID | 304 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
nep | +0.575 |
attribute | +0.503 |
scorp | +0.487 |
abs | +0.473 |
attributes | +0.473 |
Neg logit contributions | |
Kuala | -0.446 |
RM | -0.446 |
illi | -0.414 |
ngth | -0.413 |
avier | -0.391 |
Token | . |
Token ID | 13 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
nep | +1.581 |
attribute | +1.359 |
scorp | +1.324 |
abs | +1.275 |
attributes | +1.274 |
Neg logit contributions | |
Kuala | -1.324 |
RM | -1.323 |
illi | -1.234 |
ngth | -1.217 |
avier | -1.170 |
Token | g |
Token ID | 70 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
nep | +3.282 |
attribute | +2.926 |
scorp | +2.821 |
abs | +2.755 |
attributes | +2.752 |
Neg logit contributions | |
Kuala | -2.439 |
RM | -2.424 |
ngth | -2.285 |
illi | -2.243 |
avier | -2.108 |
Token | .: |
Token ID | 11207 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
nep | +2.528 |
attribute | +2.058 |
scorp | +1.952 |
abs | +1.871 |
attributes | +1.837 |
Neg logit contributions | |
Kuala | -4.485 |
RM | -4.462 |
ngth | -4.263 |
illi | -4.244 |
avier | -4.100 |
Token |
|
Token ID | 198 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
nep | +1.396 |
attribute | +1.218 |
scorp | +1.171 |
abs | +1.136 |
attributes | +1.133 |
Neg logit contributions | |
Kuala | -1.317 |
RM | -1.308 |
illi | -1.233 |
ngth | -1.233 |
avier | -1.185 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
RM | +0.217 |
Kuala | +0.217 |
illi | +0.200 |
ngth | +0.189 |
avier | +0.189 |
Neg logit contributions | |
nep | -0.301 |
attribute | -0.252 |
scorp | -0.249 |
attributes | -0.237 |
abs | -0.237 |
Token | ruby |
Token ID | 49137 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
nep | +1.105 |
attribute | +0.945 |
scorp | +0.904 |
abs | +0.876 |
attributes | +0.873 |
Neg logit contributions | |
Kuala | -1.237 |
RM | -1.223 |
ngth | -1.156 |
illi | -1.154 |
avier | -1.106 |
Token | [ |
Token ID | 685 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Kuala | +0.445 |
RM | +0.443 |
illi | +0.411 |
ngth | +0.410 |
avier | +0.387 |
Neg logit contributions | |
nep | -0.606 |
attribute | -0.532 |
scorp | -0.516 |
abs | -0.501 |
attributes | -0.501 |
Token | comment |
Token ID | 2912 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
nep | +1.566 |
attribute | +1.354 |
scorp | +1.320 |
abs | +1.277 |
attributes | +1.275 |
Neg logit contributions | |
Kuala | -1.208 |
RM | -1.203 |
illi | -1.115 |
ngth | -1.104 |
avier | -1.056 |
Token | on |
Token ID | 319 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
nep | +1.983 |
attribute | +1.680 |
scorp | +1.614 |
abs | +1.552 |
attributes | +1.551 |
Neg logit contributions | |
Kuala | -2.349 |
RM | -2.345 |
illi | -2.210 |
ngth | -2.208 |
avier | -2.112 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
Kuala | +0.095 |
RM | +0.093 |
illi | +0.087 |
ngth | +0.085 |
avier | +0.084 |
Neg logit contributions | |
nep | -0.100 |
attribute | -0.082 |
scorp | -0.081 |
abs | -0.077 |
attributes | -0.076 |
Token | Share |
Token ID | 8734 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
Kuala | +3.180 |
RM | +3.080 |
illi | +2.878 |
vell | +2.792 |
avier | +2.785 |
Neg logit contributions | |
nep | -3.088 |
scorp | -2.417 |
attribute | -2.361 |
abs | -2.247 |
attributes | -2.223 |
Token | this |
Token ID | 428 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
nep | +0.352 |
attribute | +0.297 |
scorp | +0.291 |
abs | +0.280 |
attributes | +0.278 |
Neg logit contributions | |
Kuala | -0.303 |
RM | -0.301 |
illi | -0.280 |
ngth | -0.275 |
avier | -0.267 |
Token | comment |
Token ID | 2912 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
nep | +2.094 |
attribute | +1.818 |
scorp | +1.768 |
abs | +1.711 |
attributes | +1.710 |
Neg logit contributions | |
Kuala | -1.639 |
RM | -1.634 |
illi | -1.517 |
ngth | -1.506 |
avier | -1.435 |
Token | on |
Token ID | 319 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
nep | +3.153 |
attribute | +2.795 |
scorp | +2.615 |
abs | +2.565 |
attributes | +2.561 |
Neg logit contributions | |
RM | -4.321 |
Kuala | -4.316 |
ngth | -4.203 |
illi | -4.095 |
avier | -3.890 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Kuala | +0.103 |
RM | +0.101 |
illi | +0.094 |
ngth | +0.091 |
avier | +0.090 |
Neg logit contributions | |
nep | -0.103 |
attribute | -0.085 |
scorp | -0.083 |
abs | -0.080 |
attributes | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Kuala | +0.821 |
RM | +0.821 |
ngth | +0.769 |
illi | +0.766 |
avier | +0.727 |
Neg logit contributions | |
nep | -0.927 |
attribute | -0.802 |
scorp | -0.778 |
abs | -0.753 |
attributes | -0.749 |
Token |
|
Token ID | 198 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
nep | +2.677 |
attribute | +2.358 |
scorp | +2.265 |
abs | +2.209 |
attributes | +2.205 |
Neg logit contributions | |
Kuala | -2.413 |
RM | -2.409 |
ngth | -2.284 |
illi | -2.254 |
avier | -2.136 |
Token | NY |
Token ID | 12805 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
nep | +2.346 |
attribute | +1.956 |
scorp | +1.854 |
abs | +1.796 |
attributes | +1.780 |
Neg logit contributions | |
Kuala | -3.361 |
RM | -3.255 |
ngth | -3.188 |
illi | -3.134 |
vell | -2.992 |
Token | , |
Token ID | 11 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
Kuala | +1.121 |
RM | +1.116 |
illi | +1.045 |
ngth | +1.042 |
avier | +0.990 |
Neg logit contributions | |
nep | -1.271 |
attribute | -1.105 |
scorp | -1.068 |
abs | -1.038 |
attributes | -1.036 |
Token | and |
Token ID | 290 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
nep | +0.243 |
attribute | +0.210 |
scorp | +0.202 |
abs | +0.196 |
attributes | +0.196 |
Neg logit contributions | |
Kuala | -0.241 |
RM | -0.240 |
ngth | -0.227 |
illi | -0.226 |
avier | -0.215 |
Token | big |
Token ID | 1263 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Kuala | +0.280 |
RM | +0.279 |
illi | +0.262 |
ngth | +0.262 |
avier | +0.250 |
Neg logit contributions | |
nep | -0.260 |
attribute | -0.222 |
scorp | -0.214 |
abs | -0.207 |
attributes | -0.206 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
RM | +1.432 |
Kuala | +1.431 |
illi | +1.328 |
ngth | +1.313 |
vell | +1.255 |
Neg logit contributions | |
nep | -1.732 |
attribute | -1.491 |
scorp | -1.449 |
abs | -1.393 |
attributes | -1.393 |
Token | box |
Token ID | 3091 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Kuala | +1.175 |
RM | +1.172 |
illi | +1.092 |
ngth | +1.089 |
avier | +1.044 |
Neg logit contributions | |
nep | -1.166 |
attribute | -0.992 |
scorp | -0.958 |
attributes | -0.923 |
abs | -0.921 |
Token | y |
Token ID | 88 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
RM | +0.962 |
Kuala | +0.960 |
illi | +0.888 |
ngth | +0.883 |
avier | +0.839 |
Neg logit contributions | |
nep | -1.336 |
attribute | -1.166 |
scorp | -1.132 |
abs | -1.096 |
attributes | -1.096 |
Token | speakers |
Token ID | 11636 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
nep | +0.820 |
attribute | +0.717 |
scorp | +0.694 |
abs | +0.674 |
attributes | +0.674 |
Neg logit contributions | |
Kuala | -0.655 |
RM | -0.653 |
illi | -0.608 |
ngth | -0.608 |
avier | -0.575 |
Token | , |
Token ID | 11 |
Feature activation | +4.65e-03 |
Pos logit contributions | |
Kuala | +0.734 |
RM | +0.733 |
illi | +0.683 |
ngth | +0.681 |
avier | +0.648 |
Neg logit contributions | |
nep | -0.843 |
attribute | -0.731 |
scorp | -0.707 |
abs | -0.684 |
attributes | -0.684 |
Token | look |
Token ID | 804 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
nep | +0.032 |
attribute | +0.027 |
scorp | +0.026 |
abs | +0.025 |
attributes | +0.025 |
Neg logit contributions | |
Kuala | -0.034 |
RM | -0.034 |
illi | -0.032 |
ngth | -0.032 |
avier | -0.031 |
Token | like |
Token ID | 588 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
nep | +0.612 |
attribute | +0.525 |
scorp | +0.506 |
abs | +0.489 |
attributes | +0.488 |
Neg logit contributions | |
Kuala | -0.635 |
RM | -0.633 |
illi | -0.596 |
ngth | -0.593 |
avier | -0.566 |
Token | something |
Token ID | 1223 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
nep | +1.184 |
attribute | +1.020 |
scorp | +0.985 |
abs | +0.958 |
attributes | +0.948 |
Neg logit contributions | |
RM | -1.207 |
Kuala | -1.202 |
illi | -1.139 |
ngth | -1.133 |
avier | -1.076 |
Token | a |
Token ID | 257 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
nep | +0.222 |
attribute | +0.190 |
scorp | +0.183 |
abs | +0.177 |
attributes | +0.177 |
Neg logit contributions | |
RM | -0.233 |
Kuala | -0.232 |
ngth | -0.219 |
illi | -0.219 |
avier | -0.208 |
Token | bleak |
Token ID | 30942 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
nep | +1.537 |
attribute | +1.321 |
scorp | +1.277 |
abs | +1.228 |
attributes | +1.223 |
Neg logit contributions | |
RM | -1.592 |
Kuala | -1.585 |
illi | -1.498 |
ngth | -1.496 |
avier | -1.421 |
Token | outlook |
Token ID | 19360 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
nep | +1.315 |
attribute | +1.126 |
scorp | +1.081 |
abs | +1.042 |
attributes | +1.039 |
Neg logit contributions | |
RM | -1.448 |
Kuala | -1.447 |
ngth | -1.366 |
illi | -1.365 |
avier | -1.298 |
Token | for |
Token ID | 329 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
nep | +0.591 |
attribute | +0.515 |
scorp | +0.497 |
attributes | +0.482 |
abs | +0.482 |
Neg logit contributions | |
Kuala | -0.504 |
RM | -0.504 |
illi | -0.471 |
ngth | -0.471 |
avier | -0.446 |
Token | a |
Token ID | 257 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
nep | +0.098 |
attribute | +0.084 |
scorp | +0.081 |
attributes | +0.079 |
abs | +0.079 |
Neg logit contributions | |
RM | -0.101 |
Kuala | -0.100 |
ngth | -0.095 |
illi | -0.095 |
vell | -0.090 |
Token | vulnerable |
Token ID | 8826 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
nep | +0.588 |
attribute | +0.508 |
scorp | +0.491 |
abs | +0.474 |
attributes | +0.474 |
Neg logit contributions | |
RM | -0.548 |
Kuala | -0.548 |
illi | -0.513 |
ngth | -0.512 |
avier | -0.486 |
Token | country |
Token ID | 1499 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
nep | +1.198 |
attribute | +1.044 |
scorp | +1.008 |
abs | +0.978 |
attributes | +0.973 |
Neg logit contributions | |
RM | -1.066 |
Kuala | -1.061 |
ngth | -1.007 |
illi | -1.002 |
avier | -0.946 |
Token | in |
Token ID | 287 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
nep | +0.604 |
attribute | +0.523 |
scorp | +0.504 |
abs | +0.489 |
attributes | +0.488 |
Neg logit contributions | |
RM | -0.567 |
Kuala | -0.567 |
illi | -0.532 |
ngth | -0.532 |
avier | -0.504 |
Token | the |
Token ID | 262 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
nep | +0.620 |
attribute | +0.530 |
scorp | +0.511 |
abs | +0.496 |
attributes | +0.493 |
Neg logit contributions | |
RM | -0.668 |
Kuala | -0.661 |
illi | -0.628 |
ngth | -0.627 |
avier | -0.596 |
Token | remote |
Token ID | 6569 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
Kuala | +0.289 |
RM | +0.287 |
illi | +0.268 |
ngth | +0.266 |
avier | +0.255 |
Neg logit contributions | |
nep | -0.312 |
attribute | -0.269 |
scorp | -0.260 |
abs | -0.251 |
attributes | -0.251 |
Token | Pacific |
Token ID | 8211 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Kuala | +0.583 |
RM | +0.576 |
illi | +0.536 |
ngth | +0.532 |
avier | +0.510 |
Neg logit contributions | |
nep | -0.643 |
attribute | -0.555 |
scorp | -0.538 |
attributes | -0.518 |
abs | -0.517 |
Token | Asia |
Token ID | 7229 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
nep | +0.716 |
attribute | +0.611 |
scorp | +0.588 |
abs | +0.567 |
attributes | +0.567 |
Neg logit contributions | |
Kuala | -0.772 |
RM | -0.771 |
illi | -0.725 |
ngth | -0.723 |
avier | -0.691 |
Token | and |
Token ID | 290 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
nep | +1.356 |
attribute | +1.167 |
scorp | +1.125 |
abs | +1.094 |
attributes | +1.086 |
Neg logit contributions | |
Kuala | -1.407 |
RM | -1.398 |
illi | -1.323 |
ngth | -1.319 |
avier | -1.257 |
Token | Europe |
Token ID | 2031 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
nep | +0.520 |
attribute | +0.444 |
scorp | +0.428 |
abs | +0.412 |
attributes | +0.412 |
Neg logit contributions | |
Kuala | -0.548 |
RM | -0.547 |
illi | -0.513 |
ngth | -0.512 |
avier | -0.489 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
nep | +0.093 |
attribute | +0.080 |
scorp | +0.077 |
abs | +0.074 |
attributes | +0.074 |
Neg logit contributions | |
Kuala | -0.092 |
RM | -0.091 |
illi | -0.086 |
ngth | -0.085 |
avier | -0.082 |
Token | between |
Token ID | 1022 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
nep | +1.300 |
attribute | +1.123 |
scorp | +1.082 |
abs | +1.051 |
attributes | +1.048 |
Neg logit contributions | |
RM | -1.258 |
Kuala | -1.252 |
ngth | -1.180 |
illi | -1.179 |
avier | -1.121 |
Token | East |
Token ID | 3687 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
Kuala | +0.084 |
RM | +0.084 |
illi | +0.079 |
ngth | +0.079 |
avier | +0.075 |
Neg logit contributions | |
nep | -0.078 |
attribute | -0.067 |
scorp | -0.064 |
abs | -0.062 |
attributes | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
nep | +0.715 |
attribute | +0.617 |
scorp | +0.594 |
abs | +0.576 |
attributes | +0.574 |
Neg logit contributions | |
Kuala | -0.699 |
RM | -0.698 |
illi | -0.657 |
ngth | -0.652 |
avier | -0.623 |
Token | West |
Token ID | 2688 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
nep | +1.994 |
attribute | +1.698 |
scorp | +1.609 |
abs | +1.571 |
attributes | +1.571 |
Neg logit contributions | |
RM | -2.348 |
Kuala | -2.326 |
illi | -2.231 |
ngth | -2.212 |
avier | -2.132 |
Token | , |
Token ID | 11 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
nep | +2.278 |
attribute | +1.975 |
scorp | +1.894 |
abs | +1.862 |
attributes | +1.847 |
Neg logit contributions | |
RM | -2.106 |
Kuala | -2.102 |
illi | -1.983 |
ngth | -1.968 |
avier | -1.891 |
Token | as |
Token ID | 355 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
Kuala | +0.622 |
RM | +0.619 |
illi | +0.577 |
ngth | +0.574 |
avier | +0.547 |
Neg logit contributions | |
nep | -0.697 |
attribute | -0.602 |
scorp | -0.583 |
attributes | -0.563 |
abs | -0.561 |
Token | natural |
Token ID | 3288 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
nep | +0.057 |
attribute | +0.049 |
scorp | +0.047 |
abs | +0.045 |
attributes | +0.045 |
Neg logit contributions | |
Kuala | -0.058 |
RM | -0.058 |
illi | -0.054 |
ngth | -0.054 |
avier | -0.052 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Kuala | +0.590 |
RM | +0.588 |
illi | +0.553 |
ngth | +0.551 |
avier | +0.527 |
Neg logit contributions | |
nep | -0.548 |
attribute | -0.467 |
scorp | -0.450 |
abs | -0.434 |
attributes | -0.434 |
Token | . |
Token ID | 13 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
Kuala | +0.780 |
RM | +0.778 |
illi | +0.727 |
ngth | +0.724 |
avier | +0.690 |
Neg logit contributions | |
nep | -0.865 |
attribute | -0.748 |
scorp | -0.724 |
abs | -0.699 |
attributes | -0.699 |
Token | This |
Token ID | 770 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
nep | +0.335 |
attribute | +0.293 |
scorp | +0.282 |
abs | +0.274 |
attributes | +0.273 |
Neg logit contributions | |
Kuala | -0.299 |
RM | -0.299 |
ngth | -0.280 |
illi | -0.280 |
avier | -0.266 |
Token | is |
Token ID | 318 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
nep | +0.329 |
attribute | +0.284 |
scorp | +0.273 |
abs | +0.265 |
attributes | +0.264 |
Neg logit contributions | |
Kuala | -0.328 |
RM | -0.328 |
illi | -0.308 |
ngth | -0.308 |
avier | -0.292 |
Token | about |
Token ID | 546 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
nep | +0.376 |
attribute | +0.322 |
scorp | +0.311 |
abs | +0.300 |
attributes | +0.299 |
Neg logit contributions | |
Kuala | -0.388 |
RM | -0.388 |
ngth | -0.365 |
illi | -0.365 |
avier | -0.347 |
Token | people |
Token ID | 661 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
nep | +1.534 |
attribute | +1.330 |
scorp | +1.280 |
abs | +1.247 |
attributes | +1.239 |
Neg logit contributions | |
RM | -1.671 |
Kuala | -1.663 |
ngth | -1.597 |
illi | -1.577 |
avier | -1.497 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
nep | +0.607 |
attribute | +0.533 |
scorp | +0.513 |
abs | +0.500 |
attributes | +0.499 |
Neg logit contributions | |
Kuala | -0.539 |
RM | -0.537 |
ngth | -0.504 |
illi | -0.502 |
avier | -0.476 |
Token | This |
Token ID | 770 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
Kuala | +0.823 |
RM | +0.820 |
illi | +0.763 |
ngth | +0.757 |
avier | +0.722 |
Neg logit contributions | |
nep | -0.955 |
attribute | -0.825 |
scorp | -0.800 |
abs | -0.773 |
attributes | -0.772 |
Token | is |
Token ID | 318 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
Kuala | +0.287 |
RM | +0.287 |
ngth | +0.270 |
illi | +0.270 |
avier | +0.256 |
Neg logit contributions | |
nep | -0.284 |
attribute | -0.246 |
scorp | -0.236 |
abs | -0.230 |
attributes | -0.228 |
Token | about |
Token ID | 546 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Kuala | +0.158 |
RM | +0.158 |
illi | +0.149 |
ngth | +0.148 |
avier | +0.142 |
Neg logit contributions | |
nep | -0.126 |
attribute | -0.106 |
scorp | -0.102 |
abs | -0.098 |
attributes | -0.098 |
Token | families |
Token ID | 4172 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
nep | +0.750 |
attribute | +0.646 |
scorp | +0.622 |
abs | +0.602 |
attributes | +0.602 |
Neg logit contributions | |
RM | -0.820 |
Kuala | -0.817 |
ngth | -0.778 |
illi | -0.772 |
avier | -0.735 |
Token | must |
Token ID | 1276 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
nep | +0.317 |
attribute | +0.272 |
scorp | +0.263 |
abs | +0.254 |
attributes | +0.254 |
Neg logit contributions | |
Kuala | -0.323 |
RM | -0.322 |
illi | -0.302 |
ngth | -0.302 |
avier | -0.288 |
Token | bring |
Token ID | 2222 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
nep | +1.251 |
attribute | +1.061 |
scorp | +1.018 |
abs | +0.980 |
attributes | +0.977 |
Neg logit contributions | |
Kuala | -1.513 |
RM | -1.513 |
illi | -1.425 |
ngth | -1.422 |
avier | -1.362 |
Token | down |
Token ID | 866 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
nep | +0.377 |
attribute | +0.324 |
scorp | +0.313 |
abs | +0.302 |
attributes | +0.302 |
Neg logit contributions | |
RM | -0.383 |
Kuala | -0.383 |
illi | -0.359 |
ngth | -0.359 |
avier | -0.343 |
Token | a |
Token ID | 257 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Kuala | +1.066 |
RM | +1.061 |
illi | +0.994 |
ngth | +0.988 |
avier | +0.943 |
Neg logit contributions | |
nep | -1.111 |
attribute | -0.955 |
scorp | -0.918 |
abs | -0.889 |
attributes | -0.888 |
Token | pilot |
Token ID | 8022 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Kuala | +1.082 |
RM | +1.073 |
illi | +1.008 |
ngth | +1.003 |
avier | +0.962 |
Neg logit contributions | |
nep | -0.999 |
attribute | -0.852 |
scorp | -0.812 |
attributes | -0.791 |
abs | -0.787 |
Token | named |
Token ID | 3706 |
Feature activation | -5.33e-04 |
Pos logit contributions | |
Kuala | +1.428 |
RM | +1.424 |
illi | +1.332 |
ngth | +1.323 |
avier | +1.264 |
Neg logit contributions | |
nep | -1.561 |
attribute | -1.347 |
scorp | -1.301 |
attributes | -1.258 |
abs | -1.257 |
Token | the |
Token ID | 262 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
RM | +0.003 |
Kuala | +0.003 |
ngth | +0.003 |
illi | +0.003 |
avier | +0.003 |
Neg logit contributions | |
nep | -0.004 |
attribute | -0.004 |
scorp | -0.004 |
abs | -0.004 |
attributes | -0.004 |
Token | Black |
Token ID | 2619 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
Kuala | +0.529 |
RM | +0.528 |
illi | +0.492 |
ngth | +0.491 |
avier | +0.467 |
Neg logit contributions | |
nep | -0.614 |
attribute | -0.533 |
scorp | -0.516 |
abs | -0.499 |
attributes | -0.499 |
Token | Baron |
Token ID | 21770 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
Kuala | +0.458 |
RM | +0.457 |
illi | +0.426 |
ngth | +0.425 |
avier | +0.404 |
Neg logit contributions | |
nep | -0.521 |
attribute | -0.452 |
scorp | -0.438 |
abs | -0.424 |
attributes | -0.423 |
Token | in |
Token ID | 287 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
Kuala | +0.498 |
RM | +0.496 |
illi | +0.463 |
ngth | +0.461 |
avier | +0.439 |
Neg logit contributions | |
nep | -0.579 |
attribute | -0.503 |
scorp | -0.487 |
abs | -0.471 |
attributes | -0.471 |
Token | an |
Token ID | 281 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Kuala | +0.217 |
RM | +0.217 |
illi | +0.204 |
ngth | +0.203 |
avier | +0.194 |
Neg logit contributions | |
nep | -0.202 |
attribute | -0.172 |
scorp | -0.166 |
abs | -0.160 |
attributes | -0.160 |
Token | - |
Token ID | 12 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Kuala | +0.325 |
RM | +0.324 |
illi | +0.300 |
ngth | +0.299 |
avier | +0.282 |
Neg logit contributions | |
nep | -0.443 |
attribute | -0.389 |
scorp | -0.378 |
abs | -0.367 |
attributes | -0.367 |
Token | wealth |
Token ID | 14298 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
RM | +1.696 |
Kuala | +1.684 |
illi | +1.560 |
ngth | +1.547 |
avier | +1.465 |
Neg logit contributions | |
nep | -2.619 |
attribute | -2.312 |
scorp | -2.248 |
attributes | -2.182 |
abs | -2.178 |
Token | y |
Token ID | 88 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
nep | +0.753 |
attribute | +0.665 |
scorp | +0.644 |
abs | +0.626 |
attributes | +0.626 |
Neg logit contributions | |
Kuala | -0.576 |
RM | -0.573 |
illi | -0.530 |
ngth | -0.528 |
avier | -0.499 |
Token | , |
Token ID | 11 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
nep | +0.497 |
attribute | +0.429 |
scorp | +0.414 |
abs | +0.400 |
attributes | +0.400 |
Neg logit contributions | |
Kuala | -0.473 |
RM | -0.472 |
illi | -0.442 |
ngth | -0.441 |
avier | -0.420 |
Token | climate |
Token ID | 4258 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
Kuala | +1.668 |
RM | +1.659 |
illi | +1.544 |
ngth | +1.531 |
avier | +1.471 |
Neg logit contributions | |
nep | -1.822 |
attribute | -1.562 |
scorp | -1.515 |
attributes | -1.462 |
abs | -1.452 |
Token | change |
Token ID | 1487 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
RM | +2.093 |
Kuala | +2.086 |
illi | +1.946 |
ngth | +1.928 |
avier | +1.853 |
Neg logit contributions | |
nep | -2.370 |
attribute | -2.034 |
scorp | -1.968 |
attributes | -1.903 |
abs | -1.891 |
Token | - |
Token ID | 12 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
RM | +2.944 |
Kuala | +2.911 |
illi | +2.731 |
ngth | +2.687 |
avier | +2.616 |
Neg logit contributions | |
nep | -3.159 |
attribute | -2.688 |
scorp | -2.606 |
attributes | -2.509 |
cowork | -2.503 |
Token | den |
Token ID | 6559 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
RM | +1.208 |
Kuala | +1.204 |
illi | +1.109 |
ngth | +1.098 |
avier | +1.037 |
Neg logit contributions | |
nep | -1.931 |
attribute | -1.705 |
scorp | -1.661 |
attributes | -1.612 |
abs | -1.609 |
Token | ying |
Token ID | 1112 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
Kuala | +1.618 |
RM | +1.614 |
illi | +1.508 |
ngth | +1.502 |
avier | +1.430 |
Neg logit contributions | |
nep | -1.834 |
attribute | -1.586 |
scorp | -1.536 |
abs | -1.485 |
attributes | -1.484 |
Token | , |
Token ID | 11 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Kuala | +0.638 |
RM | +0.635 |
illi | +0.591 |
ngth | +0.587 |
avier | +0.561 |
Neg logit contributions | |
nep | -0.741 |
attribute | -0.640 |
scorp | -0.620 |
attributes | -0.599 |
abs | -0.597 |
Token | union |
Token ID | 6441 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Kuala | +2.277 |
RM | +2.259 |
illi | +2.100 |
ngth | +2.070 |
avier | +2.002 |
Neg logit contributions | |
nep | -2.628 |
attribute | -2.247 |
scorp | -2.189 |
attributes | -2.111 |
abs | -2.092 |
Token | of |
Token ID | 286 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
nep | +0.445 |
attribute | +0.387 |
scorp | +0.373 |
abs | +0.363 |
attributes | +0.362 |
Neg logit contributions | |
RM | -0.396 |
Kuala | -0.395 |
ngth | -0.369 |
illi | -0.368 |
avier | -0.351 |
Token | your |
Token ID | 534 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Kuala | +0.666 |
RM | +0.666 |
illi | +0.628 |
ngth | +0.628 |
avier | +0.602 |
Neg logit contributions | |
nep | -0.519 |
attribute | -0.435 |
scorp | -0.418 |
abs | -0.401 |
attributes | -0.400 |
Token | house |
Token ID | 2156 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
Kuala | +0.946 |
RM | +0.939 |
illi | +0.881 |
ngth | +0.875 |
avier | +0.842 |
Neg logit contributions | |
nep | -0.888 |
attribute | -0.756 |
scorp | -0.730 |
attributes | -0.703 |
abs | -0.701 |
Token | and |
Token ID | 290 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Kuala | +0.215 |
RM | +0.214 |
illi | +0.200 |
ngth | +0.199 |
avier | +0.190 |
Neg logit contributions | |
nep | -0.245 |
attribute | -0.212 |
scorp | -0.205 |
abs | -0.198 |
attributes | -0.198 |
Token | arrest |
Token ID | 3251 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Kuala | +1.209 |
RM | +1.200 |
illi | +1.124 |
ngth | +1.112 |
vell | +1.077 |
Neg logit contributions | |
nep | -1.026 |
attribute | -0.850 |
scorp | -0.826 |
attributes | -0.795 |
abs | -0.784 |
Token | you |
Token ID | 345 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Kuala | +2.271 |
RM | +2.248 |
illi | +2.138 |
ngth | +2.107 |
avier | +2.052 |
Neg logit contributions | |
nep | -1.693 |
attribute | -1.394 |
scorp | -1.345 |
attributes | -1.274 |
abs | -1.270 |
Token | in |
Token ID | 287 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Kuala | +1.248 |
RM | +1.246 |
illi | +1.164 |
ngth | +1.148 |
avier | +1.098 |
Neg logit contributions | |
nep | -1.503 |
attribute | -1.291 |
scorp | -1.264 |
attributes | -1.212 |
abs | -1.200 |
Token | front |
Token ID | 2166 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Kuala | +1.350 |
RM | +1.333 |
illi | +1.253 |
ngth | +1.239 |
vell | +1.200 |
Neg logit contributions | |
nep | -1.198 |
attribute | -1.011 |
scorp | -0.975 |
attributes | -0.938 |
abs | -0.930 |
Token | of |
Token ID | 286 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Kuala | +1.087 |
RM | +1.062 |
illi | +0.990 |
ngth | +0.961 |
avier | +0.937 |
Neg logit contributions | |
nep | -1.554 |
attribute | -1.310 |
scorp | -1.298 |
attributes | -1.240 |
cowork | -1.236 |
Token | your |
Token ID | 534 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
nep | +0.696 |
attribute | +0.590 |
scorp | +0.568 |
abs | +0.548 |
attributes | +0.543 |
Neg logit contributions | |
RM | -0.876 |
Kuala | -0.870 |
ngth | -0.831 |
illi | -0.822 |
avier | -0.791 |
Token | children |
Token ID | 1751 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
Kuala | +0.319 |
RM | +0.318 |
illi | +0.299 |
ngth | +0.299 |
avier | +0.286 |
Neg logit contributions | |
nep | -0.289 |
attribute | -0.246 |
scorp | -0.237 |
abs | -0.229 |
attributes | -0.228 |
Token | in |
Token ID | 287 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Kuala | +0.995 |
RM | +0.988 |
illi | +0.921 |
ngth | +0.914 |
avier | +0.883 |
Neg logit contributions | |
nep | -0.973 |
attribute | -0.823 |
scorp | -0.806 |
abs | -0.769 |
attributes | -0.763 |
Token | many |
Token ID | 867 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
Kuala | +0.857 |
RM | +0.847 |
illi | +0.798 |
ngth | +0.793 |
avier | +0.762 |
Neg logit contributions | |
nep | -0.783 |
attribute | -0.663 |
scorp | -0.641 |
attributes | -0.616 |
abs | -0.615 |
Token | cases |
Token ID | 2663 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Kuala | +0.523 |
RM | +0.518 |
illi | +0.484 |
ngth | +0.481 |
avier | +0.461 |
Neg logit contributions | |
nep | -0.538 |
attribute | -0.461 |
scorp | -0.446 |
attributes | -0.429 |
abs | -0.429 |
Token | suggests |
Token ID | 5644 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
Kuala | +2.166 |
RM | +2.159 |
illi | +2.023 |
ngth | +1.996 |
avier | +1.940 |
Neg logit contributions | |
nep | -2.195 |
attribute | -1.837 |
scorp | -1.811 |
cowork | -1.711 |
abs | -1.702 |
Token | that |
Token ID | 326 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
Kuala | +0.409 |
RM | +0.407 |
illi | +0.382 |
ngth | +0.380 |
avier | +0.364 |
Neg logit contributions | |
nep | -0.398 |
attribute | -0.341 |
scorp | -0.329 |
abs | -0.317 |
attributes | -0.316 |
Token | local |
Token ID | 1957 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
nep | +0.338 |
attribute | +0.288 |
scorp | +0.277 |
abs | +0.267 |
attributes | +0.267 |
Neg logit contributions | |
RM | -0.375 |
Kuala | -0.375 |
illi | -0.353 |
ngth | -0.353 |
avier | -0.337 |
Token | currencies |
Token ID | 19247 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
Kuala | +1.564 |
RM | +1.559 |
illi | +1.462 |
ngth | +1.444 |
avier | +1.401 |
Neg logit contributions | |
nep | -1.231 |
attribute | -1.026 |
scorp | -0.995 |
abs | -0.944 |
attributes | -0.937 |
Token | could |
Token ID | 714 |
Feature activation | -5.60e-04 |
Pos logit contributions | |
nep | +0.090 |
attribute | +0.076 |
scorp | +0.073 |
abs | +0.070 |
attributes | +0.070 |
Neg logit contributions | |
Kuala | -0.100 |
RM | -0.100 |
illi | -0.094 |
ngth | -0.094 |
avier | -0.090 |
Token | form |
Token ID | 1296 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
Kuala | +0.004 |
RM | +0.004 |
illi | +0.004 |
ngth | +0.004 |
avier | +0.004 |
Neg logit contributions | |
nep | -0.004 |
attribute | -0.003 |
scorp | -0.003 |
attributes | -0.003 |
abs | -0.003 |
Token | part |
Token ID | 636 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
nep | +0.415 |
attribute | +0.356 |
scorp | +0.342 |
attributes | +0.331 |
abs | +0.331 |
Neg logit contributions | |
Kuala | -0.434 |
RM | -0.434 |
illi | -0.408 |
ngth | -0.407 |
avier | -0.389 |
Token | of |
Token ID | 286 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Kuala | +0.855 |
RM | +0.855 |
illi | +0.778 |
ngth | +0.761 |
avier | +0.745 |
Neg logit contributions | |
nep | -1.214 |
attribute | -1.022 |
scorp | -1.022 |
abs | -0.964 |
cowork | -0.963 |
Token | . |
Token ID | 13 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
Kuala | +0.610 |
RM | +0.609 |
illi | +0.568 |
ngth | +0.567 |
avier | +0.539 |
Neg logit contributions | |
nep | -0.693 |
attribute | -0.601 |
scorp | -0.581 |
abs | -0.563 |
attributes | -0.563 |
Token | " |
Token ID | 366 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
nep | +0.453 |
attribute | +0.398 |
scorp | +0.384 |
attributes | +0.373 |
abs | +0.371 |
Neg logit contributions | |
Kuala | -0.396 |
RM | -0.395 |
ngth | -0.375 |
illi | -0.372 |
avier | -0.352 |
Token | I |
Token ID | 40 |
Feature activation | -6.66e-03 |
Pos logit contributions | |
RM | +0.430 |
Kuala | +0.428 |
illi | +0.400 |
ngth | +0.395 |
avier | +0.381 |
Neg logit contributions | |
nep | -0.460 |
attribute | -0.394 |
scorp | -0.382 |
abs | -0.368 |
attributes | -0.368 |
Token | mean |
Token ID | 1612 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Kuala | +0.050 |
RM | +0.050 |
illi | +0.047 |
ngth | +0.047 |
avier | +0.045 |
Neg logit contributions | |
nep | -0.045 |
attribute | -0.037 |
scorp | -0.036 |
attributes | -0.035 |
abs | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Kuala | +1.330 |
RM | +1.326 |
illi | +1.235 |
ngth | +1.229 |
avier | +1.171 |
Neg logit contributions | |
nep | -1.543 |
attribute | -1.337 |
scorp | -1.294 |
attributes | -1.253 |
abs | -1.252 |
Token | I |
Token ID | 314 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Kuala | +1.230 |
RM | +1.221 |
illi | +1.140 |
ngth | +1.131 |
avier | +1.089 |
Neg logit contributions | |
nep | -1.263 |
attribute | -1.079 |
scorp | -1.043 |
attributes | -1.007 |
abs | -1.005 |
Token | know |
Token ID | 760 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Kuala | +1.122 |
RM | +1.111 |
illi | +1.051 |
ngth | +1.036 |
avier | +1.005 |
Neg logit contributions | |
nep | -0.989 |
attribute | -0.812 |
scorp | -0.794 |
attributes | -0.764 |
abs | -0.757 |
Token | what |
Token ID | 644 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
Kuala | +1.018 |
RM | +1.014 |
illi | +0.947 |
ngth | +0.943 |
avier | +0.902 |
Neg logit contributions | |
nep | -1.069 |
attribute | -0.919 |
scorp | -0.888 |
abs | -0.858 |
attributes | -0.857 |
Token | the |
Token ID | 262 |
Feature activation | +6.09e-03 |
Pos logit contributions | |
Kuala | +0.522 |
RM | +0.522 |
illi | +0.490 |
ngth | +0.489 |
avier | +0.466 |
Neg logit contributions | |
nep | -0.514 |
attribute | -0.441 |
scorp | -0.425 |
abs | -0.410 |
attributes | -0.410 |
Token | next |
Token ID | 1306 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
nep | +0.041 |
attribute | +0.035 |
scorp | +0.033 |
abs | +0.032 |
attributes | +0.032 |
Neg logit contributions | |
RM | -0.046 |
Kuala | -0.046 |
ngth | -0.044 |
illi | -0.043 |
avier | -0.041 |
Token | Nirvana |
Token ID | 49923 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Kuala | +0.861 |
RM | +0.860 |
illi | +0.806 |
ngth | +0.804 |
avier | +0.765 |
Neg logit contributions | |
nep | -0.917 |
attribute | -0.792 |
scorp | -0.765 |
abs | -0.739 |
attributes | -0.739 |
Token | electricity |
Token ID | 8744 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Kuala | +0.215 |
RM | +0.214 |
illi | +0.201 |
ngth | +0.200 |
avier | +0.192 |
Neg logit contributions | |
nep | -0.209 |
attribute | -0.179 |
scorp | -0.173 |
abs | -0.166 |
attributes | -0.166 |
Token | from |
Token ID | 422 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Kuala | +1.094 |
RM | +1.088 |
illi | +1.010 |
ngth | +1.001 |
avier | +0.954 |
Neg logit contributions | |
nep | -1.411 |
attribute | -1.226 |
scorp | -1.195 |
abs | -1.153 |
attributes | -1.149 |
Token | these |
Token ID | 777 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Kuala | +1.487 |
RM | +1.474 |
illi | +1.380 |
ngth | +1.367 |
avier | +1.313 |
Neg logit contributions | |
nep | -1.487 |
attribute | -1.271 |
scorp | -1.232 |
abs | -1.185 |
attributes | -1.182 |
Token | power |
Token ID | 1176 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
Kuala | +1.587 |
RM | +1.568 |
illi | +1.473 |
ngth | +1.454 |
vell | +1.401 |
Neg logit contributions | |
nep | -1.536 |
attribute | -1.306 |
scorp | -1.269 |
abs | -1.215 |
attributes | -1.204 |
Token | plants |
Token ID | 6134 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Kuala | +0.555 |
RM | +0.554 |
illi | +0.520 |
ngth | +0.518 |
avier | +0.496 |
Neg logit contributions | |
nep | -0.514 |
attribute | -0.437 |
scorp | -0.422 |
abs | -0.406 |
attributes | -0.404 |
Token | will |
Token ID | 481 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
Kuala | +1.157 |
RM | +1.152 |
illi | +1.084 |
ngth | +1.074 |
avier | +1.032 |
Neg logit contributions | |
nep | -1.146 |
attribute | -0.974 |
scorp | -0.947 |
abs | -0.906 |
attributes | -0.903 |
Token | cost |
Token ID | 1575 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Kuala | +0.530 |
RM | +0.528 |
illi | +0.493 |
ngth | +0.491 |
avier | +0.468 |
Neg logit contributions | |
nep | -0.604 |
attribute | -0.522 |
scorp | -0.506 |
attributes | -0.489 |
abs | -0.489 |
Token | 18 |
Token ID | 1248 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
nep | +1.004 |
attribute | +0.869 |
scorp | +0.837 |
attributes | +0.812 |
abs | +0.812 |
Neg logit contributions | |
Kuala | -0.918 |
RM | -0.918 |
ngth | -0.862 |
illi | -0.860 |
avier | -0.817 |
Token | to |
Token ID | 284 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
RM | +0.454 |
Kuala | +0.453 |
illi | +0.428 |
ngth | +0.425 |
avier | +0.413 |
Neg logit contributions | |
nep | -0.281 |
attribute | -0.229 |
scorp | -0.218 |
attributes | -0.206 |
abs | -0.205 |
Token | 50 |
Token ID | 2026 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
nep | +1.849 |
attribute | +1.633 |
scorp | +1.583 |
abs | +1.541 |
attributes | +1.540 |
Neg logit contributions | |
Kuala | -1.277 |
RM | -1.277 |
ngth | -1.184 |
illi | -1.180 |
avier | -1.109 |
Token | percent |
Token ID | 1411 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Kuala | +0.749 |
RM | +0.747 |
illi | +0.710 |
ngth | +0.706 |
avier | +0.685 |
Neg logit contributions | |
nep | -0.398 |
attribute | -0.317 |
scorp | -0.300 |
attributes | -0.282 |
abs | -0.281 |
Token | s |
Token ID | 82 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Kuala | +0.247 |
RM | +0.246 |
illi | +0.228 |
ngth | +0.228 |
avier | +0.215 |
Neg logit contributions | |
nep | -0.350 |
attribute | -0.308 |
scorp | -0.299 |
abs | -0.291 |
attributes | -0.291 |
Token | )} |
Token ID | 38165 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
nep | +1.226 |
attribute | +1.107 |
scorp | +1.071 |
abs | +1.056 |
attributes | +1.052 |
Neg logit contributions | |
Kuala | -0.598 |
RM | -0.586 |
illi | -0.536 |
ngth | -0.532 |
avier | -0.493 |
Token | 51 |
Token ID | 6885 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Kuala | +0.380 |
RM | +0.379 |
ngth | +0.353 |
illi | +0.352 |
avier | +0.332 |
Neg logit contributions | |
nep | -0.502 |
attribute | -0.440 |
scorp | -0.426 |
abs | -0.414 |
attributes | -0.413 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Kuala | +1.144 |
RM | +1.142 |
illi | +1.061 |
ngth | +1.056 |
avier | +1.003 |
Neg logit contributions | |
nep | -1.412 |
attribute | -1.230 |
scorp | -1.191 |
attributes | -1.154 |
abs | -1.153 |
Token | N |
Token ID | 399 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Kuala | +0.646 |
RM | +0.644 |
illi | +0.597 |
ngth | +0.595 |
avier | +0.562 |
Neg logit contributions | |
nep | -0.883 |
attribute | -0.775 |
scorp | -0.752 |
abs | -0.730 |
attributes | -0.729 |
Token | d |
Token ID | 67 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
RM | +1.713 |
Kuala | +1.700 |
illi | +1.561 |
ngth | +1.523 |
vell | +1.458 |
Neg logit contributions | |
nep | -2.923 |
attribute | -2.586 |
scorp | -2.527 |
attributes | -2.456 |
abs | -2.447 |
Token | 4 |
Token ID | 19 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
RM | +2.289 |
Kuala | +2.193 |
illi | +1.953 |
ngth | +1.862 |
vell | +1.821 |
Neg logit contributions | |
nep | -5.279 |
attribute | -4.685 |
scorp | -4.657 |
abs | -4.502 |
attributes | -4.491 |
Token | + |
Token ID | 10 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Kuala | +0.885 |
RM | +0.883 |
illi | +0.818 |
ngth | +0.815 |
avier | +0.771 |
Neg logit contributions | |
nep | -1.204 |
attribute | -1.056 |
scorp | -1.024 |
abs | -0.994 |
attributes | -0.993 |
Token | { |
Token ID | 1391 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Kuala | +1.083 |
RM | +1.080 |
illi | +0.995 |
ngth | +0.990 |
avier | +0.936 |
Neg logit contributions | |
nep | -1.592 |
attribute | -1.400 |
scorp | -1.362 |
abs | -1.321 |
attributes | -1.321 |
Token | ( |
Token ID | 7 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
nep | +2.630 |
attribute | +2.343 |
scorp | +2.251 |
abs | +2.218 |
attributes | +2.204 |
Neg logit contributions | |
Kuala | -2.028 |
RM | -1.994 |
ngth | -1.904 |
illi | -1.872 |
avier | -1.759 |
Token | 10 |
Token ID | 940 |
Feature activation | -6.79e-03 |
Pos logit contributions | |
nep | +1.263 |
attribute | +1.124 |
scorp | +1.090 |
abs | +1.066 |
attributes | +1.064 |
Neg logit contributions | |
Kuala | -0.745 |
RM | -0.737 |
ngth | -0.680 |
illi | -0.678 |
avier | -0.632 |
Token |
|
Token ID | 198 |
Feature activation | -6.17e-03 |
Pos logit contributions | |
nep | +1.214 |
attribute | +1.053 |
scorp | +1.021 |
attributes | +0.987 |
abs | +0.986 |
Neg logit contributions | |
RM | -1.105 |
Kuala | -1.100 |
ngth | -1.044 |
illi | -1.040 |
avier | -0.992 |
Token |
|
Token ID | 198 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
Kuala | +0.038 |
RM | +0.038 |
illi | +0.035 |
ngth | +0.034 |
avier | +0.033 |
Neg logit contributions | |
nep | -0.051 |
attribute | -0.043 |
scorp | -0.043 |
abs | -0.041 |
attributes | -0.041 |
Token | 4 |
Token ID | 19 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Kuala | +0.221 |
RM | +0.219 |
ngth | +0.202 |
illi | +0.201 |
avier | +0.187 |
Neg logit contributions | |
nep | -0.381 |
attribute | -0.339 |
scorp | -0.330 |
abs | -0.322 |
attributes | -0.321 |
Token | ) |
Token ID | 8 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
RM | +1.238 |
Kuala | +1.231 |
illi | +1.114 |
avier | +1.062 |
ngth | +1.062 |
Neg logit contributions | |
nep | -2.117 |
attribute | -1.800 |
scorp | -1.784 |
abs | -1.704 |
attributes | -1.704 |
Token | Sv |
Token ID | 44343 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Kuala | +1.064 |
RM | +1.062 |
illi | +0.990 |
ngth | +0.987 |
avier | +0.938 |
Neg logit contributions | |
nep | -1.256 |
attribute | -1.091 |
scorp | -1.057 |
abs | -1.023 |
attributes | -1.022 |
Token | arna |
Token ID | 28610 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
RM | +1.491 |
Kuala | +1.491 |
illi | +1.387 |
ngth | +1.372 |
avier | +1.301 |
Neg logit contributions | |
nep | -2.070 |
attribute | -1.813 |
scorp | -1.766 |
attributes | -1.709 |
abs | -1.708 |
Token | Ak |
Token ID | 9084 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Kuala | +3.751 |
RM | +3.694 |
illi | +3.465 |
ngth | +3.450 |
vell | +3.308 |
Neg logit contributions | |
nep | -3.965 |
attribute | -3.408 |
scorp | -3.312 |
attributes | -3.187 |
abs | -3.183 |
Token | arsh |
Token ID | 5406 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
nep | +1.466 |
attribute | +1.288 |
scorp | +1.253 |
abs | +1.216 |
attributes | +1.212 |
Neg logit contributions | |
Kuala | -1.068 |
RM | -1.064 |
ngth | -0.979 |
illi | -0.968 |
avier | -0.922 |
Token | ana |
Token ID | 2271 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
Kuala | +0.727 |
RM | +0.725 |
illi | +0.672 |
ngth | +0.671 |
avier | +0.636 |
Neg logit contributions | |
nep | -0.934 |
attribute | -0.817 |
scorp | -0.791 |
abs | -0.767 |
attributes | -0.767 |
Token | Bh |
Token ID | 16581 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Kuala | +3.476 |
RM | +3.434 |
illi | +3.207 |
ngth | +3.192 |
vell | +3.054 |
Neg logit contributions | |
nep | -3.709 |
attribute | -3.186 |
scorp | -3.096 |
abs | -2.979 |
attributes | -2.975 |
Token | air |
Token ID | 958 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
Kuala | +1.810 |
RM | +1.804 |
illi | +1.674 |
ngth | +1.653 |
avier | +1.571 |
Neg logit contributions | |
nep | -2.831 |
attribute | -2.500 |
scorp | -2.441 |
attributes | -2.365 |
abs | -2.360 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
RM | +0.287 |
Kuala | +0.287 |
illi | +0.263 |
avier | +0.249 |
ngth | +0.248 |
Neg logit contributions | |
nep | -0.397 |
attribute | -0.331 |
scorp | -0.329 |
cowork | -0.312 |
attributes | -0.312 |
Token | Can |
Token ID | 6090 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Kuala | +0.073 |
RM | +0.073 |
illi | +0.068 |
ngth | +0.068 |
avier | +0.064 |
Neg logit contributions | |
nep | -0.086 |
attribute | -0.075 |
scorp | -0.073 |
abs | -0.070 |
attributes | -0.070 |
Token | you |
Token ID | 345 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Kuala | +1.277 |
RM | +1.273 |
illi | +1.205 |
ngth | +1.201 |
avier | +1.157 |
Neg logit contributions | |
nep | -0.928 |
attribute | -0.770 |
scorp | -0.739 |
abs | -0.705 |
attributes | -0.705 |
Token | explain |
Token ID | 4727 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
Kuala | +1.383 |
RM | +1.376 |
illi | +1.292 |
ngth | +1.277 |
avier | +1.231 |
Neg logit contributions | |
nep | -1.343 |
attribute | -1.123 |
scorp | -1.105 |
attributes | -1.055 |
abs | -1.048 |
Token | what |
Token ID | 644 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Kuala | +1.495 |
RM | +1.492 |
illi | +1.400 |
ngth | +1.397 |
avier | +1.334 |
Neg logit contributions | |
nep | -1.438 |
attribute | -1.230 |
scorp | -1.185 |
abs | -1.143 |
attributes | -1.142 |
Token | is |
Token ID | 318 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
Kuala | +1.406 |
RM | +1.402 |
illi | +1.314 |
ngth | +1.307 |
avier | +1.249 |
Neg logit contributions | |
nep | -1.422 |
attribute | -1.219 |
scorp | -1.181 |
abs | -1.137 |
attributes | -1.135 |
Token | the |
Token ID | 262 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Kuala | +4.143 |
RM | +4.140 |
illi | +3.864 |
ngth | +3.831 |
avier | +3.666 |
Neg logit contributions | |
nep | -3.903 |
attribute | -3.316 |
scorp | -3.239 |
abs | -3.103 |
attributes | -3.101 |
Token | cause |
Token ID | 2728 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Kuala | +1.732 |
RM | +1.728 |
illi | +1.620 |
ngth | +1.603 |
avier | +1.538 |
Neg logit contributions | |
nep | -1.621 |
attribute | -1.375 |
scorp | -1.334 |
attributes | -1.281 |
abs | -1.281 |
Token | of |
Token ID | 286 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Kuala | +1.943 |
RM | +1.933 |
illi | +1.805 |
ngth | +1.802 |
avier | +1.717 |
Neg logit contributions | |
nep | -2.262 |
attribute | -1.975 |
scorp | -1.900 |
abs | -1.850 |
attributes | -1.845 |
Token | the |
Token ID | 262 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
Kuala | +1.490 |
RM | +1.487 |
illi | +1.399 |
ngth | +1.396 |
avier | +1.336 |
Neg logit contributions | |
nep | -1.331 |
attribute | -1.131 |
scorp | -1.088 |
abs | -1.048 |
attributes | -1.047 |
Token | increase |
Token ID | 2620 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
Kuala | +0.445 |
RM | +0.443 |
illi | +0.415 |
ngth | +0.412 |
avier | +0.395 |
Neg logit contributions | |
nep | -0.452 |
attribute | -0.388 |
scorp | -0.375 |
attributes | -0.362 |
abs | -0.362 |
Token | Because |
Token ID | 8128 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Kuala | +0.455 |
RM | +0.455 |
illi | +0.424 |
ngth | +0.422 |
avier | +0.402 |
Neg logit contributions | |
nep | -0.524 |
attribute | -0.454 |
scorp | -0.440 |
abs | -0.425 |
attributes | -0.425 |
Token | if |
Token ID | 611 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
Kuala | +1.427 |
RM | +1.417 |
illi | +1.323 |
ngth | +1.310 |
avier | +1.268 |
Neg logit contributions | |
nep | -1.472 |
attribute | -1.251 |
scorp | -1.219 |
attributes | -1.167 |
abs | -1.160 |
Token | it |
Token ID | 340 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
Kuala | +1.757 |
RM | +1.750 |
illi | +1.644 |
ngth | +1.636 |
avier | +1.581 |
Neg logit contributions | |
nep | -1.460 |
attribute | -1.225 |
scorp | -1.180 |
attributes | -1.129 |
abs | -1.125 |
Token | was |
Token ID | 373 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
Kuala | +0.321 |
RM | +0.321 |
illi | +0.300 |
ngth | +0.299 |
avier | +0.285 |
Neg logit contributions | |
nep | -0.337 |
attribute | -0.291 |
scorp | -0.281 |
abs | -0.272 |
attributes | -0.271 |
Token | that |
Token ID | 326 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
Kuala | +0.657 |
RM | +0.656 |
illi | +0.612 |
ngth | +0.609 |
avier | +0.584 |
Neg logit contributions | |
nep | -0.673 |
attribute | -0.577 |
scorp | -0.558 |
attributes | -0.538 |
abs | -0.536 |
Token | bad |
Token ID | 2089 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Kuala | +2.911 |
RM | +2.903 |
illi | +2.698 |
ngth | +2.677 |
avier | +2.622 |
Neg logit contributions | |
nep | -2.504 |
attribute | -2.079 |
scorp | -2.015 |
attributes | -1.928 |
abs | -1.898 |
Token | , |
Token ID | 11 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
Kuala | +3.256 |
RM | +3.250 |
illi | +2.993 |
ngth | +2.940 |
avier | +2.826 |
Neg logit contributions | |
nep | -4.216 |
attribute | -3.617 |
scorp | -3.563 |
attributes | -3.404 |
abs | -3.391 |
Token | it |
Token ID | 340 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
Kuala | +0.686 |
RM | +0.684 |
illi | +0.641 |
ngth | +0.638 |
avier | +0.611 |
Neg logit contributions | |
nep | -0.671 |
attribute | -0.573 |
scorp | -0.554 |
attributes | -0.533 |
abs | -0.532 |
Token | wouldn |
Token ID | 3636 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
nep | +0.371 |
attribute | +0.322 |
scorp | +0.309 |
abs | +0.302 |
attributes | +0.300 |
Neg logit contributions | |
Kuala | -0.367 |
RM | -0.365 |
ngth | -0.343 |
illi | -0.341 |
avier | -0.324 |
Token | � |
Token ID | 447 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
nep | +1.829 |
attribute | +1.594 |
scorp | +1.533 |
abs | +1.491 |
attributes | +1.488 |
Neg logit contributions | |
Kuala | -1.672 |
RM | -1.664 |
ngth | -1.561 |
illi | -1.556 |
avier | -1.477 |
Token | � |
Token ID | 247 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
nep | +0.230 |
attribute | +0.203 |
scorp | +0.197 |
abs | +0.191 |
attributes | +0.191 |
Neg logit contributions | |
RM | -0.150 |
Kuala | -0.150 |
illi | -0.138 |
ngth | -0.137 |
avier | -0.130 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
nep | +0.218 |
attribute | +0.190 |
scorp | +0.183 |
abs | +0.178 |
attributes | +0.177 |
Neg logit contributions | |
Kuala | -0.190 |
RM | -0.189 |
illi | -0.177 |
ngth | -0.177 |
avier | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | -9.93e-02 |
Pos logit contributions | |
RM | +0.730 |
Kuala | +0.726 |
illi | +0.666 |
avier | +0.633 |
vell | +0.627 |
Neg logit contributions | |
nep | -1.052 |
attribute | -0.869 |
scorp | -0.867 |
cowork | -0.822 |
attributes | -0.819 |
Token | Never |
Token ID | 12295 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
RM | +0.676 |
Kuala | +0.666 |
illi | +0.625 |
ngth | +0.612 |
avier | +0.595 |
Neg logit contributions | |
nep | -0.756 |
attribute | -0.647 |
scorp | -0.631 |
attributes | -0.606 |
abs | -0.604 |
Token | mind |
Token ID | 2000 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
nep | +1.563 |
attribute | +1.298 |
scorp | +1.206 |
abs | +1.167 |
attributes | +1.160 |
Neg logit contributions | |
Kuala | -2.639 |
RM | -2.628 |
illi | -2.513 |
ngth | -2.501 |
avier | -2.391 |
Token | the |
Token ID | 262 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
nep | +0.260 |
attribute | +0.223 |
scorp | +0.215 |
abs | +0.208 |
attributes | +0.208 |
Neg logit contributions | |
RM | -0.265 |
Kuala | -0.265 |
illi | -0.248 |
ngth | -0.248 |
avier | -0.236 |
Token | fact |
Token ID | 1109 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Kuala | +1.805 |
RM | +1.790 |
illi | +1.652 |
ngth | +1.643 |
avier | +1.567 |
Neg logit contributions | |
nep | -2.396 |
attribute | -2.074 |
scorp | -2.024 |
attributes | -1.950 |
abs | -1.946 |
Token | that |
Token ID | 326 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Kuala | +3.605 |
RM | +3.579 |
illi | +3.348 |
ngth | +3.327 |
avier | +3.178 |
Neg logit contributions | |
nep | -4.040 |
attribute | -3.486 |
scorp | -3.381 |
attributes | -3.256 |
abs | -3.244 |
Token | Team |
Token ID | 4816 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Kuala | +2.280 |
RM | +2.246 |
illi | +2.109 |
ngth | +2.089 |
avier | +2.009 |
Neg logit contributions | |
nep | -2.441 |
attribute | -2.093 |
scorp | -2.027 |
attributes | -1.950 |
abs | -1.938 |
Token | Canada |
Token ID | 3340 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
RM | +1.534 |
Kuala | +1.533 |
illi | +1.431 |
ngth | +1.431 |
avier | +1.363 |
Neg logit contributions | |
nep | -1.604 |
attribute | -1.387 |
scorp | -1.338 |
abs | -1.305 |
attributes | -1.294 |
Token | also |
Token ID | 635 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Kuala | +0.208 |
RM | +0.207 |
illi | +0.194 |
ngth | +0.193 |
avier | +0.185 |
Neg logit contributions | |
nep | -0.219 |
attribute | -0.188 |
scorp | -0.182 |
abs | -0.176 |
attributes | -0.175 |
Token | left |
Token ID | 1364 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Kuala | +0.748 |
RM | +0.743 |
illi | +0.695 |
ngth | +0.687 |
avier | +0.663 |
Neg logit contributions | |
nep | -0.812 |
attribute | -0.693 |
scorp | -0.674 |
abs | -0.645 |
attributes | -0.645 |