Token | read |
Token ID | 1100 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
ioned | +2.698 |
inatory | +2.588 |
enance | +2.416 |
eenth | +2.416 |
alities | +2.405 |
Neg logit contributions | |
iler | -2.395 |
ilers | -2.101 |
fter | -2.075 |
ghan | -1.970 |
llor | -1.863 |
Token | : |
Token ID | 25 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
iler | +1.740 |
fter | +1.505 |
ilers | +1.499 |
ghan | +1.417 |
lder | +1.340 |
Neg logit contributions | |
ioned | -2.146 |
inatory | -2.086 |
eenth | -1.961 |
atural | -1.940 |
alities | -1.932 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
iler | +0.308 |
ilers | +0.271 |
fter | +0.268 |
ghan | +0.255 |
lder | +0.242 |
Neg logit contributions | |
ioned | -0.332 |
inatory | -0.321 |
eenth | -0.301 |
enance | -0.297 |
alities | -0.296 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ioned | +0.832 |
inatory | +0.795 |
enance | +0.755 |
eenth | +0.753 |
alities | +0.735 |
Neg logit contributions | |
iler | -0.885 |
ilers | -0.794 |
fter | -0.766 |
ghan | -0.733 |
�� | -0.709 |
Token | " |
Token ID | 1 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ioned | +0.855 |
inatory | +0.820 |
eenth | +0.747 |
enance | +0.740 |
alities | +0.735 |
Neg logit contributions | |
iler | -1.275 |
ilers | -1.151 |
fter | -1.139 |
ghan | -1.095 |
lder | -1.051 |
Token | Bar |
Token ID | 10374 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
ioned | +1.258 |
inatory | +1.213 |
eenth | +1.122 |
enance | +1.114 |
alities | +1.106 |
Neg logit contributions | |
iler | -1.428 |
ilers | -1.273 |
fter | -1.256 |
ghan | -1.201 |
lder | -1.143 |
Token | ack |
Token ID | 441 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
ioned | +10.640 |
inatory | +9.815 |
alities | +9.243 |
tons | +9.139 |
eenth | +9.135 |
Neg logit contributions | |
iler | -12.640 |
fter | -11.340 |
ilers | -11.285 |
ghan | -10.499 |
llor | -10.090 |
Token | Obama |
Token ID | 2486 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
ioned | +3.472 |
inatory | +3.359 |
eenth | +3.098 |
enance | +3.087 |
alities | +3.066 |
Neg logit contributions | |
iler | -3.522 |
ilers | -3.134 |
fter | -3.096 |
ghan | -2.933 |
lder | -2.774 |
Token | would |
Token ID | 561 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
iler | +0.025 |
ilers | +0.022 |
fter | +0.022 |
ghan | +0.021 |
lder | +0.020 |
Neg logit contributions | |
ioned | -0.024 |
inatory | -0.023 |
eenth | -0.022 |
enance | -0.021 |
alities | -0.021 |
Token | be |
Token ID | 307 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
ioned | +1.872 |
inatory | +1.797 |
enance | +1.686 |
eenth | +1.680 |
alities | +1.668 |
Neg logit contributions | |
iler | -1.414 |
ilers | -1.231 |
fter | -1.204 |
ghan | -1.141 |
llor | -1.079 |
Token | the |
Token ID | 262 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ioned | +3.253 |
inatory | +3.142 |
enance | +2.973 |
eenth | +2.961 |
alities | +2.915 |
Neg logit contributions | |
iler | -2.727 |
ilers | -2.404 |
fter | -2.353 |
ghan | -2.218 |
lder | -2.101 |
Token | General |
Token ID | 3611 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ioned | +1.826 |
inatory | +1.772 |
eenth | +1.657 |
enance | +1.647 |
alities | +1.640 |
Neg logit contributions | |
iler | -1.505 |
ilers | -1.315 |
fter | -1.293 |
ghan | -1.223 |
lder | -1.154 |
Token | to |
Token ID | 284 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
ioned | +2.263 |
inatory | +2.193 |
eenth | +2.045 |
enance | +2.037 |
alities | +2.024 |
Neg logit contributions | |
iler | -1.957 |
ilers | -1.716 |
fter | -1.690 |
ghan | -1.603 |
lder | -1.513 |
Token | pr |
Token ID | 778 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
iler | +0.706 |
ilers | +0.614 |
fter | +0.604 |
ghan | +0.572 |
lder | +0.537 |
Neg logit contributions | |
ioned | -0.907 |
inatory | -0.879 |
eenth | -0.822 |
enance | -0.819 |
alities | -0.815 |
Token | or |
Token ID | 273 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
ioned | +7.289 |
inatory | +7.134 |
ally | +6.591 |
enance | +6.407 |
alities | +6.406 |
Neg logit contributions | |
iler | -10.994 |
ilers | -10.315 |
fter | -9.936 |
ghan | -9.883 |
lder | -9.086 |
Token | ogue |
Token ID | 5119 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
ioned | +2.582 |
inatory | +2.336 |
atural | +2.051 |
alities | +2.043 |
eenth | +1.976 |
Neg logit contributions | |
iler | -5.929 |
ilers | -5.515 |
fter | -5.377 |
ghan | -5.118 |
llor | -5.034 |
Token | Parliament |
Token ID | 8411 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
ioned | +2.601 |
inatory | +2.520 |
eenth | +2.350 |
enance | +2.347 |
alities | +2.323 |
Neg logit contributions | |
iler | -2.290 |
ilers | -2.005 |
fter | -1.983 |
ghan | -1.877 |
lder | -1.769 |
Token | — |
Token ID | 960 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
ioned | +11.264 |
inatory | +10.915 |
eenth | +10.110 |
alities | +10.033 |
ally | +10.018 |
Neg logit contributions | |
iler | -11.840 |
ilers | -10.589 |
fter | -10.536 |
ghan | -9.936 |
lder | -9.542 |
Token | a |
Token ID | 64 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
ioned | +4.718 |
inatory | +4.595 |
enance | +4.227 |
atural | +4.202 |
eenth | +4.201 |
Neg logit contributions | |
iler | -5.068 |
ilers | -4.527 |
fter | -4.399 |
ghan | -4.235 |
lder | -4.044 |
Token | measure |
Token ID | 3953 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ioned | +0.791 |
inatory | +0.768 |
eenth | +0.721 |
enance | +0.716 |
alities | +0.713 |
Neg logit contributions | |
iler | -0.596 |
ilers | -0.516 |
fter | -0.508 |
ghan | -0.479 |
lder | -0.449 |
Token | that |
Token ID | 326 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
ioned | +2.631 |
inatory | +2.535 |
enance | +2.394 |
eenth | +2.382 |
alities | +2.373 |
Neg logit contributions | |
iler | -2.132 |
ilers | -1.869 |
fter | -1.825 |
ghan | -1.733 |
lder | -1.628 |
Token | itself |
Token ID | 2346 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ioned | +3.421 |
inatory | +3.300 |
enance | +3.092 |
eenth | +3.087 |
alities | +3.069 |
Neg logit contributions | |
iler | -3.006 |
ilers | -2.653 |
fter | -2.597 |
ghan | -2.465 |
lder | -2.324 |
Token | supporter |
Token ID | 15525 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
ioned | +0.064 |
inatory | +0.062 |
eenth | +0.060 |
ally | +0.060 |
alities | +0.059 |
Neg logit contributions | |
iler | -0.061 |
ilers | -0.054 |
fter | -0.050 |
ghan | -0.048 |
lder | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
iler | +5.404 |
ilers | +4.724 |
fter | +4.662 |
ghan | +4.434 |
lder | +4.179 |
Neg logit contributions | |
ioned | -6.210 |
inatory | -6.029 |
eenth | -5.621 |
enance | -5.591 |
alities | -5.559 |
Token | Powered |
Token ID | 45090 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
iler | +1.590 |
ilers | +1.353 |
fter | +1.344 |
ghan | +1.272 |
lder | +1.195 |
Neg logit contributions | |
ioned | -2.297 |
inatory | -2.236 |
eenth | -2.088 |
atural | -2.069 |
alities | -2.068 |
Token | by |
Token ID | 416 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
iler | +2.163 |
ilers | +1.897 |
fter | +1.870 |
ghan | +1.772 |
lder | +1.676 |
Neg logit contributions | |
ioned | -2.438 |
inatory | -2.360 |
eenth | -2.202 |
enance | -2.189 |
alities | -2.177 |
Token | Press |
Token ID | 4332 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
iler | +2.122 |
ilers | +1.836 |
fter | +1.808 |
ghan | +1.695 |
lder | +1.592 |
Neg logit contributions | |
ioned | -2.885 |
inatory | -2.807 |
eenth | -2.620 |
atural | -2.617 |
alities | -2.606 |
Token | Pat |
Token ID | 12130 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
ioned | +3.351 |
inatory | +3.223 |
eenth | +2.913 |
bugs | +2.826 |
enance | +2.794 |
Neg logit contributions | |
iler | -5.723 |
ilers | -5.298 |
fter | -5.267 |
ghan | -5.084 |
lder | -4.917 |
Token | ron |
Token ID | 1313 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
ioned | +7.186 |
inatory | +6.558 |
enance | +6.015 |
eenth | +5.896 |
inators | +5.872 |
Neg logit contributions | |
iler | -16.142 |
ilers | -15.093 |
fter | -15.065 |
ghan | -14.279 |
llor | -14.163 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ioned | +5.864 |
inatory | +5.480 |
eenth | +5.291 |
atural | +5.197 |
enance | +5.134 |
Neg logit contributions | |
iler | -10.347 |
ilers | -9.405 |
fter | -9.269 |
ghan | -9.139 |
lder | -8.746 |
Token | Washington |
Token ID | 17402 |
Feature activation | +7.83e+00 |
Pos logit contributions | |
ioned | +1.237 |
inatory | +1.194 |
eenth | +1.107 |
enance | +1.098 |
alities | +1.091 |
Neg logit contributions | |
iler | -1.343 |
ilers | -1.195 |
fter | -1.176 |
ghan | -1.122 |
lder | -1.069 |
Token | Post |
Token ID | 2947 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
ioned | +6.464 |
inatory | +6.256 |
eenth | +5.806 |
enance | +5.771 |
alities | +5.722 |
Neg logit contributions | |
iler | -6.440 |
ilers | -5.729 |
fter | -5.578 |
ghan | -5.275 |
llor | -5.051 |
Token | columnist |
Token ID | 22309 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ioned | +3.070 |
inatory | +2.959 |
eenth | +2.766 |
enance | +2.736 |
atural | +2.722 |
Neg logit contributions | |
iler | -2.959 |
ilers | -2.614 |
fter | -2.579 |
ghan | -2.454 |
lder | -2.331 |
Token | common |
Token ID | 2219 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
iler | +0.380 |
ilers | +0.328 |
fter | +0.323 |
ghan | +0.305 |
lder | +0.286 |
Neg logit contributions | |
ioned | -0.514 |
inatory | -0.500 |
eenth | -0.469 |
enance | -0.466 |
alities | -0.464 |
Token | way |
Token ID | 835 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
ioned | +2.769 |
inatory | +2.686 |
eenth | +2.527 |
alities | +2.513 |
enance | +2.509 |
Neg logit contributions | |
iler | -2.089 |
ilers | -1.827 |
fter | -1.785 |
ghan | -1.688 |
llor | -1.580 |
Token | to |
Token ID | 284 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
iler | +3.082 |
ilers | +2.621 |
fter | +2.569 |
ghan | +2.410 |
lder | +2.329 |
Neg logit contributions | |
ioned | -4.388 |
inatory | -4.318 |
enance | -4.049 |
atural | -4.039 |
eenth | -4.011 |
Token | power |
Token ID | 1176 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
iler | +0.488 |
ilers | +0.417 |
fter | +0.409 |
ghan | +0.384 |
llor | +0.357 |
Neg logit contributions | |
ioned | -0.748 |
inatory | -0.729 |
eenth | -0.686 |
enance | -0.680 |
alities | -0.679 |
Token | door |
Token ID | 3420 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
iler | +0.379 |
ilers | +0.331 |
fter | +0.327 |
ghan | +0.310 |
lder | +0.295 |
Neg logit contributions | |
ioned | -0.423 |
inatory | -0.411 |
eenth | -0.382 |
enance | -0.380 |
atural | -0.379 |
Token | bell |
Token ID | 7923 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
ioned | +4.977 |
inatory | +4.816 |
alities | +4.453 |
eenth | +4.447 |
tons | +4.358 |
Neg logit contributions | |
iler | -5.411 |
fter | -4.822 |
ilers | -4.798 |
ghan | -4.564 |
llor | -4.356 |
Token | s |
Token ID | 82 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
inatory | +8.769 |
ioned | +8.761 |
bells | +8.361 |
eenth | +7.915 |
tons | +7.889 |
Neg logit contributions | |
iler | -13.887 |
fter | -12.518 |
ilers | -12.469 |
ghan | -12.275 |
lde | -11.642 |
Token | and |
Token ID | 290 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
ioned | +4.434 |
inatory | +4.260 |
eenth | +3.990 |
enance | +3.965 |
alities | +3.911 |
Neg logit contributions | |
iler | -5.021 |
ilers | -4.492 |
fter | -4.429 |
ghan | -4.244 |
llor | -4.059 |
Token | tele |
Token ID | 5735 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
ioned | +4.254 |
inatory | +4.144 |
eenth | +3.855 |
enance | +3.836 |
alities | +3.833 |
Neg logit contributions | |
iler | -4.134 |
ilers | -3.655 |
fter | -3.609 |
ghan | -3.475 |
llor | -3.265 |
Token | phones |
Token ID | 9708 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
ioned | +2.083 |
inatory | +1.997 |
eenth | +1.773 |
alities | +1.753 |
atural | +1.743 |
Neg logit contributions | |
iler | -3.752 |
fter | -3.396 |
ilers | -3.395 |
ghan | -3.262 |
lder | -3.132 |
Token | before |
Token ID | 878 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ioned | +1.963 |
inatory | +1.896 |
eenth | +1.771 |
enance | +1.756 |
alities | +1.746 |
Neg logit contributions | |
iler | -1.913 |
ilers | -1.690 |
fter | -1.668 |
ghan | -1.588 |
lder | -1.504 |
Token | GOP |
Token ID | 6796 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ioned | +3.363 |
inatory | +3.228 |
enance | +3.014 |
eenth | +2.991 |
alities | +2.968 |
Neg logit contributions | |
iler | -3.451 |
ilers | -3.073 |
fter | -3.021 |
ghan | -2.889 |
llor | -2.725 |
Token | officials |
Token ID | 2828 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
ioned | +1.803 |
inatory | +1.731 |
eenth | +1.587 |
enance | +1.572 |
alities | +1.561 |
Neg logit contributions | |
iler | -2.451 |
ilers | -2.205 |
fter | -2.180 |
ghan | -2.095 |
lder | -2.001 |
Token | are |
Token ID | 389 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
iler | +0.348 |
ilers | +0.300 |
fter | +0.296 |
ghan | +0.279 |
lder | +0.261 |
Neg logit contributions | |
ioned | -0.472 |
inatory | -0.459 |
eenth | -0.431 |
enance | -0.428 |
alities | -0.426 |
Token | trying |
Token ID | 2111 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
ioned | +0.801 |
inatory | +0.777 |
eenth | +0.728 |
enance | +0.724 |
alities | +0.719 |
Neg logit contributions | |
iler | -0.657 |
ilers | -0.573 |
fter | -0.564 |
ghan | -0.534 |
lder | -0.503 |
Token | to |
Token ID | 284 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ioned | +3.996 |
inatory | +3.870 |
eenth | +3.603 |
enance | +3.587 |
alities | +3.565 |
Neg logit contributions | |
iler | -3.467 |
ilers | -3.030 |
fter | -2.988 |
ghan | -2.819 |
lder | -2.662 |
Token | ram |
Token ID | 15770 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
ioned | +1.035 |
inatory | +1.005 |
eenth | +0.942 |
enance | +0.934 |
alities | +0.933 |
Neg logit contributions | |
iler | -0.771 |
ilers | -0.667 |
fter | -0.659 |
ghan | -0.622 |
lder | -0.581 |
Token | through |
Token ID | 832 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
ioned | +10.497 |
inatory | +10.071 |
enance | +9.527 |
eenth | +9.266 |
ogether | +9.237 |
Neg logit contributions | |
iler | -12.406 |
ilers | -11.361 |
fter | -11.022 |
ghan | -10.431 |
llor | -10.049 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ioned | +3.041 |
inatory | +2.957 |
enance | +2.749 |
eenth | +2.744 |
alities | +2.723 |
Neg logit contributions | |
iler | -2.813 |
ilers | -2.483 |
fter | -2.438 |
ghan | -2.318 |
llor | -2.186 |
Token | ridiculous |
Token ID | 11441 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
ioned | +1.653 |
inatory | +1.609 |
eenth | +1.505 |
enance | +1.498 |
alities | +1.491 |
Neg logit contributions | |
iler | -1.298 |
ilers | -1.137 |
fter | -1.113 |
ghan | -1.049 |
llor | -0.986 |
Token | and |
Token ID | 290 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
ioned | +4.869 |
inatory | +4.708 |
eenth | +4.397 |
alities | +4.397 |
enance | +4.396 |
Neg logit contributions | |
iler | -4.118 |
ilers | -3.699 |
fter | -3.564 |
ghan | -3.354 |
llor | -3.197 |
Token | unpopular |
Token ID | 24166 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
ioned | +2.889 |
inatory | +2.814 |
eenth | +2.634 |
enance | +2.621 |
alities | +2.607 |
Neg logit contributions | |
iler | -2.323 |
ilers | -2.032 |
fter | -1.994 |
ghan | -1.890 |
llor | -1.786 |
Token | I |
Token ID | 314 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
ioned | +0.135 |
inatory | +0.131 |
eenth | +0.122 |
enance | +0.121 |
alities | +0.120 |
Neg logit contributions | |
iler | -0.131 |
ilers | -0.115 |
fter | -0.113 |
ghan | -0.108 |
lder | -0.103 |
Token | have |
Token ID | 423 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
iler | +2.098 |
ilers | +1.776 |
fter | +1.748 |
ghan | +1.649 |
lder | +1.559 |
Neg logit contributions | |
ioned | -3.130 |
inatory | -3.065 |
eenth | -2.886 |
enance | -2.866 |
alities | -2.855 |
Token | never |
Token ID | 1239 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
iler | +2.501 |
ilers | +2.139 |
fter | +2.120 |
ghan | +2.001 |
lder | +1.897 |
Neg logit contributions | |
ioned | -3.440 |
inatory | -3.355 |
eenth | -3.156 |
enance | -3.114 |
atural | -3.104 |
Token | stood |
Token ID | 6204 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
iler | +0.880 |
ilers | +0.757 |
fter | +0.749 |
ghan | +0.706 |
lder | +0.667 |
Neg logit contributions | |
ioned | -1.169 |
inatory | -1.138 |
eenth | -1.068 |
enance | -1.058 |
atural | -1.055 |
Token | for |
Token ID | 329 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
ioned | +5.760 |
inatory | +5.443 |
enance | +5.114 |
eenth | +5.084 |
alities | +5.051 |
Neg logit contributions | |
iler | -5.732 |
ilers | -5.089 |
fter | -4.967 |
ghan | -4.810 |
lder | -4.501 |
Token | Parliament |
Token ID | 8411 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
ioned | +3.898 |
inatory | +3.750 |
enance | +3.497 |
eenth | +3.472 |
alities | +3.451 |
Neg logit contributions | |
iler | -3.909 |
ilers | -3.477 |
fter | -3.424 |
ghan | -3.287 |
lder | -3.064 |
Token | . |
Token ID | 13 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
ioned | +10.634 |
inatory | +10.017 |
enance | +9.235 |
ally | +9.217 |
alities | +9.165 |
Neg logit contributions | |
iler | -11.983 |
ilers | -10.853 |
fter | -10.769 |
ghan | -10.307 |
lder | -9.550 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
ioned | +2.673 |
inatory | +2.584 |
eenth | +2.404 |
enance | +2.381 |
alities | +2.365 |
Neg logit contributions | |
iler | -2.718 |
ilers | -2.408 |
fter | -2.381 |
ghan | -2.263 |
lder | -2.146 |
Token | Earlier |
Token ID | 13689 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
ioned | +0.544 |
inatory | +0.525 |
eenth | +0.487 |
enance | +0.483 |
alities | +0.480 |
Neg logit contributions | |
iler | -0.584 |
ilers | -0.519 |
fter | -0.512 |
ghan | -0.489 |
lder | -0.465 |
Token | today |
Token ID | 1909 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
iler | +0.634 |
ilers | +0.558 |
fter | +0.550 |
ghan | +0.522 |
lder | +0.495 |
Neg logit contributions | |
ioned | -0.673 |
inatory | -0.651 |
enance | -0.606 |
eenth | -0.605 |
atural | -0.599 |
Token | , |
Token ID | 11 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
iler | +0.720 |
ilers | +0.631 |
fter | +0.630 |
ghan | +0.601 |
lder | +0.566 |
Neg logit contributions | |
ioned | -0.738 |
inatory | -0.716 |
eenth | -0.660 |
enance | -0.657 |
alities | -0.655 |
Token | time |
Token ID | 640 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
iler | +0.132 |
ilers | +0.117 |
fter | +0.115 |
ghan | +0.110 |
lder | +0.104 |
Neg logit contributions | |
ioned | -0.132 |
inatory | -0.128 |
eenth | -0.119 |
enance | -0.118 |
alities | -0.118 |
Token | and |
Token ID | 290 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
ioned | +0.931 |
inatory | +0.904 |
eenth | +0.843 |
enance | +0.836 |
alities | +0.834 |
Neg logit contributions | |
iler | -0.808 |
ilers | -0.707 |
fter | -0.697 |
ghan | -0.662 |
lder | -0.624 |
Token | attention |
Token ID | 3241 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
ioned | +3.228 |
inatory | +3.051 |
enance | +2.904 |
eenth | +2.854 |
alities | +2.803 |
Neg logit contributions | |
iler | -3.495 |
ilers | -3.141 |
fter | -3.098 |
ghan | -2.918 |
llor | -2.860 |
Token | to |
Token ID | 284 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
iler | +0.685 |
ilers | +0.590 |
fter | +0.582 |
ghan | +0.552 |
lder | +0.514 |
Neg logit contributions | |
ioned | -0.891 |
inatory | -0.872 |
eenth | -0.814 |
alities | -0.809 |
atural | -0.804 |
Token | the |
Token ID | 262 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
ioned | +1.330 |
inatory | +1.289 |
eenth | +1.205 |
enance | +1.197 |
alities | +1.190 |
Neg logit contributions | |
iler | -1.147 |
ilers | -1.003 |
fter | -0.989 |
ghan | -0.938 |
lder | -0.886 |
Token | bell |
Token ID | 8966 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
ioned | +0.566 |
inatory | +0.548 |
eenth | +0.511 |
enance | +0.507 |
alities | +0.504 |
Neg logit contributions | |
iler | -0.526 |
ilers | -0.462 |
fter | -0.456 |
ghan | -0.434 |
lder | -0.411 |
Token | es |
Token ID | 274 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ioned | +11.169 |
inatory | +10.895 |
bugs | +10.386 |
atural | +10.322 |
eenth | +10.260 |
Neg logit contributions | |
iler | -10.818 |
fter | -9.565 |
ilers | -9.514 |
ghan | -9.254 |
llor | -8.665 |
Token | of |
Token ID | 286 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
ioned | +1.778 |
inatory | +1.724 |
eenth | +1.613 |
enance | +1.602 |
alities | +1.594 |
Neg logit contributions | |
iler | -1.496 |
ilers | -1.306 |
fter | -1.286 |
ghan | -1.219 |
lder | -1.150 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ioned | +2.187 |
inatory | +2.118 |
eenth | +1.981 |
enance | +1.967 |
alities | +1.955 |
Neg logit contributions | |
iler | -1.919 |
ilers | -1.680 |
fter | -1.658 |
ghan | -1.572 |
lder | -1.484 |
Token | evening |
Token ID | 6180 |
Feature activation | +7.12e+00 |
Pos logit contributions | |
iler | +0.089 |
ilers | +0.079 |
fter | +0.077 |
ghan | +0.074 |
lder | +0.070 |
Neg logit contributions | |
ioned | -0.094 |
inatory | -0.091 |
eenth | -0.084 |
enance | -0.084 |
alities | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ioned | +6.024 |
inatory | +5.767 |
eenth | +5.456 |
enance | +5.378 |
alities | +5.290 |
Neg logit contributions | |
iler | -5.733 |
ilers | -5.105 |
fter | -4.963 |
ghan | -4.756 |
lder | -4.452 |
Token | ( |
Token ID | 357 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ioned | +1.178 |
inatory | +1.141 |
eenth | +1.065 |
enance | +1.057 |
alities | +1.052 |
Neg logit contributions | |
iler | -1.061 |
ilers | -0.931 |
fter | -0.918 |
ghan | -0.872 |
lder | -0.825 |
Token | at |
Token ID | 265 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
ioned | +0.252 |
inatory | +0.244 |
eenth | +0.228 |
enance | +0.226 |
alities | +0.225 |
Neg logit contributions | |
iler | -0.235 |
ilers | -0.206 |
fter | -0.204 |
ghan | -0.193 |
lder | -0.183 |
Token | the |
Token ID | 262 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ioned | +3.489 |
inatory | +3.399 |
eenth | +3.173 |
enance | +3.134 |
atural | +3.125 |
Neg logit contributions | |
iler | -3.108 |
ilers | -2.741 |
fter | -2.702 |
ghan | -2.571 |
llor | -2.414 |
Token | time |
Token ID | 640 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
iler | +1.423 |
ilers | +1.237 |
fter | +1.224 |
ghan | +1.153 |
lder | +1.097 |
Neg logit contributions | |
ioned | -1.686 |
inatory | -1.635 |
eenth | -1.528 |
enance | -1.521 |
alities | -1.510 |
Token | called |
Token ID | 1444 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
ioned | +0.088 |
inatory | +0.086 |
eenth | +0.081 |
enance | +0.080 |
alities | +0.080 |
Neg logit contributions | |
iler | -0.068 |
ilers | -0.059 |
fter | -0.058 |
ghan | -0.055 |
lder | -0.051 |
Token | 1992 |
Token ID | 9768 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
ioned | +0.763 |
inatory | +0.738 |
eenth | +0.687 |
enance | +0.681 |
alities | +0.678 |
Neg logit contributions | |
iler | -0.753 |
ilers | -0.664 |
fter | -0.656 |
ghan | -0.624 |
lder | -0.593 |
Token | KD |
Token ID | 43943 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ioned | +11.147 |
inatory | +10.898 |
eenth | +10.126 |
ally | +10.101 |
atural | +10.017 |
Neg logit contributions | |
iler | -10.318 |
ilers | -9.189 |
fter | -8.851 |
ghan | -8.474 |
llor | -8.159 |
Token | ) |
Token ID | 8 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
iler | +1.099 |
ilers | +0.947 |
fter | +0.935 |
ghan | +0.882 |
lder | +0.832 |
Neg logit contributions | |
ioned | -1.387 |
inatory | -1.347 |
eenth | -1.259 |
enance | -1.257 |
alities | -1.251 |
Token | and |
Token ID | 290 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
iler | +0.609 |
ilers | +0.534 |
fter | +0.527 |
ghan | +0.499 |
lder | +0.473 |
Neg logit contributions | |
ioned | -0.663 |
inatory | -0.641 |
eenth | -0.599 |
enance | -0.595 |
alities | -0.591 |
Token | comet |
Token ID | 31733 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
ioned | +1.468 |
inatory | +1.416 |
eenth | +1.309 |
enance | +1.302 |
alities | +1.292 |
Neg logit contributions | |
iler | -1.550 |
ilers | -1.384 |
fter | -1.360 |
ghan | -1.303 |
lder | -1.230 |
Token | 107 |
Token ID | 16226 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
ioned | +0.902 |
inatory | +0.876 |
eenth | +0.821 |
enance | +0.816 |
alities | +0.812 |
Neg logit contributions | |
iler | -0.706 |
ilers | -0.613 |
fter | -0.603 |
ghan | -0.570 |
lder | -0.536 |
Token | January |
Token ID | 3269 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
iler | +1.643 |
ilers | +1.453 |
fter | +1.436 |
ghan | +1.371 |
lder | +1.305 |
Neg logit contributions | |
ioned | -1.593 |
inatory | -1.543 |
eenth | -1.431 |
enance | -1.419 |
atural | -1.408 |
Token | . |
Token ID | 13 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
ioned | +1.098 |
inatory | +1.063 |
eenth | +0.992 |
enance | +0.987 |
alities | +0.981 |
Neg logit contributions | |
iler | -1.012 |
ilers | -0.892 |
fter | -0.877 |
ghan | -0.833 |
lder | -0.790 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
iler | +0.705 |
ilers | +0.612 |
fter | +0.604 |
ghan | +0.577 |
lder | +0.542 |
Neg logit contributions | |
ioned | -0.846 |
inatory | -0.820 |
eenth | -0.767 |
enance | -0.765 |
atural | -0.758 |
Token |
|
Token ID | 198 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
ioned | +0.973 |
inatory | +0.926 |
eenth | +0.878 |
enance | +0.874 |
alities | +0.863 |
Neg logit contributions | |
iler | -1.057 |
ilers | -0.951 |
fter | -0.916 |
ghan | -0.875 |
�� | -0.866 |
Token | Par |
Token ID | 10044 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
ioned | +0.679 |
inatory | +0.653 |
eenth | +0.600 |
enance | +0.595 |
alities | +0.591 |
Neg logit contributions | |
iler | -0.881 |
ilers | -0.790 |
fter | -0.781 |
ghan | -0.749 |
lder | -0.716 |
Token | liament |
Token ID | 5130 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
ioned | +7.255 |
inatory | +6.861 |
alities | +6.360 |
atural | +6.275 |
ally | +6.244 |
Neg logit contributions | |
iler | -8.683 |
ilers | -7.787 |
fter | -7.657 |
ghan | -7.180 |
lder | -7.043 |
Token | Hill |
Token ID | 3327 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
ioned | +10.195 |
inatory | +9.777 |
alities | +8.956 |
ally | +8.840 |
inators | +8.822 |
Neg logit contributions | |
iler | -11.993 |
ilers | -10.891 |
fter | -10.482 |
ghan | -10.111 |
lder | -9.503 |
Token | on |
Token ID | 319 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ioned | +6.202 |
inatory | +5.921 |
alities | +5.492 |
eenth | +5.479 |
enance | +5.444 |
Neg logit contributions | |
iler | -6.758 |
ilers | -6.070 |
fter | -5.873 |
ghan | -5.639 |
llor | -5.465 |
Token | Wed |
Token ID | 3300 |
Feature activation | +7.75e+00 |
Pos logit contributions | |
ioned | +1.355 |
inatory | +1.308 |
eenth | +1.206 |
enance | +1.198 |
alities | +1.189 |
Neg logit contributions | |
iler | -1.591 |
ilers | -1.420 |
fter | -1.403 |
ghan | -1.343 |
lder | -1.281 |
Token | nes |
Token ID | 2516 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
ioned | +5.618 |
inatory | +5.340 |
eenth | +5.036 |
alities | +4.877 |
enance | +4.850 |
Neg logit contributions | |
iler | -7.006 |
ilers | -6.259 |
fter | -6.180 |
ghan | -5.954 |
llor | -5.746 |
Token | days |
Token ID | 12545 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ioned | +1.982 |
inatory | +1.870 |
eenth | +1.665 |
enance | +1.635 |
alities | +1.624 |
Neg logit contributions | |
iler | -4.352 |
ilers | -3.984 |
fter | -3.943 |
ghan | -3.815 |
lder | -3.680 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
ioned | +0.388 |
inatory | +0.376 |
eenth | +0.351 |
enance | +0.348 |
alities | +0.346 |
Neg logit contributions | |
iler | -0.342 |
ilers | -0.298 |
fter | -0.295 |
ghan | -0.281 |
lder | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ioned | +0.178 |
inatory | +0.173 |
eenth | +0.160 |
enance | +0.159 |
alities | +0.159 |
Neg logit contributions | |
iler | -0.165 |
ilers | -0.145 |
fter | -0.143 |
ghan | -0.136 |
lder | -0.129 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ioned | +1.236 |
inatory | +1.173 |
eenth | +1.110 |
enance | +1.105 |
bugs | +1.089 |
Neg logit contributions | |
iler | -1.308 |
ilers | -1.177 |
fter | -1.137 |
ghan | -1.083 |
�� | -1.056 |
Token | The |
Token ID | 464 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ioned | +1.056 |
inatory | +1.019 |
eenth | +0.946 |
enance | +0.938 |
alities | +0.933 |
Neg logit contributions | |
iler | -1.113 |
ilers | -0.988 |
fter | -0.973 |
ghan | -0.929 |
lder | -0.884 |
Token | door |
Token ID | 3420 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ioned | +2.414 |
inatory | +2.333 |
eenth | +2.183 |
enance | +2.170 |
alities | +2.163 |
Neg logit contributions | |
iler | -2.180 |
ilers | -1.934 |
fter | -1.879 |
ghan | -1.798 |
llor | -1.707 |
Token | bell |
Token ID | 7923 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
ioned | +2.168 |
inatory | +2.101 |
eenth | +1.938 |
enance | +1.924 |
alities | +1.923 |
Neg logit contributions | |
iler | -2.383 |
ilers | -2.126 |
fter | -2.094 |
ghan | -2.002 |
lder | -1.907 |
Token | rang |
Token ID | 28077 |
Feature activation | +9.69e+00 |
Pos logit contributions | |
ioned | +9.578 |
inatory | +9.239 |
bells | +9.116 |
eenth | +8.884 |
bugs | +8.735 |
Neg logit contributions | |
iler | -11.321 |
ilers | -10.430 |
fter | -9.844 |
ghan | -9.710 |
llor | -9.390 |
Token | while |
Token ID | 981 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ioned | +7.428 |
inatory | +7.097 |
eenth | +6.834 |
enance | +6.798 |
alities | +6.669 |
Neg logit contributions | |
iler | -8.080 |
ilers | -7.327 |
fter | -6.968 |
ghan | -6.679 |
llor | -6.508 |
Token | I |
Token ID | 314 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
ioned | +1.957 |
inatory | +1.881 |
eenth | +1.760 |
alities | +1.748 |
enance | +1.748 |
Neg logit contributions | |
iler | -1.817 |
ilers | -1.606 |
fter | -1.573 |
ghan | -1.499 |
llor | -1.420 |
Token | was |
Token ID | 373 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
iler | +4.538 |
fter | +3.906 |
ilers | +3.838 |
ghan | +3.683 |
lder | +3.514 |
Neg logit contributions | |
ioned | -5.477 |
inatory | -5.434 |
eenth | -5.050 |
atural | -5.016 |
enance | -4.976 |
Token | preparing |
Token ID | 10629 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
iler | +1.622 |
ilers | +1.404 |
fter | +1.403 |
ghan | +1.334 |
lder | +1.253 |
Neg logit contributions | |
ioned | -1.886 |
inatory | -1.841 |
eenth | -1.713 |
atural | -1.696 |
enance | -1.694 |
Token | . |
Token ID | 13 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
ioned | +1.746 |
inatory | +1.648 |
eenth | +1.567 |
enance | +1.548 |
bugs | +1.533 |
Neg logit contributions | |
iler | -1.901 |
ilers | -1.710 |
fter | -1.665 |
ghan | -1.587 |
�� | -1.540 |
Token | Now |
Token ID | 2735 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
iler | +2.507 |
ilers | +2.187 |
fter | +2.179 |
ghan | +2.075 |
lder | +1.984 |
Neg logit contributions | |
ioned | -2.503 |
inatory | -2.436 |
eenth | -2.237 |
atural | -2.223 |
enance | -2.218 |
Token | we |
Token ID | 356 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
iler | +0.745 |
ilers | +0.636 |
fter | +0.627 |
ghan | +0.588 |
lder | +0.550 |
Neg logit contributions | |
ioned | -1.106 |
inatory | -1.076 |
eenth | -1.012 |
enance | -1.005 |
alities | -1.001 |
Token | cut |
Token ID | 2005 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
iler | +4.039 |
ilers | +3.391 |
fter | +3.341 |
ghan | +3.085 |
lder | +2.994 |
Neg logit contributions | |
ioned | -5.978 |
inatory | -5.855 |
eenth | -5.473 |
atural | -5.463 |
alities | -5.437 |
Token | the |
Token ID | 262 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
iler | +3.373 |
ilers | +2.871 |
fter | +2.820 |
ghan | +2.696 |
lder | +2.586 |
Neg logit contributions | |
ioned | -4.294 |
inatory | -4.162 |
eenth | -3.862 |
enance | -3.850 |
atural | -3.835 |
Token | bell |
Token ID | 8966 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
iler | +0.851 |
ilers | +0.747 |
fter | +0.737 |
ghan | +0.701 |
lder | +0.665 |
Neg logit contributions | |
ioned | -0.917 |
inatory | -0.888 |
eenth | -0.827 |
enance | -0.821 |
alities | -0.816 |
Token | peppers |
Token ID | 31804 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
ioned | +8.398 |
inatory | +7.777 |
bugs | +7.613 |
atural | +7.571 |
bells | +7.482 |
Neg logit contributions | |
iler | -12.687 |
fter | -11.740 |
ilers | -11.475 |
ghan | -11.374 |
llor | -11.097 |
Token | into |
Token ID | 656 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
ioned | +3.468 |
inatory | +3.360 |
eenth | +3.172 |
enance | +3.127 |
alities | +3.125 |
Neg logit contributions | |
iler | -3.066 |
ilers | -2.721 |
fter | -2.666 |
ghan | -2.531 |
llor | -2.418 |
Token | small |
Token ID | 1402 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
iler | +2.183 |
ilers | +1.879 |
fter | +1.864 |
ghan | +1.758 |
lder | +1.683 |
Neg logit contributions | |
ioned | -2.784 |
inatory | -2.685 |
enance | -2.508 |
eenth | -2.504 |
atural | -2.492 |
Token | - |
Token ID | 12 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
ioned | +0.157 |
inatory | +0.152 |
eenth | +0.142 |
enance | +0.141 |
alities | +0.140 |
Neg logit contributions | |
iler | -0.140 |
ilers | -0.123 |
fter | -0.121 |
ghan | -0.115 |
lder | -0.109 |
Token | medium |
Token ID | 24132 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ioned | +1.772 |
inatory | +1.701 |
eenth | +1.582 |
alities | +1.560 |
enance | +1.560 |
Neg logit contributions | |
iler | -2.108 |
ilers | -1.887 |
fter | -1.863 |
ghan | -1.781 |
llor | -1.699 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ioned | +0.284 |
inatory | +0.275 |
eenth | +0.256 |
enance | +0.254 |
alities | +0.253 |
Neg logit contributions | |
iler | -0.253 |
ilers | -0.221 |
fter | -0.219 |
ghan | -0.207 |
lder | -0.196 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ioned | +1.193 |
inatory | +1.135 |
enance | +1.079 |
eenth | +1.076 |
alities | +1.053 |
Neg logit contributions | |
iler | -1.318 |
ilers | -1.190 |
fter | -1.148 |
ghan | -1.096 |
�� | -1.093 |
Token | Fourth |
Token ID | 45530 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ioned | +0.914 |
inatory | +0.880 |
eenth | +0.813 |
enance | +0.804 |
alities | +0.798 |
Neg logit contributions | |
iler | -1.186 |
ilers | -1.065 |
fter | -1.051 |
ghan | -1.012 |
lder | -0.964 |
Token | , |
Token ID | 11 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
ioned | +1.880 |
inatory | +1.817 |
eenth | +1.685 |
enance | +1.669 |
alities | +1.658 |
Neg logit contributions | |
iler | -2.137 |
ilers | -1.912 |
fter | -1.880 |
ghan | -1.799 |
lder | -1.713 |
Token | snap |
Token ID | 11495 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
iler | +3.099 |
ilers | +2.711 |
fter | +2.705 |
ghan | +2.488 |
llor | +2.423 |
Neg logit contributions | |
ioned | -3.553 |
inatory | -3.406 |
eenth | -3.188 |
atural | -3.151 |
alities | -3.133 |
Token | parliamentary |
Token ID | 17521 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
ioned | +1.200 |
inatory | +1.153 |
eenth | +1.058 |
enance | +1.049 |
alities | +1.040 |
Neg logit contributions | |
iler | -1.603 |
ilers | -1.440 |
fter | -1.424 |
ghan | -1.364 |
lder | -1.310 |
Token | elections |
Token ID | 7024 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ioned | +8.122 |
inatory | +7.945 |
alities | +7.295 |
ally | +6.965 |
enance | +6.931 |
Neg logit contributions | |
iler | -13.333 |
fter | -12.120 |
ilers | -12.104 |
ghan | -11.797 |
llor | -10.991 |
Token | in |
Token ID | 287 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ioned | +2.880 |
inatory | +2.793 |
enance | +2.609 |
eenth | +2.604 |
alities | +2.574 |
Neg logit contributions | |
iler | -2.443 |
ilers | -2.135 |
fter | -2.095 |
ghan | -2.019 |
lder | -1.892 |
Token | Catalonia |
Token ID | 33859 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
iler | +0.163 |
ilers | +0.144 |
fter | +0.142 |
ghan | +0.135 |
lder | +0.128 |
Neg logit contributions | |
ioned | -0.165 |
inatory | -0.159 |
eenth | -0.148 |
enance | -0.147 |
alities | -0.146 |
Token | could |
Token ID | 714 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ioned | +1.098 |
inatory | +1.067 |
eenth | +0.999 |
enance | +0.993 |
alities | +0.988 |
Neg logit contributions | |
iler | -0.860 |
ilers | -0.748 |
fter | -0.736 |
ghan | -0.696 |
lder | -0.654 |
Token | be |
Token ID | 307 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
ioned | +1.804 |
inatory | +1.754 |
eenth | +1.647 |
enance | +1.635 |
alities | +1.633 |
Neg logit contributions | |
iler | -1.290 |
ilers | -1.110 |
fter | -1.092 |
ghan | -1.042 |
llor | -0.963 |
Token | ae |
Token ID | 3609 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
ioned | +0.457 |
inatory | +0.443 |
eenth | +0.408 |
enance | +0.403 |
atural | +0.402 |
Neg logit contributions | |
iler | -0.515 |
ilers | -0.457 |
fter | -0.450 |
ghan | -0.428 |
lder | -0.409 |
Token | of |
Token ID | 286 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
iler | +4.315 |
ilers | +3.699 |
fter | +3.647 |
ghan | +3.486 |
lder | +3.322 |
Neg logit contributions | |
ioned | -5.396 |
inatory | -5.288 |
eenth | -4.936 |
atural | -4.900 |
enance | -4.897 |
Token | everyone |
Token ID | 2506 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ioned | +1.014 |
inatory | +0.982 |
eenth | +0.914 |
enance | +0.908 |
alities | +0.902 |
Neg logit contributions | |
iler | -0.961 |
ilers | -0.846 |
fter | -0.835 |
ghan | -0.794 |
lder | -0.753 |
Token | standing |
Token ID | 5055 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
ioned | +4.158 |
inatory | +3.988 |
eenth | +3.768 |
alities | +3.758 |
enance | +3.757 |
Neg logit contributions | |
iler | -3.564 |
ilers | -3.134 |
fter | -3.110 |
ghan | -2.922 |
llor | -2.746 |
Token | for |
Token ID | 329 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
ioned | +5.635 |
inatory | +5.361 |
eenth | +5.028 |
enance | +5.027 |
alities | +5.012 |
Neg logit contributions | |
iler | -5.730 |
ilers | -5.078 |
fter | -4.985 |
ghan | -4.739 |
llor | -4.505 |
Token | Parliament |
Token ID | 8411 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ioned | +2.817 |
inatory | +2.721 |
eenth | +2.534 |
enance | +2.525 |
alities | +2.513 |
Neg logit contributions | |
iler | -2.695 |
ilers | -2.381 |
fter | -2.351 |
ghan | -2.234 |
lder | -2.105 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ioned | +10.745 |
inatory | +10.316 |
alities | +9.756 |
ally | +9.592 |
eenth | +9.528 |
Neg logit contributions | |
iler | -10.576 |
ilers | -9.424 |
fter | -9.399 |
ghan | -8.871 |
lder | -8.246 |
Token |
|
Token ID | 198 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
ioned | +1.235 |
inatory | +1.194 |
eenth | +1.113 |
enance | +1.103 |
alities | +1.097 |
Neg logit contributions | |
iler | -1.210 |
ilers | -1.069 |
fter | -1.054 |
ghan | -1.004 |
lder | -0.952 |
Token |
|
Token ID | 198 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
ioned | +0.196 |
inatory | +0.190 |
eenth | +0.177 |
enance | +0.176 |
alities | +0.175 |
Neg logit contributions | |
iler | -0.166 |
ilers | -0.145 |
fter | -0.143 |
ghan | -0.136 |
lder | -0.128 |
Token | It |
Token ID | 1026 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
ioned | +0.059 |
inatory | +0.057 |
eenth | +0.053 |
enance | +0.052 |
alities | +0.052 |
Neg logit contributions | |
iler | -0.065 |
ilers | -0.058 |
fter | -0.058 |
ghan | -0.055 |
lder | -0.052 |
Token | � |
Token ID | 447 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ioned | +5.272 |
inatory | +5.070 |
eenth | +4.705 |
alities | +4.654 |
enance | +4.654 |
Neg logit contributions | |
iler | -6.295 |
ilers | -5.698 |
fter | -5.605 |
ghan | -5.351 |
lder | -5.065 |
Token | also |
Token ID | 635 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
iler | +1.138 |
ilers | +1.001 |
fter | +0.994 |
ghan | +0.950 |
lder | +0.900 |
Neg logit contributions | |
ioned | -1.112 |
inatory | -1.080 |
eenth | -0.998 |
atural | -0.990 |
enance | -0.987 |
Token | reached |
Token ID | 4251 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
iler | +1.501 |
ilers | +1.320 |
fter | +1.316 |
ghan | +1.259 |
lder | +1.196 |
Neg logit contributions | |
ioned | -1.407 |
inatory | -1.372 |
eenth | -1.265 |
atural | -1.256 |
enance | -1.245 |
Token | out |
Token ID | 503 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
iler | +0.112 |
ilers | +0.098 |
fter | +0.097 |
ghan | +0.092 |
lder | +0.087 |
Neg logit contributions | |
ioned | -0.122 |
inatory | -0.119 |
eenth | -0.111 |
atural | -0.109 |
enance | -0.109 |
Token | to |
Token ID | 284 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
ioned | +0.794 |
inatory | +0.771 |
eenth | +0.722 |
enance | +0.714 |
atural | +0.712 |
Neg logit contributions | |
iler | -0.636 |
ilers | -0.552 |
fter | -0.545 |
ghan | -0.518 |
lder | -0.487 |
Token | ' |
Token ID | 705 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
ioned | +2.153 |
inatory | +2.080 |
eenth | +1.929 |
enance | +1.928 |
alities | +1.911 |
Neg logit contributions | |
iler | -2.133 |
ilers | -1.885 |
fter | -1.860 |
ghan | -1.767 |
llor | -1.680 |
Token | National |
Token ID | 16186 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
ioned | +3.192 |
inatory | +3.079 |
enance | +2.848 |
alities | +2.838 |
eenth | +2.837 |
Neg logit contributions | |
iler | -3.369 |
ilers | -3.003 |
fter | -2.940 |
ghan | -2.804 |
llor | -2.681 |
Token | Review |
Token ID | 6602 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ioned | +8.875 |
inatory | +8.077 |
enance | +7.433 |
ally | +7.361 |
atural | +7.311 |
Neg logit contributions | |
iler | -12.575 |
ilers | -11.515 |
fter | -11.325 |
ghan | -10.802 |
llor | -10.694 |
Token | ,' |
Token ID | 4032 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
ioned | +1.560 |
inatory | +1.515 |
eenth | +1.419 |
enance | +1.408 |
alities | +1.401 |
Neg logit contributions | |
iler | -1.266 |
ilers | -1.102 |
fter | -1.087 |
ghan | -1.029 |
lder | -0.968 |
Token | a |
Token ID | 257 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
ioned | +2.734 |
inatory | +2.642 |
eenth | +2.455 |
enance | +2.440 |
alities | +2.431 |
Neg logit contributions | |
iler | -2.626 |
ilers | -2.322 |
fter | -2.277 |
ghan | -2.158 |
lder | -2.057 |
Token | magazine |
Token ID | 7093 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
iler | +0.566 |
ilers | +0.488 |
fter | +0.479 |
ghan | +0.452 |
lder | +0.423 |
Neg logit contributions | |
ioned | -0.786 |
inatory | -0.764 |
eenth | -0.718 |
enance | -0.713 |
alities | -0.710 |
Token | that |
Token ID | 326 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
ioned | +4.128 |
inatory | +3.977 |
enance | +3.744 |
eenth | +3.704 |
alities | +3.701 |
Neg logit contributions | |
iler | -3.557 |
ilers | -3.147 |
fter | -3.079 |
ghan | -2.914 |
llor | -2.784 |
Token | that |
Token ID | 326 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
iler | +0.114 |
ilers | +0.099 |
fter | +0.098 |
ghan | +0.093 |
lder | +0.088 |
Neg logit contributions | |
ioned | -0.134 |
inatory | -0.130 |
eenth | -0.122 |
enance | -0.121 |
alities | -0.120 |
Token | having |
Token ID | 1719 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ioned | +1.430 |
inatory | +1.381 |
eenth | +1.285 |
enance | +1.278 |
alities | +1.270 |
Neg logit contributions | |
iler | -1.393 |
ilers | -1.229 |
fter | -1.213 |
ghan | -1.154 |
lder | -1.094 |
Token | a |
Token ID | 257 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
ioned | +1.748 |
inatory | +1.687 |
eenth | +1.576 |
enance | +1.572 |
alities | +1.559 |
Neg logit contributions | |
iler | -1.553 |
ilers | -1.363 |
fter | -1.346 |
ghan | -1.274 |
llor | -1.205 |
Token | video |
Token ID | 2008 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ioned | +0.840 |
inatory | +0.814 |
eenth | +0.762 |
enance | +0.757 |
alities | +0.753 |
Neg logit contributions | |
iler | -0.685 |
ilers | -0.600 |
fter | -0.591 |
ghan | -0.559 |
llor | -0.526 |
Token | of |
Token ID | 286 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
ioned | +1.368 |
inatory | +1.329 |
eenth | +1.246 |
enance | +1.237 |
alities | +1.231 |
Neg logit contributions | |
iler | -1.050 |
ilers | -0.911 |
fter | -0.899 |
ghan | -0.850 |
lder | -0.798 |
Token | nightclub |
Token ID | 26617 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
ioned | +5.188 |
inatory | +4.971 |
enance | +4.677 |
alities | +4.637 |
eenth | +4.624 |
Neg logit contributions | |
iler | -5.063 |
ilers | -4.519 |
fter | -4.443 |
ghan | -4.216 |
llor | -4.062 |
Token | scenes |
Token ID | 8188 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ioned | +10.405 |
inatory | +9.941 |
alities | +9.214 |
tons | +9.213 |
inators | +9.210 |
Neg logit contributions | |
iler | -10.473 |
ilers | -9.364 |
fter | -9.302 |
ghan | -9.213 |
llor | -8.683 |
Token | playing |
Token ID | 2712 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
ioned | +2.132 |
inatory | +2.062 |
eenth | +1.925 |
enance | +1.920 |
alities | +1.906 |
Neg logit contributions | |
iler | -1.931 |
ilers | -1.703 |
fter | -1.677 |
ghan | -1.598 |
llor | -1.519 |
Token | in |
Token ID | 287 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ioned | +3.843 |
inatory | +3.671 |
enance | +3.417 |
eenth | +3.416 |
alities | +3.413 |
Neg logit contributions | |
iler | -4.048 |
ilers | -3.624 |
fter | -3.513 |
ghan | -3.392 |
llor | -3.247 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
iler | +0.088 |
ilers | +0.077 |
fter | +0.076 |
ghan | +0.072 |
lder | +0.068 |
Neg logit contributions | |
ioned | -0.101 |
inatory | -0.098 |
eenth | -0.092 |
enance | -0.091 |
alities | -0.091 |
Token | background |
Token ID | 4469 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
iler | +1.375 |
ilers | +1.177 |
fter | +1.162 |
ghan | +1.091 |
lder | +1.027 |
Neg logit contributions | |
ioned | -1.910 |
inatory | -1.857 |
eenth | -1.746 |
enance | -1.734 |
atural | -1.723 |
Token | resist |
Token ID | 4180 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ioned | +1.501 |
inatory | +1.453 |
enance | +1.357 |
eenth | +1.353 |
alities | +1.348 |
Neg logit contributions | |
iler | -1.194 |
ilers | -1.046 |
fter | -1.031 |
ghan | -0.990 |
llor | -0.929 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ioned | +1.926 |
inatory | +1.850 |
enance | +1.734 |
eenth | +1.733 |
alities | +1.722 |
Neg logit contributions | |
iler | -1.700 |
ilers | -1.495 |
fter | -1.488 |
ghan | -1.389 |
lder | -1.323 |
Token | temptation |
Token ID | 29062 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ioned | +1.166 |
inatory | +1.130 |
eenth | +1.055 |
enance | +1.048 |
alities | +1.043 |
Neg logit contributions | |
iler | -1.046 |
ilers | -0.918 |
fter | -0.906 |
ghan | -0.860 |
lder | -0.813 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
iler | +1.295 |
ilers | +1.119 |
fter | +1.092 |
ghan | +1.039 |
lder | +0.974 |
Neg logit contributions | |
ioned | -1.724 |
inatory | -1.676 |
eenth | -1.574 |
enance | -1.560 |
atural | -1.550 |
Token | recall |
Token ID | 10014 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
iler | +0.668 |
ilers | +0.571 |
fter | +0.563 |
ghan | +0.526 |
llor | +0.492 |
Neg logit contributions | |
ioned | -1.032 |
inatory | -1.002 |
eenth | -0.942 |
enance | -0.938 |
alities | -0.936 |
Token | 1974 |
Token ID | 16489 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
ioned | +1.690 |
inatory | +1.632 |
eenth | +1.520 |
enance | +1.517 |
alities | +1.507 |
Neg logit contributions | |
iler | -1.584 |
ilers | -1.396 |
fter | -1.377 |
ghan | -1.305 |
lder | -1.236 |
Token | 's |
Token ID | 338 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
ioned | +9.543 |
inatory | +9.449 |
ally | +8.576 |
alities | +8.556 |
eenth | +8.540 |
Neg logit contributions | |
iler | -10.751 |
fter | -9.849 |
ilers | -9.774 |
ghan | -9.173 |
llor | -8.798 |
Token | masterpiece |
Token ID | 30669 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
ioned | +2.921 |
inatory | +2.842 |
eenth | +2.636 |
enance | +2.607 |
alities | +2.606 |
Neg logit contributions | |
iler | -2.931 |
ilers | -2.606 |
fter | -2.586 |
ghan | -2.456 |
llor | -2.340 |
Token |
|
Token ID | 198 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
ioned | +3.214 |
inatory | +3.112 |
eenth | +2.891 |
enance | +2.870 |
alities | +2.858 |
Neg logit contributions | |
iler | -3.143 |
ilers | -2.787 |
fter | -2.776 |
ghan | -2.619 |
llor | -2.498 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ioned | +1.683 |
inatory | +1.603 |
eenth | +1.515 |
enance | +1.511 |
bugs | +1.495 |
Neg logit contributions | |
iler | -1.886 |
ilers | -1.705 |
fter | -1.644 |
�� | -1.566 |
ghan | -1.563 |
Token | Image |
Token ID | 5159 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
ioned | +1.453 |
inatory | +1.403 |
eenth | +1.300 |
enance | +1.292 |
alities | +1.283 |
Neg logit contributions | |
iler | -1.552 |
ilers | -1.381 |
fter | -1.360 |
ghan | -1.293 |
llor | -1.234 |
Token | hope |
Token ID | 2911 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
iler | +1.789 |
ilers | +1.541 |
fter | +1.515 |
ghan | +1.426 |
lder | +1.335 |
Neg logit contributions | |
ioned | -2.513 |
inatory | -2.440 |
eenth | -2.294 |
enance | -2.281 |
alities | -2.270 |
Token | he |
Token ID | 339 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
iler | +0.820 |
ilers | +0.710 |
fter | +0.706 |
ghan | +0.660 |
lder | +0.634 |
Neg logit contributions | |
ioned | -1.006 |
inatory | -0.985 |
eenth | -0.921 |
atural | -0.911 |
enance | -0.909 |
Token | apolog |
Token ID | 8453 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
ioned | +2.063 |
inatory | +1.984 |
eenth | +1.838 |
enance | +1.835 |
alities | +1.824 |
Neg logit contributions | |
iler | -2.440 |
ilers | -2.196 |
fter | -2.147 |
ghan | -2.050 |
llor | -1.962 |
Token | izes |
Token ID | 4340 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
ioned | +0.283 |
inatory | +0.265 |
eenth | +0.228 |
enance | +0.225 |
alities | +0.221 |
Neg logit contributions | |
iler | -0.809 |
ilers | -0.746 |
fter | -0.739 |
ghan | -0.717 |
lder | -0.694 |
Token | [ |
Token ID | 685 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
iler | +0.070 |
ilers | +0.062 |
fter | +0.061 |
ghan | +0.058 |
lder | +0.055 |
Neg logit contributions | |
ioned | -0.071 |
inatory | -0.069 |
eenth | -0.064 |
enance | -0.063 |
atural | -0.063 |
Token | Tuesday |
Token ID | 26133 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
ioned | +0.457 |
inatory | +0.441 |
eenth | +0.404 |
enance | +0.402 |
alities | +0.399 |
Neg logit contributions | |
iler | -0.582 |
ilers | -0.523 |
fter | -0.515 |
ghan | -0.495 |
lder | -0.473 |
Token | ], |
Token ID | 4357 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ioned | +9.658 |
inatory | +9.163 |
eenth | +8.632 |
alities | +8.567 |
enance | +8.545 |
Neg logit contributions | |
iler | -10.995 |
ilers | -10.014 |
fter | -9.199 |
ghan | -9.155 |
pires | -8.843 |
Token | to |
Token ID | 284 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
ioned | +2.388 |
inatory | +2.307 |
eenth | +2.132 |
enance | +2.117 |
alities | +2.110 |
Neg logit contributions | |
iler | -2.676 |
ilers | -2.389 |
fter | -2.344 |
ghan | -2.244 |
llor | -2.133 |
Token | be |
Token ID | 307 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
iler | +0.747 |
ilers | +0.652 |
fter | +0.641 |
ghan | +0.607 |
lder | +0.575 |
Neg logit contributions | |
ioned | -0.885 |
inatory | -0.860 |
eenth | -0.804 |
enance | -0.797 |
alities | -0.794 |
Token | honest |
Token ID | 5508 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ioned | +0.497 |
inatory | +0.483 |
eenth | +0.449 |
atural | +0.445 |
enance | +0.445 |
Neg logit contributions | |
iler | -0.449 |
ilers | -0.390 |
fter | -0.390 |
ghan | -0.369 |
lder | -0.349 |
Token | with |
Token ID | 351 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
iler | +1.548 |
ilers | +1.372 |
fter | +1.369 |
ghan | +1.310 |
llor | +1.237 |
Neg logit contributions | |
ioned | -1.454 |
inatory | -1.411 |
eenth | -1.307 |
enance | -1.296 |
atural | -1.296 |
Token | Chuck |
Token ID | 44324 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
iler | +5.562 |
fter | +4.952 |
ilers | +4.871 |
ghan | +4.760 |
lder | +4.488 |
Neg logit contributions | |
ioned | -5.608 |
inatory | -5.495 |
enance | -5.111 |
eenth | -5.106 |
alities | -5.024 |
Token | Ye |
Token ID | 11609 |
Feature activation | -8.84e+00 |
Pos logit contributions | |
ioned | +2.350 |
inatory | +2.277 |
eenth | +2.128 |
enance | +2.113 |
alities | +2.099 |
Neg logit contributions | |
iler | -2.098 |
ilers | -1.841 |
fter | -1.813 |
ghan | -1.718 |
lder | -1.627 |
Token | ager |
Token ID | 3536 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
iler | +3.833 |
ilers | +2.903 |
fter | +2.822 |
ghan | +2.550 |
lder | +2.395 |
Neg logit contributions | |
ioned | -10.738 |
inatory | -10.663 |
eenth | -10.087 |
HCR | -10.066 |
atural | -10.056 |
Token | and |
Token ID | 290 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
iler | +1.547 |
ilers | +1.341 |
fter | +1.336 |
ghan | +1.286 |
lder | +1.206 |
Neg logit contributions | |
ioned | -1.650 |
inatory | -1.622 |
eenth | -1.505 |
alities | -1.488 |
enance | -1.486 |
Token | the |
Token ID | 262 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ioned | +1.702 |
inatory | +1.646 |
eenth | +1.532 |
enance | +1.520 |
alities | +1.512 |
Neg logit contributions | |
iler | -1.652 |
ilers | -1.458 |
fter | -1.438 |
ghan | -1.368 |
lder | -1.298 |
Token | Bell |
Token ID | 7459 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
iler | +0.492 |
ilers | +0.432 |
fter | +0.428 |
ghan | +0.407 |
lder | +0.388 |
Neg logit contributions | |
ioned | -0.491 |
inatory | -0.476 |
eenth | -0.442 |
enance | -0.441 |
alities | -0.436 |
Token | X |
Token ID | 1395 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ioned | +10.797 |
inatory | +10.229 |
eenth | +9.686 |
atural | +9.516 |
tons | +9.506 |
Neg logit contributions | |
iler | -9.934 |
fter | -8.990 |
ilers | -8.806 |
ghan | -8.465 |
llor | -8.192 |
Token | - |
Token ID | 12 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
iler | +0.406 |
ilers | +0.350 |
fter | +0.346 |
ghan | +0.327 |
lder | +0.308 |
Neg logit contributions | |
ioned | -0.526 |
inatory | -0.514 |
enance | -0.484 |
eenth | -0.480 |
alities | -0.477 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ioned | +0.674 |
inatory | +0.655 |
eenth | +0.616 |
enance | +0.612 |
alities | +0.609 |
Neg logit contributions | |
iler | -0.475 |
ilers | -0.408 |
fter | -0.401 |
ghan | -0.378 |
lder | -0.353 |
Token | . |
Token ID | 13 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
ioned | +1.937 |
inatory | +1.875 |
eenth | +1.747 |
enance | +1.735 |
alities | +1.724 |
Neg logit contributions | |
iler | -1.829 |
ilers | -1.610 |
fter | -1.588 |
ghan | -1.511 |
lder | -1.432 |
Token | � |
Token ID | 447 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
iler | +0.360 |
ilers | +0.316 |
fter | +0.314 |
ghan | +0.299 |
lder | +0.284 |
Neg logit contributions | |
ioned | -0.360 |
inatory | -0.349 |
eenth | -0.323 |
enance | -0.323 |
alities | -0.321 |
Token | music |
Token ID | 2647 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
ioned | +2.964 |
inatory | +2.874 |
eenth | +2.643 |
alities | +2.634 |
enance | +2.629 |
Neg logit contributions | |
iler | -2.900 |
ilers | -2.563 |
fter | -2.534 |
ghan | -2.398 |
lder | -2.290 |
Token | . |
Token ID | 13 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
ioned | +2.144 |
inatory | +2.064 |
eenth | +1.923 |
enance | +1.918 |
alities | +1.906 |
Neg logit contributions | |
iler | -1.986 |
ilers | -1.749 |
fter | -1.726 |
ghan | -1.635 |
lder | -1.548 |
Token | The |
Token ID | 383 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
ioned | +0.707 |
inatory | +0.685 |
eenth | +0.636 |
enance | +0.631 |
alities | +0.628 |
Neg logit contributions | |
iler | -0.701 |
ilers | -0.619 |
fter | -0.611 |
ghan | -0.582 |
lder | -0.553 |
Token | plan |
Token ID | 1410 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ioned | +0.889 |
inatory | +0.862 |
eenth | +0.805 |
enance | +0.799 |
alities | +0.795 |
Neg logit contributions | |
iler | -0.777 |
ilers | -0.679 |
fter | -0.670 |
ghan | -0.635 |
lder | -0.601 |
Token | for |
Token ID | 329 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
ioned | +1.370 |
inatory | +1.329 |
eenth | +1.238 |
enance | +1.228 |
alities | +1.221 |
Neg logit contributions | |
iler | -1.288 |
ilers | -1.133 |
fter | -1.118 |
ghan | -1.064 |
lder | -1.007 |
Token | Saturday |
Token ID | 3909 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
ioned | +3.033 |
inatory | +2.935 |
eenth | +2.740 |
enance | +2.734 |
alities | +2.712 |
Neg logit contributions | |
iler | -2.907 |
ilers | -2.585 |
fter | -2.542 |
ghan | -2.448 |
llor | -2.311 |
Token | was |
Token ID | 373 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ioned | +9.867 |
inatory | +9.252 |
eenth | +8.744 |
enance | +8.725 |
alities | +8.572 |
Neg logit contributions | |
iler | -10.651 |
ilers | -9.680 |
fter | -9.450 |
ghan | -8.952 |
lder | -8.619 |
Token | country |
Token ID | 1499 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
ioned | +1.788 |
inatory | +1.730 |
eenth | +1.616 |
enance | +1.612 |
alities | +1.598 |
Neg logit contributions | |
iler | -1.513 |
ilers | -1.325 |
fter | -1.300 |
ghan | -1.233 |
lder | -1.163 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ioned | +4.790 |
inatory | +4.593 |
eenth | +4.239 |
alities | +4.235 |
atural | +4.230 |
Neg logit contributions | |
iler | -4.788 |
ilers | -4.245 |
fter | -4.214 |
ghan | -3.982 |
llor | -3.789 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ioned | +1.130 |
inatory | +1.093 |
eenth | +1.019 |
enance | +1.012 |
alities | +1.005 |
Neg logit contributions | |
iler | -1.076 |
ilers | -0.949 |
fter | -0.936 |
ghan | -0.890 |
lder | -0.843 |
Token | old |
Token ID | 1468 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ioned | +1.549 |
inatory | +1.496 |
eenth | +1.397 |
enance | +1.390 |
alities | +1.382 |
Neg logit contributions | |
iler | -1.406 |
ilers | -1.237 |
fter | -1.217 |
ghan | -1.159 |
lder | -1.094 |
Token | but |
Token ID | 475 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
iler | +1.638 |
ilers | +1.447 |
fter | +1.421 |
ghan | +1.367 |
lder | +1.302 |
Neg logit contributions | |
ioned | -1.601 |
inatory | -1.564 |
eenth | -1.448 |
atural | -1.431 |
enance | -1.430 |
Token | dismissing |
Token ID | 37514 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
iler | +0.490 |
ilers | +0.428 |
fter | +0.422 |
ghan | +0.399 |
lder | +0.379 |
Neg logit contributions | |
ioned | -0.585 |
inatory | -0.568 |
eenth | -0.531 |
atural | -0.526 |
enance | -0.524 |
Token | bad |
Token ID | 2089 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
ioned | +1.532 |
inatory | +1.483 |
eenth | +1.382 |
enance | +1.375 |
alities | +1.367 |
Neg logit contributions | |
iler | -1.414 |
ilers | -1.243 |
fter | -1.228 |
ghan | -1.166 |
lder | -1.101 |
Token | ones |
Token ID | 3392 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
ioned | +3.926 |
inatory | +3.767 |
alities | +3.460 |
enance | +3.458 |
eenth | +3.455 |
Neg logit contributions | |
iler | -4.902 |
ilers | -4.377 |
fter | -4.350 |
ghan | -4.160 |
llor | -3.961 |
Token | . |
Token ID | 13 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ioned | +2.035 |
inatory | +1.957 |
eenth | +1.834 |
enance | +1.828 |
alities | +1.808 |
Neg logit contributions | |
iler | -1.887 |
ilers | -1.661 |
fter | -1.646 |
ghan | -1.559 |
lder | -1.472 |
Token | Bell |
Token ID | 7459 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
iler | +0.395 |
ilers | +0.348 |
fter | +0.344 |
ghan | +0.328 |
lder | +0.312 |
Neg logit contributions | |
ioned | -0.404 |
inatory | -0.392 |
eenth | -0.363 |
enance | -0.361 |
alities | -0.359 |
Token | w |
Token ID | 86 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ioned | +10.973 |
inatory | +10.655 |
eenth | +9.850 |
alities | +9.839 |
atural | +9.777 |
Neg logit contributions | |
iler | -9.616 |
ilers | -8.564 |
fter | -8.556 |
ghan | -7.993 |
llor | -7.524 |
Token | ether |
Token ID | 6750 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ioned | +3.142 |
inatory | +3.055 |
eenth | +2.886 |
enance | +2.853 |
alities | +2.836 |
Neg logit contributions | |
iler | -2.177 |
ilers | -1.891 |
fter | -1.866 |
ghan | -1.764 |
llor | -1.644 |
Token | Partners |
Token ID | 14205 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ioned | +3.982 |
inatory | +3.843 |
eenth | +3.587 |
enance | +3.561 |
alities | +3.538 |
Neg logit contributions | |
iler | -3.984 |
ilers | -3.531 |
fter | -3.485 |
ghan | -3.298 |
llor | -3.128 |
Token | � |
Token ID | 447 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ioned | +2.003 |
inatory | +1.929 |
eenth | +1.815 |
enance | +1.794 |
alities | +1.788 |
Neg logit contributions | |
iler | -1.727 |
ilers | -1.517 |
fter | -1.495 |
ghan | -1.416 |
lder | -1.332 |
Token | � |
Token ID | 247 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
ioned | +0.202 |
inatory | +0.196 |
eenth | +0.186 |
enance | +0.184 |
atural | +0.182 |
Neg logit contributions | |
iler | -0.144 |
ilers | -0.124 |
fter | -0.121 |
ghan | -0.113 |
lder | -0.107 |
Token | s |
Token ID | 82 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ioned | +0.919 |
inatory | +0.870 |
eenth | +0.795 |
alities | +0.777 |
enance | +0.774 |
Neg logit contributions | |
iler | -1.690 |
ilers | -1.535 |
fter | -1.518 |
ghan | -1.460 |
llor | -1.416 |
Token | )} |
Token ID | 38165 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
iler | +0.158 |
ilers | +0.141 |
fter | +0.138 |
ghan | +0.133 |
lder | +0.125 |
Neg logit contributions | |
ioned | -0.149 |
inatory | -0.144 |
eenth | -0.134 |
enance | -0.133 |
alities | -0.132 |
Token | 37 |
Token ID | 5214 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
iler | +2.072 |
ilers | +1.779 |
fter | +1.731 |
ghan | +1.684 |
lder | +1.555 |
Neg logit contributions | |
ioned | -3.125 |
inatory | -3.032 |
eenth | -2.873 |
atural | -2.872 |
enance | -2.864 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ioned | +2.326 |
inatory | +2.160 |
eenth | +2.069 |
enance | +2.053 |
alities | +2.035 |
Neg logit contributions | |
iler | -2.681 |
ilers | -2.416 |
fter | -2.347 |
�� | -2.265 |
ghan | -2.238 |
Token | f |
Token ID | 277 |
Feature activation | -8.52e+00 |
Pos logit contributions | |
iler | +0.861 |
ilers | +0.749 |
fter | +0.736 |
ghan | +0.696 |
lder | +0.654 |
Neg logit contributions | |
ioned | -1.083 |
inatory | -1.050 |
eenth | -0.984 |
enance | -0.978 |
alities | -0.974 |
Token | xe |
Token ID | 27705 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
iler | +4.835 |
ilers | +3.979 |
fter | +3.903 |
ghan | +3.705 |
lder | +3.488 |
Neg logit contributions | |
ioned | -9.082 |
inatory | -8.850 |
eenth | -8.424 |
alities | -8.377 |
atural | -8.282 |
Token | 6 |
Token ID | 21 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
iler | +6.197 |
ghan | +4.775 |
ilers | +4.676 |
fter | +4.608 |
lder | +4.140 |
Neg logit contributions | |
ioned | -17.031 |
inatory | -16.563 |
eenth | -15.831 |
alities | -15.699 |
enance | -15.644 |
Token | { |
Token ID | 1391 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
iler | +2.304 |
ilers | +1.980 |
fter | +1.962 |
ghan | +1.851 |
lder | +1.735 |
Neg logit contributions | |
ioned | -3.236 |
inatory | -3.156 |
eenth | -2.985 |
enance | -2.952 |
alities | -2.934 |
Token | ( |
Token ID | 7 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
iler | +3.787 |
ilers | +3.313 |
fter | +3.287 |
ghan | +3.119 |
lder | +2.973 |
Neg logit contributions | |
ioned | -4.115 |
inatory | -4.006 |
eenth | -3.720 |
atural | -3.686 |
enance | -3.686 |
Token | 77 |
Token ID | 3324 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
iler | +3.169 |
ilers | +2.734 |
fter | +2.688 |
ghan | +2.557 |
lder | +2.421 |
Neg logit contributions | |
ioned | -4.081 |
inatory | -3.977 |
eenth | -3.702 |
enance | -3.691 |
alities | -3.688 |
Token | s |
Token ID | 82 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ioned | +3.644 |
inatory | +3.417 |
eenth | +3.186 |
bugs | +3.138 |
tons | +3.122 |
Neg logit contributions | |
iler | -8.364 |
ilers | -7.599 |
fter | -7.454 |
ghan | -7.226 |
llor | -7.114 |
Token | s |
Token ID | 82 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
ioned | +3.163 |
inatory | +3.016 |
eenth | +2.777 |
alities | +2.708 |
enance | +2.649 |
Neg logit contributions | |
iler | -5.993 |
ilers | -5.440 |
fter | -5.386 |
ghan | -5.174 |
llor | -5.058 |
Token | )} |
Token ID | 38165 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
ioned | +0.531 |
inatory | +0.512 |
eenth | +0.479 |
enance | +0.475 |
alities | +0.471 |
Neg logit contributions | |
iler | -0.586 |
ilers | -0.524 |
fter | -0.509 |
ghan | -0.495 |
lder | -0.465 |
Token | 10 |
Token ID | 838 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
iler | +1.735 |
ilers | +1.494 |
fter | +1.493 |
ghan | +1.397 |
lder | +1.315 |
Neg logit contributions | |
ioned | -2.222 |
inatory | -2.152 |
eenth | -2.022 |
enance | -1.986 |
atural | -1.984 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ioned | +2.010 |
inatory | +1.868 |
eenth | +1.790 |
enance | +1.782 |
tons | +1.762 |
Neg logit contributions | |
iler | -2.282 |
ilers | -2.059 |
fter | -2.007 |
�� | -1.921 |
ghan | -1.915 |
Token | B |
Token ID | 347 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
iler | +1.866 |
ilers | +1.628 |
fter | +1.606 |
ghan | +1.522 |
lder | +1.437 |
Neg logit contributions | |
ioned | -2.218 |
inatory | -2.152 |
eenth | -2.012 |
enance | -1.999 |
alities | -1.987 |
Token | xe |
Token ID | 27705 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
iler | +2.860 |
ilers | +2.529 |
fter | +2.512 |
ghan | +2.391 |
lder | +2.285 |
Neg logit contributions | |
ioned | -2.799 |
inatory | -2.707 |
eenth | -2.513 |
enance | -2.489 |
alities | -2.480 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
iler | +6.275 |
ghan | +4.887 |
fter | +4.835 |
ilers | +4.810 |
lder | +4.384 |
Neg logit contributions | |
ioned | -16.248 |
inatory | -15.719 |
eenth | -14.989 |
enance | -14.889 |
alities | -14.877 |
Token | { |
Token ID | 1391 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
ioned | +1.334 |
inatory | +1.289 |
eenth | +1.203 |
enance | +1.197 |
alities | +1.191 |
Neg logit contributions | |
iler | -1.124 |
ilers | -0.983 |
fter | -0.964 |
ghan | -0.913 |
llor | -0.861 |
Token | ( |
Token ID | 7 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
iler | +2.998 |
ilers | +2.642 |
fter | +2.609 |
ghan | +2.482 |
lder | +2.357 |
Neg logit contributions | |
ioned | -3.106 |
inatory | -3.009 |
eenth | -2.799 |
enance | -2.777 |
alities | -2.763 |
Token | 66 |
Token ID | 2791 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
iler | +2.582 |
ilers | +2.244 |
fter | +2.215 |
ghan | +2.099 |
lder | +1.998 |
Neg logit contributions | |
ioned | -3.094 |
inatory | -3.009 |
eenth | -2.797 |
alities | -2.783 |
enance | -2.782 |
Token | s |
Token ID | 82 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
ioned | +2.162 |
inatory | +2.061 |
eenth | +1.882 |
alities | +1.845 |
enance | +1.826 |
Neg logit contributions | |
iler | -3.860 |
ilers | -3.506 |
fter | -3.469 |
ghan | -3.335 |
llor | -3.233 |
Token | s |
Token ID | 82 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
iler | +1.777 |
ilers | +1.609 |
fter | +1.601 |
ghan | +1.534 |
lder | +1.468 |
Neg logit contributions | |
ioned | -1.280 |
inatory | -1.229 |
enance | -1.121 |
eenth | -1.112 |
atural | -1.089 |
Token | )} |
Token ID | 38165 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
iler | +1.770 |
ilers | +1.548 |
fter | +1.539 |
ghan | +1.439 |
lder | +1.375 |
Neg logit contributions | |
ioned | -2.041 |
inatory | -1.968 |
eenth | -1.839 |
enance | -1.832 |
alities | -1.804 |
Token | 52 |
Token ID | 6740 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
iler | +3.150 |
ilers | +2.712 |
fter | +2.684 |
ghan | +2.512 |
lder | +2.389 |
Neg logit contributions | |
ioned | -4.365 |
inatory | -4.268 |
eenth | -4.002 |
enance | -3.982 |
atural | -3.949 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ioned | +4.476 |
inatory | +4.152 |
ally | +3.958 |
eenth | +3.933 |
enance | +3.920 |
Neg logit contributions | |
iler | -5.488 |
ilers | -4.921 |
fter | -4.849 |
ghan | -4.720 |
�� | -4.669 |
Token | Q |
Token ID | 1195 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
iler | +1.795 |
ilers | +1.559 |
fter | +1.537 |
ghan | +1.452 |
lder | +1.369 |
Neg logit contributions | |
ioned | -2.287 |
inatory | -2.223 |
eenth | -2.082 |
enance | -2.069 |
alities | -2.056 |
Token | xf |
Token ID | 26152 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
iler | +3.785 |
ilers | +3.343 |
fter | +3.321 |
ghan | +3.141 |
lder | +3.028 |
Neg logit contributions | |
ioned | -3.873 |
inatory | -3.795 |
eenth | -3.516 |
enance | -3.492 |
alities | -3.478 |
Token | 7 |
Token ID | 22 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
iler | +5.882 |
ghan | +4.523 |
ilers | +4.484 |
fter | +4.387 |
lder | +3.924 |
Neg logit contributions | |
ioned | -16.261 |
inatory | -15.850 |
alities | -15.259 |
eenth | -15.239 |
enance | -14.882 |
Token | + |
Token ID | 10 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
iler | +0.351 |
ilers | +0.305 |
fter | +0.301 |
ghan | +0.284 |
lder | +0.267 |
Neg logit contributions | |
ioned | -0.443 |
inatory | -0.430 |
eenth | -0.403 |
enance | -0.400 |
alities | -0.398 |
Token | { |
Token ID | 1391 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
iler | +1.646 |
ilers | +1.422 |
fter | +1.403 |
ghan | +1.320 |
lder | +1.251 |
Neg logit contributions | |
ioned | -2.231 |
inatory | -2.169 |
eenth | -2.040 |
enance | -2.025 |
atural | -2.008 |
Token | ( |
Token ID | 7 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
iler | +3.328 |
ilers | +2.900 |
fter | +2.857 |
ghan | +2.673 |
lder | +2.586 |
Neg logit contributions | |
ioned | -3.871 |
inatory | -3.741 |
eenth | -3.537 |
enance | -3.496 |
atural | -3.474 |
Token | 113 |
Token ID | 16616 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
iler | +3.077 |
ilers | +2.621 |
fter | +2.598 |
ghan | +2.424 |
lder | +2.276 |
Neg logit contributions | |
ioned | -4.656 |
inatory | -4.538 |
eenth | -4.259 |
enance | -4.236 |
atural | -4.235 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
ioned | +3.173 |
inatory | +3.078 |
eenth | +2.913 |
enance | +2.891 |
alities | +2.854 |
Neg logit contributions | |
iler | -2.484 |
ilers | -2.166 |
fter | -2.112 |
ghan | -1.995 |
llor | -1.901 |
Token | 10 |
Token ID | 838 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ioned | +0.755 |
inatory | +0.732 |
eenth | +0.683 |
enance | +0.680 |
alities | +0.676 |
Neg logit contributions | |
iler | -0.655 |
ilers | -0.573 |
fter | -0.565 |
ghan | -0.536 |
lder | -0.506 |
Token | : |
Token ID | 25 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
ioned | +2.140 |
inatory | +2.068 |
eenth | +1.938 |
enance | +1.918 |
alities | +1.911 |
Neg logit contributions | |
iler | -1.841 |
ilers | -1.611 |
fter | -1.582 |
ghan | -1.498 |
llor | -1.420 |
Token | 31 |
Token ID | 3132 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
iler | +2.309 |
ilers | +2.002 |
fter | +1.990 |
ghan | +1.881 |
lder | +1.779 |
Neg logit contributions | |
ioned | -2.827 |
inatory | -2.756 |
eenth | -2.556 |
atural | -2.541 |
enance | -2.540 |
Token | , |
Token ID | 837 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
ioned | +1.627 |
inatory | +1.570 |
eenth | +1.457 |
enance | +1.442 |
alities | +1.433 |
Neg logit contributions | |
iler | -1.778 |
ilers | -1.581 |
fter | -1.555 |
ghan | -1.489 |
lder | -1.422 |
Token | e |
Token ID | 304 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
iler | +1.621 |
fter | +1.398 |
ilers | +1.385 |
ghan | +1.287 |
lder | +1.216 |
Neg logit contributions | |
ioned | -2.184 |
inatory | -2.133 |
enance | -1.987 |
alities | -1.985 |
atural | -1.977 |
Token | u |
Token ID | 84 |
Feature activation | -9.95e+00 |
Pos logit contributions | |
iler | +12.502 |
fter | +11.539 |
ilers | +11.121 |
ghan | +10.642 |
lder | +10.480 |
Neg logit contributions | |
ioned | -9.578 |
inatory | -9.464 |
enance | -8.692 |
eenth | -8.472 |
atural | -8.392 |
Token | inside |
Token ID | 48787 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
iler | +8.147 |
fter | +7.272 |
ilers | +7.034 |
ghan | +6.932 |
lder | +6.653 |
Neg logit contributions | |
ioned | -7.945 |
inatory | -7.654 |
enance | -7.115 |
eenth | -7.070 |
alities | -6.954 |
Token | , |
Token ID | 837 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
iler | +1.987 |
fter | +1.737 |
ilers | +1.734 |
ghan | +1.631 |
lder | +1.549 |
Neg logit contributions | |
ioned | -2.223 |
inatory | -2.186 |
enance | -2.022 |
eenth | -2.018 |
alities | -1.993 |
Token | Sof |
Token ID | 41427 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
iler | +2.322 |
fter | +2.013 |
ilers | +2.012 |
ghan | +1.885 |
lder | +1.783 |
Neg logit contributions | |
ioned | -2.756 |
inatory | -2.683 |
atural | -2.479 |
eenth | -2.476 |
enance | -2.475 |
Token | ia |
Token ID | 544 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
iler | +5.687 |
ilers | +5.001 |
fter | +4.960 |
ghan | +4.782 |
lder | +4.421 |
Neg logit contributions | |
ioned | -5.010 |
inatory | -4.861 |
enance | -4.523 |
eenth | -4.510 |
alities | -4.493 |
Token | actually |
Token ID | 1682 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
ioned | +0.249 |
inatory | +0.242 |
eenth | +0.226 |
enance | +0.224 |
alities | +0.223 |
Neg logit contributions | |
iler | -0.220 |
ilers | -0.192 |
fter | -0.190 |
ghan | -0.180 |
lder | -0.170 |
Token | drives |
Token ID | 10182 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
iler | +0.496 |
ilers | +0.439 |
fter | +0.434 |
ghan | +0.413 |
lder | +0.393 |
Neg logit contributions | |
ioned | -0.459 |
inatory | -0.444 |
eenth | -0.411 |
enance | -0.408 |
alities | -0.405 |
Token | the |
Token ID | 262 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
iler | +1.044 |
ilers | +0.899 |
fter | +0.895 |
ghan | +0.844 |
lder | +0.795 |
Neg logit contributions | |
ioned | -1.274 |
inatory | -1.240 |
eenth | -1.161 |
enance | -1.141 |
atural | -1.141 |
Token | sheet |
Token ID | 9629 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
iler | +0.376 |
ilers | +0.327 |
fter | +0.321 |
ghan | +0.304 |
lder | +0.286 |
Neg logit contributions | |
ioned | -0.483 |
inatory | -0.469 |
eenth | -0.440 |
enance | -0.437 |
alities | -0.435 |
Token | of |
Token ID | 286 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
iler | +0.321 |
ilers | +0.278 |
fter | +0.275 |
ghan | +0.260 |
lder | +0.246 |
Neg logit contributions | |
ioned | -0.386 |
inatory | -0.376 |
eenth | -0.350 |
enance | -0.347 |
alities | -0.346 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
ioned | +2.226 |
inatory | +2.141 |
enance | +1.987 |
eenth | +1.977 |
alities | +1.968 |
Neg logit contributions | |
iler | -2.257 |
ilers | -2.022 |
fter | -1.976 |
ghan | -1.893 |
llor | -1.794 |
Token | backwards |
Token ID | 16196 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
iler | +9.420 |
fter | +7.841 |
ilers | +7.546 |
ghan | +7.103 |
thereof | +7.045 |
Neg logit contributions | |
ioned | -12.476 |
inatory | -12.414 |
HCR | -11.501 |
inators | -11.480 |
atural | -11.460 |
Token | and |
Token ID | 290 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
iler | +1.917 |
ilers | +1.658 |
fter | +1.643 |
ghan | +1.550 |
lder | +1.459 |
Neg logit contributions | |
ioned | -2.264 |
inatory | -2.192 |
eenth | -2.047 |
atural | -2.016 |
enance | -2.016 |
Token | inland |
Token ID | 37874 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ioned | +0.546 |
inatory | +0.529 |
eenth | +0.495 |
enance | +0.492 |
alities | +0.489 |
Neg logit contributions | |
iler | -0.438 |
ilers | -0.379 |
fter | -0.376 |
ghan | -0.353 |
lder | -0.333 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
iler | +1.629 |
ilers | +1.413 |
fter | +1.401 |
ghan | +1.327 |
lder | +1.247 |
Neg logit contributions | |
ioned | -1.909 |
inatory | -1.852 |
eenth | -1.730 |
enance | -1.706 |
alities | -1.700 |
Token | � |
Token ID | 564 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
iler | +0.898 |
ilers | +0.781 |
fter | +0.775 |
ghan | +0.735 |
lder | +0.695 |
Neg logit contributions | |
ioned | -1.022 |
inatory | -0.994 |
eenth | -0.921 |
enance | -0.916 |
alities | -0.913 |
Token | 39 |
Token ID | 2670 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ioned | +5.309 |
inatory | +5.100 |
eenth | +4.752 |
atural | +4.695 |
alities | +4.648 |
Neg logit contributions | |
iler | -5.619 |
ilers | -5.057 |
fter | -4.863 |
ghan | -4.674 |
llor | -4.511 |
Token | gig |
Token ID | 12526 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ioned | +3.673 |
inatory | +3.537 |
eenth | +3.273 |
atural | +3.237 |
enance | +3.219 |
Neg logit contributions | |
iler | -4.266 |
ilers | -3.826 |
fter | -3.724 |
ghan | -3.580 |
llor | -3.455 |
Token | at |
Token ID | 265 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ioned | +1.517 |
inatory | +1.455 |
eenth | +1.332 |
enance | +1.316 |
alities | +1.311 |
Neg logit contributions | |
iler | -2.132 |
ilers | -1.922 |
fter | -1.899 |
ghan | -1.825 |
lder | -1.749 |
Token | ons |
Token ID | 684 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ioned | +2.044 |
inatory | +1.961 |
eenth | +1.824 |
enance | +1.802 |
alities | +1.792 |
Neg logit contributions | |
iler | -2.494 |
ilers | -2.233 |
fter | -2.212 |
ghan | -2.128 |
llor | -2.013 |
Token | of |
Token ID | 286 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
iler | +1.173 |
ilers | +1.002 |
fter | +0.990 |
ghan | +0.926 |
lder | +0.869 |
Neg logit contributions | |
ioned | -1.679 |
inatory | -1.636 |
eenth | -1.535 |
enance | -1.525 |
alities | -1.522 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
ioned | +0.601 |
inatory | +0.578 |
eenth | +0.538 |
enance | +0.537 |
alities | +0.532 |
Neg logit contributions | |
iler | -0.588 |
ilers | -0.523 |
fter | -0.512 |
ghan | -0.489 |
llor | -0.463 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
iler | +9.353 |
fter | +7.897 |
ilers | +7.859 |
ghan | +7.338 |
lder | +7.033 |
Neg logit contributions | |
inatory | -12.892 |
ioned | -12.575 |
inators | -11.800 |
eenth | -11.787 |
nesday | -11.734 |
Token | and |
Token ID | 290 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
iler | +1.024 |
ilers | +0.898 |
fter | +0.889 |
ghan | +0.843 |
lder | +0.801 |
Neg logit contributions | |
ioned | -1.097 |
inatory | -1.064 |
eenth | -0.990 |
enance | -0.983 |
alities | -0.975 |
Token | approximately |
Token ID | 6702 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ioned | +0.050 |
inatory | +0.048 |
eenth | +0.045 |
enance | +0.045 |
alities | +0.045 |
Neg logit contributions | |
iler | -0.045 |
ilers | -0.039 |
fter | -0.039 |
ghan | -0.037 |
lder | -0.035 |
Token | 30 |
Token ID | 1542 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
iler | +1.620 |
ilers | +1.402 |
fter | +1.385 |
ghan | +1.309 |
lder | +1.235 |
Neg logit contributions | |
ioned | -2.069 |
inatory | -2.018 |
eenth | -1.891 |
enance | -1.872 |
alities | -1.862 |
Token | percent |
Token ID | 1411 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
ioned | +2.005 |
inatory | +1.939 |
eenth | +1.796 |
enance | +1.773 |
atural | +1.771 |
Neg logit contributions | |
iler | -2.155 |
ilers | -1.918 |
fter | -1.885 |
ghan | -1.803 |
lder | -1.715 |
Token | is |
Token ID | 318 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ioned | +0.333 |
inatory | +0.322 |
eenth | +0.301 |
enance | +0.298 |
alities | +0.296 |
Neg logit contributions | |
iler | -0.325 |
ilers | -0.286 |
fter | -0.282 |
ghan | -0.268 |
lder | -0.255 |
Token | more |
Token ID | 517 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
iler | +1.649 |
ilers | +1.404 |
fter | +1.390 |
ghan | +1.308 |
lder | +1.237 |
Neg logit contributions | |
ioned | -2.278 |
inatory | -2.229 |
eenth | -2.096 |
enance | -2.070 |
alities | -2.064 |
Token | fat |
Token ID | 3735 |
Feature activation | -9.92e+00 |
Pos logit contributions | |
iler | +1.784 |
ilers | +1.514 |
fter | +1.493 |
ghan | +1.417 |
lder | +1.331 |
Neg logit contributions | |
ioned | -2.433 |
inatory | -2.392 |
eenth | -2.247 |
atural | -2.221 |
enance | -2.214 |
Token | and |
Token ID | 290 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
iler | +6.462 |
ilers | +5.406 |
fter | +5.209 |
ghan | +4.908 |
lder | +4.669 |
Neg logit contributions | |
inatory | -9.417 |
ioned | -9.269 |
atural | -8.835 |
eenth | -8.764 |
nesday | -8.696 |
Token | less |
Token ID | 1342 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ioned | +0.238 |
inatory | +0.231 |
eenth | +0.216 |
enance | +0.214 |
alities | +0.213 |
Neg logit contributions | |
iler | -0.197 |
ilers | -0.171 |
fter | -0.169 |
ghan | -0.160 |
lder | -0.151 |
Token | glucose |
Token ID | 15701 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
iler | +1.729 |
ilers | +1.449 |
fter | +1.432 |
ghan | +1.356 |
lder | +1.284 |
Neg logit contributions | |
ioned | -2.448 |
inatory | -2.419 |
eenth | -2.272 |
atural | -2.253 |
enance | -2.233 |
Token | available |
Token ID | 1695 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
iler | +8.930 |
ilers | +7.451 |
fter | +7.137 |
ghan | +6.633 |
lder | +6.563 |
Neg logit contributions | |
inatory | -13.046 |
ioned | -12.757 |
atural | -12.318 |
nesday | -12.168 |
eenth | -12.033 |
Token | at |
Token ID | 379 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
iler | +0.683 |
ilers | +0.597 |
fter | +0.588 |
ghan | +0.558 |
lder | +0.527 |
Neg logit contributions | |
ioned | -0.795 |
inatory | -0.773 |
eenth | -0.722 |
enance | -0.716 |
alities | -0.713 |
Token | all |
Token ID | 477 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
ioned | +3.523 |
inatory | +3.415 |
eenth | +3.171 |
enance | +3.164 |
alities | +3.145 |
Neg logit contributions | |
iler | -3.110 |
ilers | -2.731 |
fter | -2.726 |
ghan | -2.580 |
llor | -2.441 |
Token | times |
Token ID | 1661 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
iler | +0.495 |
ilers | +0.447 |
fter | +0.440 |
ghan | +0.422 |
lder | +0.405 |
Neg logit contributions | |
ioned | -0.346 |
inatory | -0.335 |
eenth | -0.308 |
enance | -0.304 |
alities | -0.301 |
Token | , |
Token ID | 11 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
iler | +1.870 |
ilers | +1.628 |
fter | +1.602 |
ghan | +1.522 |
lder | +1.431 |
Neg logit contributions | |
ioned | -2.254 |
inatory | -2.199 |
eenth | -2.052 |
enance | -2.032 |
atural | -2.025 |
Token | ( |
Token ID | 7 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
iler | +3.787 |
ilers | +3.313 |
fter | +3.287 |
ghan | +3.119 |
lder | +2.973 |
Neg logit contributions | |
ioned | -4.115 |
inatory | -4.006 |
eenth | -3.720 |
atural | -3.686 |
enance | -3.686 |
Token | 77 |
Token ID | 3324 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
iler | +3.169 |
ilers | +2.734 |
fter | +2.688 |
ghan | +2.557 |
lder | +2.421 |
Neg logit contributions | |
ioned | -4.081 |
inatory | -3.977 |
eenth | -3.702 |
enance | -3.691 |
alities | -3.688 |
Token | s |
Token ID | 82 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ioned | +3.644 |
inatory | +3.417 |
eenth | +3.186 |
bugs | +3.138 |
tons | +3.122 |
Neg logit contributions | |
iler | -8.364 |
ilers | -7.599 |
fter | -7.454 |
ghan | -7.226 |
llor | -7.114 |
Token | )} |
Token ID | 38165 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ioned | +1.169 |
inatory | +1.126 |
eenth | +1.058 |
enance | +1.045 |
alities | +1.032 |
Neg logit contributions | |
iler | -1.337 |
ilers | -1.199 |
fter | -1.160 |
ghan | -1.137 |
lder | -1.066 |
Token | f |
Token ID | 277 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
iler | +1.705 |
ilers | +1.482 |
fter | +1.462 |
ghan | +1.384 |
lder | +1.305 |
Neg logit contributions | |
ioned | -2.116 |
inatory | -2.057 |
eenth | -1.926 |
enance | -1.910 |
alities | -1.901 |
Token | xe |
Token ID | 27705 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
iler | +2.995 |
ilers | +2.449 |
fter | +2.373 |
ghan | +2.240 |
lder | +2.071 |
Neg logit contributions | |
ioned | -6.078 |
inatory | -5.965 |
eenth | -5.637 |
alities | -5.624 |
enance | -5.605 |
Token | 6 |
Token ID | 21 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
iler | +5.377 |
ilers | +3.811 |
ghan | +3.809 |
fter | +3.698 |
lder | +3.273 |
Neg logit contributions | |
ioned | -16.753 |
inatory | -16.475 |
eenth | -15.810 |
alities | -15.681 |
enance | -15.639 |
Token | { |
Token ID | 1391 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
iler | +2.277 |
ilers | +1.970 |
fter | +1.944 |
ghan | +1.835 |
lder | +1.729 |
Neg logit contributions | |
ioned | -2.964 |
inatory | -2.882 |
eenth | -2.701 |
enance | -2.682 |
alities | -2.669 |
Token | ( |
Token ID | 7 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
iler | +3.724 |
ilers | +3.258 |
fter | +3.234 |
ghan | +3.067 |
lder | +2.922 |
Neg logit contributions | |
ioned | -4.048 |
inatory | -3.943 |
eenth | -3.661 |
atural | -3.627 |
enance | -3.626 |
Token | 6 |
Token ID | 21 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
iler | +3.126 |
ilers | +2.697 |
fter | +2.647 |
ghan | +2.519 |
lder | +2.385 |
Neg logit contributions | |
ioned | -4.047 |
inatory | -3.940 |
eenth | -3.671 |
enance | -3.661 |
alities | -3.654 |
Token | s |
Token ID | 82 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
iler | +2.354 |
ilers | +2.134 |
fter | +2.099 |
ghan | +2.026 |
lder | +1.942 |
Neg logit contributions | |
ioned | -1.637 |
inatory | -1.585 |
enance | -1.449 |
atural | -1.429 |
eenth | -1.426 |
Token | ' |
Token ID | 6 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
ioned | +3.078 |
inatory | +2.986 |
eenth | +2.795 |
atural | +2.759 |
enance | +2.751 |
Neg logit contributions | |
iler | -2.575 |
ilers | -2.272 |
fter | -2.216 |
ghan | -2.109 |
llor | -1.988 |
Token | wing |
Token ID | 8539 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
iler | +1.686 |
ilers | +1.441 |
fter | +1.421 |
ghan | +1.338 |
lder | +1.261 |
Neg logit contributions | |
ioned | -2.255 |
inatory | -2.197 |
eenth | -2.063 |
enance | -2.055 |
alities | -2.041 |
Token | span |
Token ID | 11506 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
iler | +4.332 |
fter | +3.559 |
ilers | +3.554 |
ghan | +3.251 |
lder | +3.139 |
Neg logit contributions | |
ioned | -6.726 |
inatory | -6.673 |
eenth | -6.239 |
alities | -6.200 |
enance | -6.199 |
Token | and |
Token ID | 290 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
iler | +1.689 |
ilers | +1.473 |
fter | +1.458 |
ghan | +1.385 |
lder | +1.313 |
Neg logit contributions | |
ioned | -1.824 |
inatory | -1.781 |
eenth | -1.655 |
enance | -1.636 |
alities | -1.632 |
Token | a |
Token ID | 257 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ioned | +1.386 |
inatory | +1.330 |
enance | +1.246 |
eenth | +1.243 |
alities | +1.235 |
Neg logit contributions | |
iler | -1.197 |
ilers | -1.059 |
fter | -1.035 |
ghan | -0.987 |
lder | -0.928 |
Token | fu |
Token ID | 14035 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
iler | +1.982 |
ilers | +1.699 |
fter | +1.676 |
ghan | +1.582 |
lder | +1.490 |
Neg logit contributions | |
ioned | -2.640 |
inatory | -2.573 |
eenth | -2.417 |
enance | -2.396 |
alities | -2.387 |
Token | selage |
Token ID | 45217 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
iler | +3.944 |
fter | +2.298 |
ilers | +2.072 |
lder | +1.735 |
ghan | +1.581 |
Neg logit contributions | |
inatory | -18.354 |
ioned | -18.342 |
enance | -18.107 |
eenth | -17.960 |
alities | -17.853 |
Token | about |
Token ID | 546 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
iler | +5.257 |
fter | +4.406 |
ilers | +4.339 |
ghan | +4.114 |
lder | +3.913 |
Neg logit contributions | |
ioned | -7.018 |
inatory | -6.999 |
eenth | -6.578 |
atural | -6.457 |
alities | -6.415 |
Token | 5 |
Token ID | 642 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
iler | +0.228 |
ilers | +0.200 |
fter | +0.196 |
ghan | +0.185 |
llor | +0.174 |
Neg logit contributions | |
ioned | -0.273 |
inatory | -0.264 |
eenth | -0.247 |
enance | -0.246 |
alities | -0.244 |
Token | ' |
Token ID | 6 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
ioned | +3.307 |
inatory | +3.206 |
eenth | +2.980 |
atural | +2.952 |
alities | +2.949 |
Neg logit contributions | |
iler | -2.578 |
ilers | -2.258 |
fter | -2.204 |
ghan | -2.100 |
llor | -1.975 |
Token | wide |
Token ID | 3094 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
iler | +3.277 |
ilers | +2.800 |
fter | +2.774 |
ghan | +2.608 |
lder | +2.461 |
Neg logit contributions | |
ioned | -4.305 |
inatory | -4.195 |
enance | -3.951 |
eenth | -3.937 |
alities | -3.904 |
Token | of |
Token ID | 286 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
iler | +3.897 |
ilers | +3.183 |
fter | +3.174 |
ghan | +2.972 |
lder | +2.796 |
Neg logit contributions | |
ioned | -6.623 |
inatory | -6.509 |
eenth | -6.099 |
enance | -6.035 |
atural | -6.018 |
Token | 26 |
Token ID | 2608 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
ioned | +0.912 |
inatory | +0.884 |
eenth | +0.822 |
enance | +0.821 |
alities | +0.815 |
Neg logit contributions | |
iler | -0.802 |
ilers | -0.705 |
fter | -0.694 |
ghan | -0.658 |
lder | -0.620 |
Token | km |
Token ID | 10571 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
ioned | +3.917 |
inatory | +3.778 |
eenth | +3.503 |
atural | +3.467 |
alities | +3.434 |
Neg logit contributions | |
iler | -4.252 |
ilers | -3.813 |
fter | -3.721 |
ghan | -3.559 |
llor | -3.440 |
Token | ( |
Token ID | 357 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
iler | +3.515 |
ilers | +2.984 |
fter | +2.934 |
ghan | +2.807 |
lder | +2.636 |
Neg logit contributions | |
ioned | -4.648 |
inatory | -4.531 |
eenth | -4.241 |
enance | -4.205 |
alities | -4.203 |
Token | 16 |
Token ID | 1433 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
iler | +1.467 |
ilers | +1.267 |
fter | +1.248 |
ghan | +1.178 |
lder | +1.105 |
Neg logit contributions | |
ioned | -1.958 |
inatory | -1.903 |
eenth | -1.785 |
enance | -1.774 |
alities | -1.766 |
Token | mi |
Token ID | 21504 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
ioned | +0.257 |
inatory | +0.250 |
eenth | +0.234 |
enance | +0.232 |
alities | +0.231 |
Neg logit contributions | |
iler | -0.213 |
ilers | -0.186 |
fter | -0.183 |
ghan | -0.173 |
lder | -0.163 |
Token | ). |
Token ID | 737 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
iler | +6.702 |
ilers | +5.222 |
fter | +5.173 |
ghan | +4.737 |
llor | +4.271 |
Neg logit contributions | |
ioned | -15.369 |
inatory | -14.783 |
enance | -14.246 |
alities | -14.138 |
eenth | -14.044 |
Token | This |
Token ID | 770 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
iler | +1.106 |
ilers | +0.961 |
fter | +0.957 |
ghan | +0.903 |
lder | +0.861 |
Neg logit contributions | |
ioned | -1.236 |
inatory | -1.206 |
eenth | -1.115 |
enance | -1.112 |
alities | -1.112 |
Token | , |
Token ID | 11 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
ioned | +1.348 |
inatory | +1.304 |
eenth | +1.220 |
enance | +1.213 |
alities | +1.207 |
Neg logit contributions | |
iler | -1.142 |
ilers | -1.002 |
fter | -0.984 |
ghan | -0.933 |
lder | -0.880 |
Token | plus |
Token ID | 5556 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
iler | +2.007 |
ilers | +1.729 |
fter | +1.718 |
ghan | +1.608 |
lder | +1.517 |
Neg logit contributions | |
ioned | -2.557 |
inatory | -2.477 |
eenth | -2.321 |
enance | -2.313 |
alities | -2.295 |
Token | Bra |
Token ID | 9718 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
iler | +3.739 |
ilers | +3.179 |
fter | +3.165 |
ghan | +2.948 |
lder | +2.870 |
Neg logit contributions | |
ioned | -4.575 |
inatory | -4.467 |
eenth | -4.211 |
enance | -4.144 |
alities | -4.126 |
Token | burning |
Token ID | 9482 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
ioned | +1.376 |
inatory | +1.329 |
eenth | +1.245 |
enance | +1.242 |
alities | +1.228 |
Neg logit contributions | |
iler | -1.206 |
ilers | -1.064 |
fter | -1.047 |
ghan | -0.988 |
lder | -0.937 |
Token | sugar |
Token ID | 7543 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
iler | +2.278 |
ilers | +1.943 |
fter | +1.913 |
ghan | +1.831 |
lder | +1.732 |
Neg logit contributions | |
ioned | -2.889 |
inatory | -2.828 |
eenth | -2.662 |
atural | -2.625 |
alities | -2.621 |
Token | ( |
Token ID | 357 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
iler | +5.238 |
ilers | +4.557 |
fter | +4.498 |
ghan | +4.244 |
lder | +3.993 |
Neg logit contributions | |
ioned | -6.210 |
inatory | -6.020 |
eenth | -5.651 |
atural | -5.642 |
alities | -5.524 |
Token | gl |
Token ID | 4743 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
ioned | +0.712 |
inatory | +0.689 |
eenth | +0.641 |
enance | +0.637 |
alities | +0.633 |
Neg logit contributions | |
iler | -0.692 |
ilers | -0.611 |
fter | -0.602 |
ghan | -0.573 |
lder | -0.544 |
Token | uc |
Token ID | 1229 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
iler | +2.537 |
ilers | +2.248 |
fter | +2.171 |
ghan | +2.055 |
llor | +2.000 |
Neg logit contributions | |
ioned | -2.193 |
inatory | -2.119 |
eenth | -1.956 |
enance | -1.953 |
atural | -1.948 |
Token | ose |
Token ID | 577 |
Feature activation | -1.40e+01 |
Pos logit contributions | |
iler | +1.959 |
ilers | +1.612 |
fter | +1.562 |
ghan | +1.458 |
lder | +1.300 |
Neg logit contributions | |
ioned | -3.816 |
inatory | -3.692 |
eenth | -3.543 |
enance | -3.517 |
atural | -3.506 |
Token | ) |
Token ID | 8 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
iler | +9.761 |
fter | +8.453 |
ilers | +8.354 |
ghan | +7.616 |
lder | +7.563 |
Neg logit contributions | |
ioned | -11.708 |
inatory | -11.510 |
eenth | -11.052 |
atural | -11.035 |
nesday | -10.833 |
Token | from |
Token ID | 422 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
iler | +2.452 |
ilers | +2.155 |
fter | +2.107 |
ghan | +2.011 |
lder | +1.895 |
Neg logit contributions | |
ioned | -2.678 |
inatory | -2.586 |
eenth | -2.415 |
enance | -2.391 |
atural | -2.390 |
Token | the |
Token ID | 262 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
iler | +0.856 |
ilers | +0.741 |
fter | +0.729 |
ghan | +0.691 |
lder | +0.654 |
Neg logit contributions | |
ioned | -1.053 |
inatory | -1.023 |
eenth | -0.963 |
atural | -0.945 |
enance | -0.945 |
Token | fed |
Token ID | 11672 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
iler | +2.144 |
ilers | +1.823 |
fter | +1.799 |
ghan | +1.690 |
lder | +1.605 |
Neg logit contributions | |
ioned | -2.934 |
inatory | -2.824 |
eenth | -2.689 |
atural | -2.648 |
alities | -2.626 |
Token | state |
Token ID | 1181 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
iler | +2.564 |
ilers | +2.081 |
fter | +2.046 |
ghan | +1.944 |
lder | +1.747 |
Neg logit contributions | |
ioned | -4.861 |
inatory | -4.696 |
eenth | -4.490 |
atural | -4.424 |
alities | -4.407 |
Token | losing |
Token ID | 6078 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
iler | +0.688 |
ilers | +0.594 |
fter | +0.587 |
ghan | +0.555 |
lder | +0.521 |
Neg logit contributions | |
ioned | -0.890 |
inatory | -0.865 |
eenth | -0.812 |
enance | -0.805 |
alities | -0.802 |
Token | 75 |
Token ID | 5441 |
Feature activation | +9.17e+00 |
Pos logit contributions | |
iler | +2.857 |
ilers | +2.460 |
fter | +2.445 |
ghan | +2.300 |
lder | +2.194 |
Neg logit contributions | |
ioned | -3.552 |
inatory | -3.471 |
eenth | -3.270 |
enance | -3.208 |
atural | -3.187 |
Token | billion |
Token ID | 2997 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ioned | +7.065 |
inatory | +6.896 |
atural | +6.365 |
tons | +6.347 |
eenth | +6.253 |
Neg logit contributions | |
iler | -7.705 |
ilers | -6.922 |
fter | -6.676 |
ghan | -6.458 |
llor | -6.240 |
Token | tons |
Token ID | 10860 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ioned | +0.190 |
inatory | +0.184 |
eenth | +0.169 |
enance | +0.168 |
alities | +0.166 |
Neg logit contributions | |
iler | -0.234 |
ilers | -0.209 |
fter | -0.206 |
ghan | -0.198 |
lder | -0.189 |
Token | of |
Token ID | 286 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
iler | +1.403 |
ilers | +1.190 |
fter | +1.174 |
ghan | +1.096 |
lder | +1.022 |
Neg logit contributions | |
ioned | -2.133 |
inatory | -2.083 |
eenth | -1.958 |
enance | -1.948 |
alities | -1.934 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
iler | +0.051 |
ilers | +0.044 |
fter | +0.044 |
ghan | +0.041 |
lder | +0.039 |
Neg logit contributions | |
ioned | -0.057 |
inatory | -0.055 |
eenth | -0.051 |
enance | -0.051 |
alities | -0.051 |
Token | every |
Token ID | 790 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
iler | +8.911 |
ilers | +7.568 |
fter | +7.534 |
ghan | +6.787 |
paste | +6.512 |
Neg logit contributions | |
inatory | -12.732 |
ioned | -12.652 |
eenth | -11.944 |
enance | -11.806 |
atural | -11.639 |
Token | year |
Token ID | 614 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
iler | +0.932 |
ilers | +0.796 |
fter | +0.785 |
ghan | +0.737 |
lder | +0.693 |
Neg logit contributions | |
ioned | -1.314 |
inatory | -1.275 |
eenth | -1.197 |
enance | -1.195 |
alities | -1.188 |
Token | ] |
Token ID | 60 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
iler | +3.381 |
ilers | +2.882 |
fter | +2.867 |
ghan | +2.676 |
lder | +2.539 |
Neg logit contributions | |
ioned | -4.624 |
inatory | -4.500 |
eenth | -4.219 |
enance | -4.166 |
alities | -4.129 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
iler | +2.167 |
ilers | +1.883 |
fter | +1.860 |
ghan | +1.768 |
lder | +1.670 |
Neg logit contributions | |
ioned | -2.649 |
inatory | -2.580 |
eenth | -2.397 |
enance | -2.383 |
alities | -2.379 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
iler | +1.161 |
ilers | +1.029 |
fter | +1.006 |
ghan | +0.957 |
llor | +0.907 |
Neg logit contributions | |
ioned | -1.217 |
inatory | -1.175 |
eenth | -1.101 |
enance | -1.097 |
alities | -1.085 |
Token | and |
Token ID | 290 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
iler | +7.194 |
ilers | +6.221 |
fter | +6.217 |
ghan | +5.791 |
lder | +5.501 |
Neg logit contributions | |
ioned | -9.772 |
inatory | -9.318 |
enance | -8.895 |
eenth | -8.749 |
alities | -8.647 |
Token | the |
Token ID | 262 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
iler | +0.877 |
ilers | +0.760 |
fter | +0.750 |
ghan | +0.708 |
lder | +0.669 |
Neg logit contributions | |
ioned | -1.085 |
inatory | -1.051 |
eenth | -0.984 |
enance | -0.978 |
alities | -0.974 |
Token | corresponding |
Token ID | 11188 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
iler | +1.827 |
ilers | +1.565 |
fter | +1.547 |
ghan | +1.458 |
lder | +1.378 |
Neg logit contributions | |
ioned | -2.362 |
inatory | -2.287 |
eenth | -2.149 |
enance | -2.139 |
alities | -2.125 |
Token | flux |
Token ID | 28462 |
Feature activation | -9.91e+00 |
Pos logit contributions | |
iler | +0.309 |
ilers | +0.267 |
fter | +0.264 |
ghan | +0.249 |
lder | +0.234 |
Neg logit contributions | |
ioned | -0.401 |
inatory | -0.389 |
eenth | -0.365 |
enance | -0.363 |
alities | -0.361 |
Token | F |
Token ID | 376 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
iler | +7.467 |
ilers | +6.339 |
fter | +6.284 |
ghan | +5.880 |
lder | +5.664 |
Neg logit contributions | |
ioned | -8.317 |
inatory | -8.280 |
eenth | -7.769 |
enance | -7.754 |
alities | -7.574 |
Token | E |
Token ID | 412 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
iler | +4.370 |
ilers | +3.685 |
fter | +3.650 |
ghan | +3.444 |
lder | +3.198 |
Neg logit contributions | |
ioned | -6.030 |
inatory | -5.849 |
enance | -5.586 |
eenth | -5.537 |
alities | -5.502 |
Token | at |
Token ID | 379 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
iler | +9.254 |
fter | +7.989 |
ilers | +7.936 |
ghan | +7.581 |
thereof | +7.092 |
Neg logit contributions | |
ioned | -12.064 |
inatory | -11.470 |
enance | -10.947 |
eenth | -10.931 |
alities | -10.642 |
Token | the |
Token ID | 262 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ioned | +0.113 |
inatory | +0.110 |
eenth | +0.103 |
enance | +0.102 |
alities | +0.101 |
Neg logit contributions | |
iler | -0.094 |
ilers | -0.082 |
fter | -0.080 |
ghan | -0.076 |
lder | -0.072 |
Token | characteristic |
Token ID | 16704 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
iler | +1.434 |
ilers | +1.237 |
fter | +1.221 |
ghan | +1.149 |
lder | +1.091 |
Neg logit contributions | |
ioned | -1.833 |
inatory | -1.774 |
eenth | -1.669 |
enance | -1.654 |
alities | -1.647 |
Token | - |
Token ID | 12 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
iler | +0.485 |
ilers | +0.420 |
fter | +0.414 |
ghan | +0.391 |
lder | +0.371 |
Neg logit contributions | |
ioned | -0.599 |
inatory | -0.582 |
eenth | -0.546 |
enance | -0.541 |
atural | -0.537 |
Token | em |
Token ID | 368 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ioned | +1.108 |
inatory | +1.074 |
eenth | +1.003 |
enance | +0.996 |
alities | +0.991 |
Neg logit contributions | |
iler | -0.989 |
ilers | -0.868 |
fter | -0.856 |
ghan | -0.813 |
lder | -0.768 |
Token | drain |
Token ID | 14782 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
iler | +6.445 |
ilers | +5.429 |
fter | +5.347 |
ghan | +4.945 |
lder | +4.904 |
Neg logit contributions | |
ioned | -8.959 |
inatory | -8.791 |
eenth | -8.159 |
atural | -8.087 |
enance | -8.070 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
iler | +2.707 |
ilers | +2.330 |
fter | +2.310 |
ghan | +2.188 |
lder | +2.096 |
Neg logit contributions | |
ioned | -3.353 |
inatory | -3.283 |
eenth | -3.058 |
atural | -3.023 |
alities | -3.021 |
Token | from |
Token ID | 422 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
iler | +7.758 |
ilers | +6.681 |
fter | +6.600 |
ghan | +6.142 |
lder | +6.048 |
Neg logit contributions | |
ioned | -10.311 |
inatory | -10.222 |
atural | -9.390 |
eenth | -9.370 |
enance | -9.369 |
Token | the |
Token ID | 262 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
iler | +0.427 |
ilers | +0.374 |
fter | +0.368 |
ghan | +0.351 |
lder | +0.332 |
Neg logit contributions | |
ioned | -0.488 |
inatory | -0.474 |
eenth | -0.443 |
enance | -0.438 |
alities | -0.435 |
Token | central |
Token ID | 4318 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
iler | +2.016 |
ilers | +1.737 |
fter | +1.717 |
ghan | +1.638 |
lder | +1.550 |
Neg logit contributions | |
ioned | -2.504 |
inatory | -2.432 |
eenth | -2.287 |
enance | -2.258 |
atural | -2.254 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
ioned | +0.992 |
inatory | +0.961 |
alities | +0.898 |
eenth | +0.897 |
enance | +0.897 |
Neg logit contributions | |
iler | -0.846 |
ilers | -0.744 |
fter | -0.733 |
ghan | -0.689 |
llor | -0.654 |
Token | sheet |
Token ID | 9629 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
iler | +8.044 |
ilers | +6.534 |
fter | +6.505 |
ghan | +6.453 |
lder | +5.992 |
Neg logit contributions | |
ioned | -13.281 |
inatory | -13.187 |
enance | -12.370 |
nesday | -12.369 |
HCR | -12.247 |
Token | ; |
Token ID | 26 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
iler | +2.205 |
ilers | +1.920 |
fter | +1.898 |
ghan | +1.804 |
lder | +1.719 |
Neg logit contributions | |
ioned | -2.467 |
inatory | -2.403 |
eenth | -2.239 |
enance | -2.217 |
atural | -2.210 |
Token | but |
Token ID | 475 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
iler | +1.622 |
ilers | +1.416 |
fter | +1.401 |
ghan | +1.325 |
lder | +1.265 |
Neg logit contributions | |
ioned | -1.863 |
inatory | -1.803 |
eenth | -1.683 |
enance | -1.670 |
alities | -1.656 |
Token | even |
Token ID | 772 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
iler | +1.477 |
ilers | +1.291 |
fter | +1.281 |
ghan | +1.209 |
lder | +1.153 |
Neg logit contributions | |
ioned | -1.666 |
inatory | -1.617 |
eenth | -1.507 |
enance | -1.490 |
alities | -1.484 |
Token | in |
Token ID | 287 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
iler | +1.276 |
ilers | +1.113 |
fter | +1.106 |
ghan | +1.045 |
lder | +0.996 |
Neg logit contributions | |
ioned | -1.412 |
inatory | -1.374 |
eenth | -1.278 |
enance | -1.268 |
atural | -1.260 |
Token | of |
Token ID | 286 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
iler | +0.464 |
ilers | +0.399 |
fter | +0.393 |
ghan | +0.370 |
lder | +0.347 |
Neg logit contributions | |
ioned | -0.650 |
inatory | -0.633 |
eenth | -0.595 |
enance | -0.592 |
alities | -0.588 |
Token | balance |
Token ID | 5236 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
ioned | +0.971 |
inatory | +0.943 |
eenth | +0.885 |
enance | +0.878 |
alities | +0.876 |
Neg logit contributions | |
iler | -0.725 |
ilers | -0.627 |
fter | -0.618 |
ghan | -0.583 |
lder | -0.545 |
Token | , |
Token ID | 11 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
iler | +2.845 |
ilers | +2.468 |
fter | +2.438 |
ghan | +2.333 |
lder | +2.197 |
Neg logit contributions | |
ioned | -3.363 |
inatory | -3.294 |
eenth | -3.074 |
enance | -3.037 |
alities | -3.033 |
Token | losing |
Token ID | 6078 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
iler | +0.285 |
ilers | +0.249 |
fter | +0.246 |
ghan | +0.234 |
lder | +0.221 |
Neg logit contributions | |
ioned | -0.321 |
inatory | -0.311 |
eenth | -0.291 |
enance | -0.289 |
alities | -0.287 |
Token | more |
Token ID | 517 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
iler | +2.102 |
ilers | +1.815 |
fter | +1.799 |
ghan | +1.705 |
lder | +1.622 |
Neg logit contributions | |
ioned | -2.531 |
inatory | -2.468 |
eenth | -2.316 |
atural | -2.269 |
enance | -2.267 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
iler | +1.471 |
ilers | +1.283 |
fter | +1.269 |
ghan | +1.205 |
lder | +1.148 |
Neg logit contributions | |
ioned | -1.633 |
inatory | -1.592 |
eenth | -1.486 |
enance | -1.465 |
atural | -1.462 |
Token | than |
Token ID | 621 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
iler | +8.603 |
ilers | +7.348 |
fter | +7.222 |
ghan | +6.795 |
lder | +6.495 |
Neg logit contributions | |
inatory | -12.533 |
ioned | -12.451 |
eenth | -11.598 |
atural | -11.551 |
enance | -11.526 |
Token | it |
Token ID | 340 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
iler | +1.366 |
ilers | +1.178 |
fter | +1.168 |
ghan | +1.095 |
lder | +1.044 |
Neg logit contributions | |
ioned | -1.757 |
inatory | -1.714 |
eenth | -1.604 |
enance | -1.590 |
alities | -1.583 |
Token | gains |
Token ID | 8810 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
ioned | +0.180 |
inatory | +0.174 |
eenth | +0.163 |
enance | +0.162 |
alities | +0.161 |
Neg logit contributions | |
iler | -0.156 |
ilers | -0.136 |
fter | -0.134 |
ghan | -0.127 |
lder | -0.120 |
Token | , |
Token ID | 11 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
iler | +5.434 |
ilers | +4.648 |
fter | +4.561 |
ghan | +4.315 |
lder | +4.101 |
Neg logit contributions | |
ioned | -7.064 |
inatory | -7.006 |
eenth | -6.476 |
enance | -6.397 |
alities | -6.390 |
Token | � |
Token ID | 447 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
iler | +0.789 |
ilers | +0.694 |
fter | +0.686 |
ghan | +0.654 |
lder | +0.622 |
Neg logit contributions | |
ioned | -0.794 |
inatory | -0.767 |
eenth | -0.713 |
enance | -0.712 |
alities | -0.701 |
Token | the |
Token ID | 262 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
iler | +0.586 |
ilers | +0.511 |
fter | +0.504 |
ghan | +0.478 |
lder | +0.452 |
Neg logit contributions | |
ioned | -0.686 |
inatory | -0.666 |
eenth | -0.622 |
enance | -0.617 |
alities | -0.613 |
Token | j |
Token ID | 474 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
iler | +0.665 |
ilers | +0.576 |
fter | +0.568 |
ghan | +0.537 |
lder | +0.506 |
Neg logit contributions | |
ioned | -0.841 |
inatory | -0.817 |
eenth | -0.766 |
enance | -0.760 |
alities | -0.756 |
Token | umble |
Token ID | 10344 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ioned | +2.167 |
inatory | +2.105 |
eenth | +1.929 |
enance | +1.922 |
alities | +1.913 |
Neg logit contributions | |
iler | -2.667 |
ilers | -2.393 |
fter | -2.385 |
ghan | -2.277 |
llor | -2.172 |
Token | of |
Token ID | 286 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
ioned | +1.193 |
inatory | +1.159 |
eenth | +1.089 |
enance | +1.083 |
alities | +1.078 |
Neg logit contributions | |
iler | -0.855 |
ilers | -0.737 |
fter | -0.724 |
ghan | -0.682 |
lder | -0.639 |
Token | floating |
Token ID | 12462 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ioned | +3.125 |
inatory | +3.015 |
alities | +2.845 |
enance | +2.822 |
eenth | +2.796 |
Neg logit contributions | |
iler | -2.799 |
ilers | -2.484 |
fter | -2.432 |
ghan | -2.314 |
llor | -2.218 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
iler | +1.829 |
ilers | +1.606 |
fter | +1.595 |
ghan | +1.517 |
lder | +1.454 |
Neg logit contributions | |
ioned | -1.835 |
inatory | -1.795 |
eenth | -1.666 |
atural | -1.641 |
enance | -1.632 |
Token | downstream |
Token ID | 33218 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
iler | +10.405 |
ilers | +9.160 |
fter | +9.029 |
ghan | +8.471 |
lder | +8.266 |
Neg logit contributions | |
ioned | -10.480 |
inatory | -10.301 |
eenth | -9.614 |
enance | -9.457 |
atural | -9.375 |
Token | from |
Token ID | 422 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
iler | +3.571 |
ilers | +3.101 |
fter | +3.059 |
ghan | +2.919 |
lder | +2.753 |
Neg logit contributions | |
ioned | -4.023 |
inatory | -3.920 |
eenth | -3.637 |
atural | -3.613 |
enance | -3.579 |
Token | the |
Token ID | 262 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
iler | +0.554 |
ilers | +0.484 |
fter | +0.476 |
ghan | +0.453 |
lder | +0.429 |
Neg logit contributions | |
ioned | -0.637 |
inatory | -0.619 |
eenth | -0.580 |
enance | -0.571 |
alities | -0.569 |
Token | glacier |
Token ID | 44539 |
Feature activation | -9.05e+00 |
Pos logit contributions | |
iler | +2.782 |
ilers | +2.348 |
fter | +2.324 |
ghan | +2.213 |
lder | +2.102 |
Neg logit contributions | |
ioned | -3.798 |
inatory | -3.695 |
eenth | -3.490 |
atural | -3.446 |
enance | -3.428 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
iler | +7.010 |
ilers | +5.928 |
fter | +5.921 |
ghan | +5.580 |
lder | +5.378 |
Neg logit contributions | |
ioned | -7.686 |
inatory | -7.504 |
eenth | -7.066 |
atural | -6.982 |
HCR | -6.807 |
Token | ( |
Token ID | 7 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
iler | +2.511 |
ilers | +2.221 |
fter | +2.188 |
ghan | +2.085 |
lder | +1.976 |
Neg logit contributions | |
ioned | -2.532 |
inatory | -2.445 |
eenth | -2.277 |
enance | -2.262 |
alities | -2.245 |
Token | 16 |
Token ID | 1433 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
iler | +2.652 |
ilers | +2.294 |
fter | +2.253 |
ghan | +2.144 |
lder | +2.030 |
Neg logit contributions | |
ioned | -3.312 |
inatory | -3.225 |
eenth | -3.009 |
alities | -2.988 |
enance | -2.985 |
Token | s |
Token ID | 82 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
iler | +0.983 |
ilers | +0.889 |
fter | +0.880 |
ghan | +0.850 |
lder | +0.811 |
Neg logit contributions | |
ioned | -0.654 |
inatory | -0.627 |
enance | -0.566 |
eenth | -0.564 |
atural | -0.555 |
Token | )} |
Token ID | 38165 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
iler | +1.643 |
ilers | +1.453 |
fter | +1.429 |
ghan | +1.366 |
lder | +1.293 |
Neg logit contributions | |
ioned | -1.656 |
inatory | -1.602 |
eenth | -1.493 |
enance | -1.481 |
alities | -1.471 |
Token | g |
Token ID | 308 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
iler | +3.084 |
ilers | +2.657 |
fter | +2.632 |
ghan | +2.486 |
lder | +2.348 |
Neg logit contributions | |
ioned | -4.147 |
inatory | -4.047 |
eenth | -3.796 |
enance | -3.747 |
atural | -3.747 |
Token | xf |
Token ID | 26152 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
iler | +2.744 |
ilers | +2.303 |
fter | +2.254 |
ghan | +2.125 |
lder | +1.992 |
Neg logit contributions | |
ioned | -4.766 |
inatory | -4.662 |
eenth | -4.388 |
enance | -4.368 |
atural | -4.355 |
Token | 4 |
Token ID | 19 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
iler | +6.398 |
ghan | +5.005 |
ilers | +4.906 |
fter | +4.728 |
lder | +4.393 |
Neg logit contributions | |
ioned | -14.922 |
inatory | -14.713 |
alities | -14.056 |
atural | -13.902 |
eenth | -13.865 |
Token | { |
Token ID | 1391 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
iler | +1.059 |
ilers | +0.928 |
fter | +0.910 |
ghan | +0.862 |
llor | +0.815 |
Neg logit contributions | |
ioned | -1.262 |
inatory | -1.219 |
eenth | -1.145 |
enance | -1.137 |
alities | -1.133 |
Token | ( |
Token ID | 7 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
iler | +3.835 |
ilers | +3.351 |
fter | +3.326 |
ghan | +3.152 |
lder | +3.009 |
Neg logit contributions | |
ioned | -4.207 |
inatory | -4.101 |
eenth | -3.808 |
atural | -3.775 |
enance | -3.768 |
Token | 303 |
Token ID | 22572 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
iler | +3.537 |
ilers | +3.048 |
fter | +2.993 |
ghan | +2.855 |
lder | +2.699 |
Neg logit contributions | |
ioned | -4.584 |
inatory | -4.473 |
eenth | -4.161 |
alities | -4.144 |
atural | -4.138 |
Token | s |
Token ID | 82 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ioned | +1.776 |
inatory | +1.670 |
eenth | +1.519 |
alities | +1.500 |
bugs | +1.491 |
Neg logit contributions | |
iler | -3.559 |
ilers | -3.233 |
fter | -3.190 |
ghan | -3.089 |
llor | -3.001 |
Token | — |
Token ID | 851 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
ioned | +2.315 |
inatory | +2.238 |
eenth | +2.082 |
enance | +2.073 |
alities | +2.056 |
Neg logit contributions | |
iler | -2.225 |
ilers | -1.965 |
fter | -1.947 |
ghan | -1.840 |
lder | -1.758 |
Token | in |
Token ID | 287 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ioned | +0.576 |
inatory | +0.558 |
eenth | +0.521 |
enance | +0.517 |
alities | +0.514 |
Neg logit contributions | |
iler | -0.526 |
ilers | -0.462 |
fter | -0.455 |
ghan | -0.433 |
lder | -0.409 |
Token | Quebec |
Token ID | 14778 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
iler | +1.362 |
ilers | +1.183 |
fter | +1.161 |
ghan | +1.103 |
lder | +1.041 |
Neg logit contributions | |
ioned | -1.700 |
inatory | -1.649 |
eenth | -1.550 |
enance | -1.536 |
alities | -1.527 |
Token | and |
Token ID | 290 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
iler | +1.022 |
ilers | +0.899 |
fter | +0.879 |
ghan | +0.844 |
lder | +0.796 |
Neg logit contributions | |
ioned | -1.071 |
inatory | -1.036 |
eenth | -0.967 |
enance | -0.960 |
alities | -0.955 |
Token | a |
Token ID | 257 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
ioned | +1.889 |
inatory | +1.831 |
enance | +1.710 |
eenth | +1.707 |
alities | +1.698 |
Neg logit contributions | |
iler | -1.627 |
ilers | -1.424 |
fter | -1.403 |
ghan | -1.323 |
lder | -1.254 |
Token | fo |
Token ID | 11511 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
iler | +2.339 |
ilers | +2.004 |
fter | +1.987 |
ghan | +1.896 |
lder | +1.793 |
Neg logit contributions | |
ioned | -2.935 |
inatory | -2.858 |
eenth | -2.668 |
enance | -2.663 |
alities | -2.642 |
Token | iled |
Token ID | 3902 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
iler | +10.610 |
ilers | +8.931 |
ghan | +8.851 |
fter | +8.606 |
iling | +7.953 |
Neg logit contributions | |
ioned | -11.061 |
inatory | -10.753 |
eenth | -10.397 |
alities | -10.364 |
enance | -10.279 |
Token | attempt |
Token ID | 2230 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
ioned | +0.743 |
inatory | +0.719 |
eenth | +0.672 |
enance | +0.667 |
alities | +0.664 |
Neg logit contributions | |
iler | -0.657 |
ilers | -0.576 |
fter | -0.568 |
ghan | -0.538 |
lder | -0.510 |
Token | at |
Token ID | 379 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
ioned | +0.486 |
inatory | +0.474 |
eenth | +0.443 |
enance | +0.440 |
alities | +0.437 |
Neg logit contributions | |
iler | -0.406 |
ilers | -0.353 |
fter | -0.349 |
ghan | -0.331 |
lder | -0.311 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ioned | +3.973 |
inatory | +3.846 |
eenth | +3.566 |
enance | +3.541 |
alities | +3.540 |
Neg logit contributions | |
iler | -3.756 |
ilers | -3.327 |
fter | -3.318 |
ghan | -3.103 |
lder | -2.981 |
Token | B |
Token ID | 347 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
ioned | +1.140 |
inatory | +1.102 |
eenth | +1.026 |
enance | +1.020 |
alities | +1.017 |
Neg logit contributions | |
iler | -1.064 |
ilers | -0.940 |
fter | -0.929 |
ghan | -0.875 |
lder | -0.834 |
Token | ties |
Token ID | 8470 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
iler | +1.801 |
ilers | +1.582 |
fter | +1.574 |
ghan | +1.499 |
lder | +1.426 |
Neg logit contributions | |
ioned | -1.766 |
inatory | -1.715 |
eenth | -1.590 |
enance | -1.567 |
atural | -1.566 |
Token | as |
Token ID | 355 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
iler | +0.467 |
ilers | +0.406 |
fter | +0.401 |
ghan | +0.380 |
lder | +0.358 |
Neg logit contributions | |
ioned | -0.565 |
inatory | -0.548 |
eenth | -0.514 |
enance | -0.510 |
alities | -0.508 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
iler | +0.677 |
ilers | +0.579 |
fter | +0.576 |
ghan | +0.539 |
lder | +0.508 |
Neg logit contributions | |
ioned | -0.969 |
inatory | -0.943 |
eenth | -0.889 |
enance | -0.886 |
alities | -0.876 |
Token | most |
Token ID | 749 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
iler | +0.959 |
ilers | +0.831 |
fter | +0.821 |
ghan | +0.776 |
lder | +0.733 |
Neg logit contributions | |
ioned | -1.214 |
inatory | -1.179 |
eenth | -1.103 |
enance | -1.098 |
atural | -1.092 |
Token | expensive |
Token ID | 5789 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
iler | +3.087 |
ilers | +2.648 |
fter | +2.646 |
ghan | +2.469 |
lder | +2.363 |
Neg logit contributions | |
ioned | -3.959 |
inatory | -3.879 |
atural | -3.613 |
eenth | -3.613 |
alities | -3.590 |
Token | yo |
Token ID | 27406 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
iler | +1.097 |
ilers | +0.929 |
fter | +0.917 |
ghan | +0.858 |
lder | +0.807 |
Neg logit contributions | |
ioned | -1.696 |
inatory | -1.654 |
eenth | -1.553 |
enance | -1.543 |
atural | -1.540 |
Token | - |
Token ID | 12 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
iler | +8.203 |
ilers | +6.590 |
fter | +6.588 |
ghan | +6.282 |
lder | +5.737 |
Neg logit contributions | |
ioned | -13.562 |
inatory | -13.278 |
enance | -12.589 |
alities | -12.548 |
inators | -12.429 |
Token | yo |
Token ID | 8226 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
iler | +1.389 |
ilers | +1.168 |
fter | +1.149 |
ghan | +1.071 |
lder | +0.985 |
Neg logit contributions | |
ioned | -2.369 |
inatory | -2.312 |
eenth | -2.169 |
enance | -2.166 |
alities | -2.152 |
Token | in |
Token ID | 287 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
iler | +4.031 |
fter | +3.468 |
ilers | +3.447 |
ghan | +3.251 |
lder | +3.120 |
Neg logit contributions | |
ioned | -5.044 |
inatory | -4.980 |
atural | -4.578 |
eenth | -4.566 |
enance | -4.555 |
Token | this |
Token ID | 428 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
iler | +2.626 |
ilers | +2.270 |
fter | +2.262 |
ghan | +2.135 |
lder | +2.033 |
Neg logit contributions | |
ioned | -3.147 |
inatory | -3.026 |
eenth | -2.823 |
enance | -2.810 |
alities | -2.769 |
Token | shootout |
Token ID | 34995 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
iler | +0.623 |
ilers | +0.532 |
fter | +0.526 |
ghan | +0.493 |
lder | +0.463 |
Neg logit contributions | |
ioned | -0.896 |
inatory | -0.871 |
eenth | -0.821 |
enance | -0.814 |
alities | -0.808 |
Token | io |
Token ID | 952 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
iler | +2.477 |
ilers | +2.198 |
fter | +2.168 |
ghan | +2.081 |
lder | +1.978 |
Neg logit contributions | |
ioned | -2.147 |
inatory | -2.073 |
eenth | -1.916 |
enance | -1.893 |
alities | -1.890 |
Token | le |
Token ID | 293 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
iler | +4.257 |
fter | +3.635 |
ilers | +3.614 |
ghan | +3.480 |
lder | +3.217 |
Neg logit contributions | |
ioned | -5.986 |
inatory | -5.866 |
enance | -5.457 |
atural | -5.442 |
alities | -5.393 |
Token | k |
Token ID | 74 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
iler | +3.146 |
ilers | +2.698 |
fter | +2.695 |
ghan | +2.624 |
lder | +2.486 |
Neg logit contributions | |
ioned | -3.572 |
inatory | -3.502 |
atural | -3.298 |
eenth | -3.265 |
enance | -3.241 |
Token | ( |
Token ID | 357 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
ioned | +1.236 |
inatory | +1.199 |
eenth | +1.122 |
enance | +1.113 |
alities | +1.106 |
Neg logit contributions | |
iler | -1.039 |
ilers | -0.905 |
fter | -0.892 |
ghan | -0.847 |
lder | -0.799 |
Token | O |
Token ID | 46 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
iler | +3.121 |
ilers | +2.734 |
fter | +2.726 |
ghan | +2.597 |
lder | +2.432 |
Neg logit contributions | |
ioned | -3.358 |
inatory | -3.249 |
eenth | -2.996 |
enance | -2.985 |
atural | -2.983 |
Token | mega |
Token ID | 13731 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
iler | +4.571 |
ilers | +3.899 |
fter | +3.752 |
ghan | +3.450 |
lder | +3.293 |
Neg logit contributions | |
ioned | -8.586 |
inatory | -8.507 |
alities | -8.051 |
enance | -8.026 |
eenth | -7.977 |
Token | Pharma |
Token ID | 41845 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
iler | +7.205 |
fter | +6.199 |
ilers | +6.040 |
ghan | +5.407 |
lder | +5.127 |
Neg logit contributions | |
ioned | -14.601 |
inatory | -14.464 |
eenth | -13.790 |
atural | -13.604 |
nesday | -13.308 |
Token | - |
Token ID | 532 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
iler | +3.667 |
ilers | +3.015 |
fter | +2.999 |
ghan | +2.791 |
lder | +2.574 |
Neg logit contributions | |
ioned | -6.935 |
inatory | -6.771 |
eenth | -6.470 |
atural | -6.363 |
enance | -6.360 |
Token | Quick |
Token ID | 12029 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
iler | +0.977 |
ilers | +0.837 |
fter | +0.832 |
ghan | +0.778 |
lder | +0.730 |
Neg logit contributions | |
ioned | -1.352 |
inatory | -1.312 |
eenth | -1.231 |
enance | -1.224 |
atural | -1.217 |
Token | step |
Token ID | 9662 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
iler | +2.346 |
ilers | +1.668 |
fter | +1.614 |
ghan | +1.383 |
lder | +1.185 |
Neg logit contributions | |
ioned | -9.030 |
inatory | -8.875 |
atural | -8.407 |
eenth | -8.400 |
enance | -8.399 |
Token | ) |
Token ID | 8 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
iler | +2.173 |
ilers | +1.862 |
fter | +1.826 |
ghan | +1.714 |
lder | +1.600 |
Neg logit contributions | |
ioned | -3.244 |
inatory | -3.152 |
eenth | -2.971 |
enance | -2.955 |
alities | -2.937 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
iler | +2.898 |
ilers | +2.541 |
fter | +2.477 |
ghan | +2.332 |
lder | +2.207 |
Neg logit contributions | |
ioned | -3.505 |
inatory | -3.356 |
eenth | -3.163 |
atural | -3.143 |
alities | -3.131 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
iler | +0.946 |
ilers | +0.840 |
fter | +0.820 |
ghan | +0.780 |
llor | +0.741 |
Neg logit contributions | |
ioned | -0.975 |
inatory | -0.937 |
eenth | -0.879 |
enance | -0.876 |
alities | -0.867 |
Token | More |
Token ID | 5167 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
iler | +0.918 |
ilers | +0.812 |
fter | +0.807 |
ghan | +0.769 |
lder | +0.736 |
Neg logit contributions | |
ioned | -0.843 |
inatory | -0.812 |
eenth | -0.752 |
enance | -0.748 |
alities | -0.743 |
Token | : |
Token ID | 25 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
iler | +2.660 |
ilers | +2.294 |
fter | +2.234 |
ghan | +2.133 |
llor | +2.021 |
Neg logit contributions | |
ioned | -3.532 |
inatory | -3.454 |
atural | -3.232 |
enance | -3.226 |
eenth | -3.226 |
Token | Law |
Token ID | 3854 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
iler | +2.111 |
ilers | +1.851 |
fter | +1.850 |
ghan | +1.767 |
lder | +1.683 |
Neg logit contributions | |
ioned | -1.990 |
inatory | -1.933 |
enance | -1.766 |
atural | -1.763 |
eenth | -1.762 |
Token | suit |
Token ID | 6063 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
ioned | +8.684 |
inatory | +8.105 |
alities | +7.801 |
eenth | +7.775 |
enance | +7.633 |
Neg logit contributions | |
iler | -9.996 |
ilers | -9.145 |
fter | -8.790 |
ghan | -8.322 |
llor | -7.951 |
Token | : |
Token ID | 25 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
ioned | +8.790 |
inatory | +8.129 |
alities | +7.873 |
eenth | +7.791 |
ally | +7.641 |
Neg logit contributions | |
iler | -9.026 |
ilers | -8.221 |
fter | -7.848 |
ghan | -7.578 |
lder | -7.213 |
Token | UC |
Token ID | 14417 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
ioned | +3.362 |
inatory | +3.231 |
eenth | +3.040 |
enance | +2.991 |
alities | +2.961 |
Neg logit contributions | |
iler | -3.661 |
ilers | -3.290 |
fter | -3.205 |
ghan | -3.072 |
lder | -2.922 |
Token | has |
Token ID | 468 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ioned | +0.471 |
inatory | +0.454 |
eenth | +0.422 |
enance | +0.418 |
alities | +0.415 |
Neg logit contributions | |
iler | -0.511 |
ilers | -0.452 |
fter | -0.448 |
ghan | -0.428 |
llor | -0.408 |
Token | ' |
Token ID | 705 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
ioned | +1.488 |
inatory | +1.442 |
eenth | +1.345 |
enance | +1.339 |
alities | +1.332 |
Neg logit contributions | |
iler | -1.304 |
ilers | -1.147 |
fter | -1.127 |
ghan | -1.072 |
lder | -1.010 |
Token | anti |
Token ID | 17096 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
ioned | +3.051 |
inatory | +2.969 |
eenth | +2.757 |
enance | +2.735 |
alities | +2.722 |
Neg logit contributions | |
iler | -2.855 |
ilers | -2.529 |
fter | -2.470 |
ghan | -2.354 |
lder | -2.248 |
Token | Olymp |
Token ID | 7001 |
Feature activation | +9.75e+00 |
Pos logit contributions | |
iler | +0.461 |
ilers | +0.403 |
fter | +0.399 |
ghan | +0.379 |
lder | +0.358 |
Neg logit contributions | |
ioned | -0.505 |
inatory | -0.488 |
eenth | -0.456 |
enance | -0.452 |
alities | -0.449 |
Token | Oil |
Token ID | 11474 |
Feature activation | -7.50e+00 |
Pos logit contributions | |
ioned | +7.713 |
inatory | +7.384 |
alities | +6.810 |
eenth | +6.785 |
atural | +6.767 |
Neg logit contributions | |
iler | -8.045 |
ilers | -7.224 |
fter | -6.953 |
ghan | -6.723 |
llor | -6.524 |
Token | , |
Token ID | 11 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
iler | +6.010 |
ilers | +5.172 |
fter | +5.109 |
ghan | +4.877 |
lder | +4.658 |
Neg logit contributions | |
ioned | -6.338 |
inatory | -6.194 |
enance | -5.803 |
eenth | -5.748 |
atural | -5.710 |
Token | which |
Token ID | 543 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
iler | +0.321 |
ilers | +0.282 |
fter | +0.279 |
ghan | +0.265 |
lder | +0.251 |
Neg logit contributions | |
ioned | -0.344 |
inatory | -0.333 |
eenth | -0.311 |
enance | -0.308 |
alities | -0.306 |
Token | received |
Token ID | 2722 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
iler | +0.588 |
ilers | +0.519 |
fter | +0.515 |
ghan | +0.490 |
lder | +0.468 |
Neg logit contributions | |
ioned | -0.554 |
inatory | -0.536 |
eenth | -0.498 |
enance | -0.493 |
atural | -0.489 |
Token | 7 |
Token ID | 767 |
Feature activation | +9.94e+00 |
Pos logit contributions | |
iler | +1.960 |
ilers | +1.702 |
fter | +1.686 |
ghan | +1.609 |
lder | +1.522 |
Neg logit contributions | |
ioned | -2.240 |
inatory | -2.156 |
eenth | -2.036 |
enance | -2.006 |
atural | -2.000 |
Token | 15 |
Token ID | 1314 |
Feature activation | +6.37e+00 |
Pos logit contributions | |
ioned | +7.781 |
inatory | +7.569 |
eenth | +6.976 |
alities | +6.931 |
atural | +6.902 |
Neg logit contributions | |
iler | -8.108 |
ilers | -7.314 |
fter | -7.076 |
ghan | -6.715 |
llor | -6.545 |
Token | million |
Token ID | 1510 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ioned | +4.934 |
inatory | +4.774 |
eenth | +4.369 |
enance | +4.342 |
alities | +4.338 |
Neg logit contributions | |
iler | -5.571 |
ilers | -5.003 |
fter | -4.930 |
ghan | -4.690 |
llor | -4.517 |
Token | h |
Token ID | 289 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
ioned | +2.082 |
inatory | +2.023 |
eenth | +1.875 |
enance | +1.856 |
alities | +1.850 |
Neg logit contributions | |
iler | -1.980 |
ilers | -1.756 |
fter | -1.735 |
ghan | -1.645 |
lder | -1.562 |
Token | ry |
Token ID | 563 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
iler | +0.658 |
ilers | +0.593 |
fter | +0.588 |
ghan | +0.565 |
lder | +0.541 |
Neg logit contributions | |
ioned | -0.444 |
inatory | -0.425 |
eenth | -0.388 |
enance | -0.384 |
alities | -0.381 |
Token | v |
Token ID | 85 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ioned | +1.059 |
inatory | +1.018 |
eenth | +0.932 |
enance | +0.923 |
alities | +0.917 |
Neg logit contributions | |
iler | -1.457 |
ilers | -1.311 |
fter | -1.296 |
ghan | -1.244 |
lder | -1.191 |
Token | al |
Token ID | 435 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
iler | +1.291 |
ilers | +1.124 |
fter | +1.114 |
ghan | +1.064 |
llor | +1.002 |
Neg logit contributions | |
ioned | -1.446 |
inatory | -1.402 |
eenth | -1.305 |
enance | -1.294 |
alities | -1.292 |
Token | ag |
Token ID | 363 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ioned | +0.334 |
inatory | +0.322 |
eenth | +0.299 |
enance | +0.297 |
alities | +0.293 |
Neg logit contributions | |
iler | -0.371 |
ilers | -0.329 |
fter | -0.326 |
ghan | -0.312 |
lder | -0.297 |
Token | se |
Token ID | 384 |
Feature activation | -8.08e+00 |
Pos logit contributions | |
iler | +2.198 |
ilers | +1.898 |
fter | +1.881 |
ghan | +1.814 |
lder | +1.700 |
Neg logit contributions | |
ioned | -2.423 |
inatory | -2.348 |
eenth | -2.204 |
enance | -2.174 |
atural | -2.159 |
Token | int |
Token ID | 493 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
iler | +6.688 |
fter | +5.768 |
ilers | +5.739 |
ghan | +5.564 |
lder | +5.268 |
Neg logit contributions | |
ioned | -6.595 |
inatory | -6.288 |
eenth | -5.955 |
atural | -5.874 |
alities | -5.787 |
Token | e |
Token ID | 68 |
Feature activation | -9.50e+00 |
Pos logit contributions | |
iler | +3.182 |
ilers | +2.818 |
fter | +2.752 |
ghan | +2.642 |
lder | +2.516 |
Neg logit contributions | |
ioned | -2.670 |
inatory | -2.629 |
atural | -2.410 |
eenth | -2.409 |
alities | -2.378 |
Token | jam |
Token ID | 39159 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
iler | +7.503 |
ilers | +6.357 |
fter | +6.322 |
ghan | +6.064 |
llor | +5.864 |
Neg logit contributions | |
ioned | -7.942 |
inatory | -7.714 |
atural | -7.244 |
alities | -7.199 |
eenth | -7.147 |
Token | k |
Token ID | 479 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
ioned | +8.250 |
inatory | +8.084 |
enance | +7.535 |
alities | +7.466 |
eenth | +7.465 |
Neg logit contributions | |
iler | -6.697 |
ilers | -5.984 |
fter | -5.888 |
ghan | -5.474 |
lder | -5.283 |
Token | ar |
Token ID | 283 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
ioned | +2.017 |
inatory | +1.950 |
eenth | +1.814 |
enance | +1.803 |
alities | +1.792 |
Neg logit contributions | |
iler | -2.026 |
ilers | -1.799 |
fter | -1.774 |
ghan | -1.687 |
lder | -1.604 |
Token | ne |
Token ID | 710 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ioned | +3.561 |
inatory | +3.457 |
eenth | +3.220 |
enance | +3.206 |
alities | +3.196 |
Neg logit contributions | |
iler | -2.860 |
ilers | -2.516 |
fter | -2.481 |
ghan | -2.326 |
llor | -2.205 |
Token | ki |
Token ID | 47748 |
Feature activation | -7.75e+00 |
Pos logit contributions | |
ioned | +0.718 |
inatory | +0.697 |
eenth | +0.653 |
enance | +0.648 |
alities | +0.645 |
Neg logit contributions | |
iler | -0.574 |
ilers | -0.499 |
fter | -0.492 |
ghan | -0.465 |
lder | -0.438 |
Token | jar |
Token ID | 17379 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
iler | +5.617 |
ilers | +4.762 |
fter | +4.750 |
ghan | +4.596 |
llor | +4.269 |
Neg logit contributions | |
ioned | -7.082 |
inatory | -6.894 |
eenth | -6.382 |
alities | -6.345 |
enance | -6.330 |
Token | any |
Token ID | 597 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
ioned | +0.749 |
inatory | +0.726 |
eenth | +0.677 |
enance | +0.670 |
alities | +0.667 |
Neg logit contributions | |
iler | -0.694 |
ilers | -0.609 |
fter | -0.601 |
ghan | -0.571 |
lder | -0.543 |
Token | potential |
Token ID | 2785 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
ioned | +3.527 |
inatory | +3.424 |
eenth | +3.186 |
enance | +3.182 |
alities | +3.168 |
Neg logit contributions | |
iler | -3.237 |
ilers | -2.869 |
fter | -2.824 |
ghan | -2.693 |
llor | -2.528 |
Token | technical |
Token ID | 6276 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ioned | +0.744 |
inatory | +0.720 |
eenth | +0.671 |
enance | +0.664 |
atural | +0.661 |
Neg logit contributions | |
iler | -0.724 |
ilers | -0.638 |
fter | -0.630 |
ghan | -0.598 |
lder | -0.570 |
Token | interference |
Token ID | 14517 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
ioned | +1.436 |
inatory | +1.385 |
eenth | +1.279 |
enance | +1.265 |
alities | +1.256 |
Neg logit contributions | |
iler | -1.725 |
ilers | -1.539 |
fter | -1.524 |
ghan | -1.457 |
lder | -1.394 |
Token | - |
Token ID | 532 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ioned | +0.496 |
inatory | +0.481 |
eenth | +0.450 |
enance | +0.448 |
alities | +0.445 |
Neg logit contributions | |
iler | -0.403 |
ilers | -0.351 |
fter | -0.346 |
ghan | -0.327 |
lder | -0.308 |
Token | LOC |
Token ID | 37347 |
Feature activation | +8.90e+00 |
Pos logit contributions | |
iler | +0.305 |
ilers | +0.267 |
fter | +0.264 |
ghan | +0.251 |
lder | +0.237 |
Neg logit contributions | |
ioned | -0.339 |
inatory | -0.329 |
eenth | -0.307 |
enance | -0.305 |
alities | -0.303 |
Token | OG |
Token ID | 7730 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
ioned | +7.588 |
inatory | +7.383 |
alities | +6.910 |
atural | +6.863 |
eenth | +6.836 |
Neg logit contributions | |
iler | -6.867 |
ilers | -6.106 |
fter | -6.018 |
ghan | -5.600 |
lder | -5.295 |
Token | , |
Token ID | 11 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
ioned | +3.726 |
inatory | +3.606 |
eenth | +3.360 |
enance | +3.327 |
alities | +3.319 |
Neg logit contributions | |
iler | -3.452 |
ilers | -3.049 |
fter | -3.010 |
ghan | -2.856 |
lder | -2.691 |
Token | the |
Token ID | 262 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
iler | +0.494 |
ilers | +0.431 |
fter | +0.426 |
ghan | +0.403 |
lder | +0.381 |
Neg logit contributions | |
ioned | -0.577 |
inatory | -0.559 |
eenth | -0.523 |
enance | -0.518 |
alities | -0.516 |
Token | London |
Token ID | 3576 |
Feature activation | +7.23e+00 |
Pos logit contributions | |
iler | +1.805 |
ilers | +1.572 |
fter | +1.557 |
ghan | +1.469 |
lder | +1.402 |
Neg logit contributions | |
ioned | -2.063 |
inatory | -2.000 |
eenth | -1.871 |
enance | -1.861 |
atural | -1.858 |
Token | Olympics |
Token ID | 14935 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
ioned | +6.275 |
inatory | +6.110 |
alities | +5.615 |
eenth | +5.613 |
enance | +5.607 |
Neg logit contributions | |
iler | -5.609 |
ilers | -4.997 |
fter | -4.849 |
ghan | -4.660 |
llor | -4.450 |
Token | 4 |
Token ID | 604 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
ioned | +1.877 |
inatory | +1.818 |
eenth | +1.696 |
enance | +1.689 |
alities | +1.677 |
Neg logit contributions | |
iler | -1.714 |
ilers | -1.512 |
fter | -1.483 |
ghan | -1.407 |
lder | -1.336 |
Token | damage |
Token ID | 2465 |
Feature activation | -7.86e+00 |
Pos logit contributions | |
ioned | +4.303 |
inatory | +4.180 |
eenth | +3.925 |
atural | +3.871 |
alities | +3.867 |
Neg logit contributions | |
iler | -3.829 |
ilers | -3.384 |
fter | -3.326 |
ghan | -3.119 |
lder | -2.981 |
Token | with |
Token ID | 351 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
iler | +5.846 |
ilers | +5.112 |
fter | +5.062 |
ghan | +4.754 |
llor | +4.573 |
Neg logit contributions | |
ioned | -6.957 |
inatory | -6.776 |
eenth | -6.375 |
atural | -6.279 |
enance | -6.237 |
Token | R |
Token ID | 371 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
iler | +1.391 |
ilers | +1.220 |
fter | +1.206 |
ghan | +1.157 |
lder | +1.092 |
Neg logit contributions | |
ioned | -1.459 |
inatory | -1.412 |
eenth | -1.321 |
enance | -1.304 |
alities | -1.295 |
Token | anged |
Token ID | 5102 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ioned | +0.146 |
inatory | +0.141 |
eenth | +0.130 |
enance | +0.128 |
alities | +0.128 |
Neg logit contributions | |
iler | -0.159 |
ilers | -0.141 |
fter | -0.138 |
ghan | -0.132 |
lder | -0.126 |
Token | Combat |
Token ID | 14487 |
Feature activation | +8.43e+00 |
Pos logit contributions | |
ioned | +0.891 |
inatory | +0.862 |
eenth | +0.803 |
enance | +0.797 |
alities | +0.792 |
Neg logit contributions | |
iler | -0.856 |
ilers | -0.755 |
fter | -0.745 |
ghan | -0.708 |
lder | -0.672 |
Token | Expert |
Token ID | 25516 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ioned | +6.861 |
inatory | +6.571 |
enance | +6.154 |
alities | +6.140 |
eenth | +6.120 |
Neg logit contributions | |
iler | -6.848 |
ilers | -6.177 |
fter | -5.981 |
ghan | -5.602 |
llor | -5.493 |
Token | . |
Token ID | 13 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
iler | +0.105 |
ilers | +0.092 |
fter | +0.091 |
ghan | +0.086 |
lder | +0.082 |
Neg logit contributions | |
ioned | -0.113 |
inatory | -0.109 |
eenth | -0.102 |
enance | -0.101 |
alities | -0.100 |
Token | Tra |
Token ID | 4759 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
iler | +0.057 |
ilers | +0.050 |
fter | +0.049 |
ghan | +0.047 |
lder | +0.045 |
Neg logit contributions | |
ioned | -0.063 |
inatory | -0.061 |
eenth | -0.056 |
enance | -0.056 |
alities | -0.056 |
Token | ited |
Token ID | 863 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
iler | +2.282 |
ilers | +1.986 |
fter | +1.951 |
ghan | +1.838 |
lder | +1.729 |
Neg logit contributions | |
ioned | -2.715 |
inatory | -2.636 |
eenth | -2.476 |
enance | -2.459 |
alities | -2.427 |
Token | poison |
Token ID | 8764 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ioned | +0.350 |
inatory | +0.341 |
eenth | +0.318 |
enance | +0.315 |
atural | +0.312 |
Neg logit contributions | |
iler | -0.328 |
ilers | -0.288 |
fter | -0.285 |
ghan | -0.271 |
llor | -0.256 |
Token | of |
Token ID | 286 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ioned | +5.997 |
inatory | +5.802 |
eenth | +5.480 |
enance | +5.442 |
alities | +5.428 |
Neg logit contributions | |
iler | -4.936 |
ilers | -4.364 |
fter | -4.346 |
ghan | -4.055 |
llor | -3.844 |
Token | thousands |
Token ID | 4138 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ioned | +1.897 |
inatory | +1.836 |
eenth | +1.688 |
enance | +1.679 |
alities | +1.677 |
Neg logit contributions | |
iler | -2.347 |
ilers | -2.108 |
fter | -2.086 |
ghan | -2.005 |
llor | -1.911 |
Token | of |
Token ID | 286 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ioned | +2.130 |
inatory | +2.070 |
eenth | +1.947 |
enance | +1.935 |
alities | +1.925 |
Neg logit contributions | |
iler | -1.509 |
ilers | -1.302 |
fter | -1.283 |
ghan | -1.206 |
lder | -1.127 |
Token | complaints |
Token ID | 9687 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
ioned | +1.903 |
inatory | +1.838 |
eenth | +1.697 |
enance | +1.687 |
alities | +1.680 |
Neg logit contributions | |
iler | -2.321 |
ilers | -2.085 |
fter | -2.061 |
ghan | -1.981 |
llor | -1.888 |
Token | . |
Token ID | 13 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
iler | +2.635 |
ilers | +2.251 |
fter | +2.225 |
ghan | +2.123 |
lder | +1.985 |
Neg logit contributions | |
ioned | -3.366 |
inatory | -3.296 |
atural | -3.050 |
eenth | -3.039 |
enance | -3.008 |
Token | That |
Token ID | 1320 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
ioned | +0.228 |
inatory | +0.221 |
eenth | +0.205 |
enance | +0.204 |
alities | +0.203 |
Neg logit contributions | |
iler | -0.227 |
ilers | -0.200 |
fter | -0.198 |
ghan | -0.188 |
lder | -0.179 |
Token | � |
Token ID | 447 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ioned | +2.649 |
inatory | +2.536 |
enance | +2.306 |
eenth | +2.305 |
alities | +2.293 |
Neg logit contributions | |
iler | -4.079 |
ilers | -3.712 |
fter | -3.649 |
ghan | -3.524 |
llor | -3.374 |
Token | � |
Token ID | 247 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
iler | +1.188 |
fter | +1.011 |
ilers | +1.006 |
ghan | +0.950 |
lder | +0.878 |
Neg logit contributions | |
ioned | -1.794 |
inatory | -1.750 |
alities | -1.635 |
eenth | -1.635 |
enance | -1.621 |
Token | s |
Token ID | 82 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ioned | +1.162 |
inatory | +1.126 |
eenth | +1.048 |
enance | +1.041 |
alities | +1.035 |
Neg logit contributions | |
iler | -1.087 |
ilers | -0.955 |
fter | -0.944 |
ghan | -0.897 |
lder | -0.850 |
Token | what |
Token ID | 644 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
ioned | +2.181 |
inatory | +2.105 |
eenth | +1.966 |
enance | +1.958 |
alities | +1.945 |
Neg logit contributions | |
iler | -2.060 |
ilers | -1.821 |
fter | -1.785 |
ghan | -1.703 |
llor | -1.607 |
Token | the |
Token ID | 262 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
iler | +0.659 |
ilers | +0.582 |
fter | +0.574 |
ghan | +0.549 |
lder | +0.526 |
Neg logit contributions | |
ioned | -0.632 |
inatory | -0.612 |
eenth | -0.568 |
enance | -0.563 |
alities | -0.559 |
Token | to |
Token ID | 284 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
ioned | +0.338 |
inatory | +0.328 |
eenth | +0.308 |
enance | +0.305 |
atural | +0.303 |
Neg logit contributions | |
iler | -0.267 |
ilers | -0.232 |
fter | -0.228 |
ghan | -0.216 |
lder | -0.203 |
Token | behave |
Token ID | 17438 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
iler | +0.615 |
ilers | +0.528 |
fter | +0.519 |
ghan | +0.489 |
lder | +0.457 |
Neg logit contributions | |
ioned | -0.877 |
inatory | -0.853 |
eenth | -0.802 |
enance | -0.797 |
alities | -0.793 |
Token | in |
Token ID | 287 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ioned | +1.937 |
inatory | +1.876 |
eenth | +1.749 |
enance | +1.739 |
alities | +1.727 |
Neg logit contributions | |
iler | -1.808 |
ilers | -1.592 |
fter | -1.570 |
ghan | -1.492 |
lder | -1.415 |
Token | the |
Token ID | 262 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
iler | +0.871 |
ilers | +0.760 |
fter | +0.747 |
ghan | +0.707 |
lder | +0.671 |
Neg logit contributions | |
ioned | -1.048 |
inatory | -1.014 |
eenth | -0.950 |
enance | -0.941 |
atural | -0.938 |
Token | 21 |
Token ID | 2310 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
iler | +1.949 |
ilers | +1.664 |
fter | +1.648 |
ghan | +1.559 |
lder | +1.462 |
Neg logit contributions | |
ioned | -2.669 |
inatory | -2.586 |
eenth | -2.424 |
atural | -2.415 |
enance | -2.401 |
Token | st |
Token ID | 301 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
ioned | +3.806 |
inatory | +3.697 |
eenth | +3.371 |
alities | +3.303 |
enance | +3.293 |
Neg logit contributions | |
iler | -6.516 |
ilers | -5.946 |
fter | -5.845 |
ghan | -5.629 |
lder | -5.399 |
Token | century |
Token ID | 4289 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
ioned | +0.673 |
inatory | +0.651 |
eenth | +0.611 |
enance | +0.609 |
alities | +0.606 |
Neg logit contributions | |
iler | -0.466 |
ilers | -0.398 |
fter | -0.394 |
ghan | -0.371 |
lder | -0.347 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
iler | +0.758 |
ilers | +0.662 |
fter | +0.653 |
ghan | +0.624 |
lder | +0.584 |
Neg logit contributions | |
ioned | -0.880 |
inatory | -0.851 |
eenth | -0.798 |
enance | -0.786 |
atural | -0.785 |
Token | Hope |
Token ID | 13408 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ioned | +0.318 |
inatory | +0.308 |
eenth | +0.287 |
enance | +0.285 |
alities | +0.283 |
Neg logit contributions | |
iler | -0.302 |
ilers | -0.265 |
fter | -0.262 |
ghan | -0.249 |
lder | -0.236 |
Token | springs |
Token ID | 24747 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ioned | +2.187 |
inatory | +2.114 |
eenth | +1.963 |
enance | +1.951 |
alities | +1.938 |
Neg logit contributions | |
iler | -2.193 |
ilers | -1.940 |
fter | -1.914 |
ghan | -1.826 |
lder | -1.732 |
Token | eternal |
Token ID | 15851 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
iler | +1.073 |
ilers | +0.918 |
fter | +0.906 |
ghan | +0.843 |
lder | +0.783 |
Neg logit contributions | |
ioned | -1.576 |
inatory | -1.536 |
eenth | -1.438 |
alities | -1.433 |
enance | -1.428 |
Token | , |
Token ID | 11 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ioned | +5.849 |
inatory | +5.586 |
eenth | +5.366 |
atural | +5.271 |
alities | +5.207 |
Neg logit contributions | |
iler | -5.855 |
ilers | -5.262 |
fter | -5.244 |
ghan | -4.854 |
llor | -4.697 |
Token | as |
Token ID | 355 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ioned | +2.194 |
inatory | +2.128 |
eenth | +1.975 |
enance | +1.960 |
alities | +1.953 |
Neg logit contributions | |
iler | -2.188 |
ilers | -1.939 |
fter | -1.910 |
ghan | -1.815 |
llor | -1.730 |
Token | it |
Token ID | 340 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
iler | +1.080 |
ilers | +0.941 |
fter | +0.929 |
ghan | +0.882 |
lder | +0.846 |
Neg logit contributions | |
ioned | -1.237 |
inatory | -1.211 |
eenth | -1.133 |
enance | -1.117 |
alities | -1.111 |
Token | seems |
Token ID | 2331 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
ioned | +2.477 |
inatory | +2.388 |
eenth | +2.214 |
enance | +2.199 |
alities | +2.186 |
Neg logit contributions | |
iler | -2.672 |
ilers | -2.383 |
fter | -2.350 |
ghan | -2.236 |
lder | -2.125 |
Token | they |
Token ID | 484 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
iler | +1.709 |
ilers | +1.470 |
fter | +1.458 |
ghan | +1.377 |
lder | +1.312 |
Neg logit contributions | |
ioned | -2.164 |
inatory | -2.129 |
eenth | -2.004 |
enance | -1.971 |
atural | -1.966 |
Token | don |
Token ID | 836 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ioned | +2.045 |
inatory | +1.966 |
enance | +1.849 |
eenth | +1.845 |
alities | +1.836 |
Neg logit contributions | |
iler | -1.511 |
ilers | -1.322 |
fter | -1.306 |
ghan | -1.221 |
llor | -1.152 |
Token | 't |
Token ID | 470 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ioned | +1.426 |
inatory | +1.314 |
eenth | +1.212 |
enance | +1.211 |
alities | +1.194 |
Neg logit contributions | |
iler | -2.386 |
ilers | -2.185 |
fter | -2.139 |
ghan | -2.052 |
llor | -2.000 |
Token | care |
Token ID | 1337 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ioned | +1.148 |
inatory | +1.108 |
enance | +1.039 |
eenth | +1.032 |
alities | +1.028 |
Neg logit contributions | |
iler | -0.839 |
ilers | -0.732 |
fter | -0.725 |
ghan | -0.680 |
llor | -0.643 |
Token | for |
Token ID | 329 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
ioned | +1.505 |
inatory | +1.454 |
eenth | +1.355 |
enance | +1.348 |
alities | +1.338 |
Neg logit contributions | |
iler | -1.417 |
ilers | -1.249 |
fter | -1.231 |
ghan | -1.170 |
lder | -1.107 |
Token | hikers |
Token ID | 47961 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
ioned | +2.533 |
inatory | +2.437 |
eenth | +2.268 |
enance | +2.266 |
alities | +2.244 |
Neg logit contributions | |
iler | -2.509 |
ilers | -2.223 |
fter | -2.195 |
ghan | -2.087 |
llor | -1.983 |
Token | ' |
Token ID | 6 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
iler | +2.395 |
ilers | +2.084 |
fter | +2.063 |
ghan | +1.967 |
lder | +1.865 |
Neg logit contributions | |
ioned | -2.734 |
inatory | -2.680 |
eenth | -2.488 |
alities | -2.460 |
enance | -2.455 |
Token | natural |
Token ID | 3288 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ioned | +2.832 |
inatory | +2.751 |
eenth | +2.584 |
alities | +2.575 |
enance | +2.569 |
Neg logit contributions | |
iler | -2.060 |
ilers | -1.789 |
fter | -1.760 |
ghan | -1.652 |
llor | -1.549 |
Token | progress |
Token ID | 4371 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
iler | +0.231 |
ilers | +0.199 |
fter | +0.196 |
ghan | +0.186 |
lder | +0.176 |
Neg logit contributions | |
ioned | -0.304 |
inatory | -0.295 |
eenth | -0.279 |
enance | -0.275 |
atural | -0.274 |
Token | of |
Token ID | 286 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
iler | +0.850 |
ilers | +0.733 |
fter | +0.716 |
ghan | +0.678 |
lder | +0.637 |
Neg logit contributions | |
ioned | -1.122 |
inatory | -1.100 |
eenth | -1.035 |
enance | -1.022 |
atural | -1.015 |
Token | the |
Token ID | 262 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ioned | +1.989 |
inatory | +1.925 |
eenth | +1.795 |
enance | +1.787 |
alities | +1.778 |
Neg logit contributions | |
iler | -1.837 |
ilers | -1.617 |
fter | -1.599 |
ghan | -1.519 |
lder | -1.435 |
Token | puls |
Token ID | 22271 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
iler | +0.176 |
ilers | +0.154 |
fter | +0.151 |
ghan | +0.144 |
lder | +0.136 |
Neg logit contributions | |
ioned | -0.206 |
inatory | -0.200 |
eenth | -0.187 |
enance | -0.185 |
alities | -0.184 |
Token | ation |
Token ID | 341 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
ioned | +1.057 |
inatory | +1.020 |
eenth | +0.945 |
enance | +0.936 |
alities | +0.929 |
Neg logit contributions | |
iler | -1.208 |
ilers | -1.076 |
fter | -1.063 |
ghan | -1.015 |
lder | -0.968 |
Token | as |
Token ID | 355 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
ioned | +0.489 |
inatory | +0.475 |
eenth | +0.446 |
enance | +0.442 |
alities | +0.439 |
Neg logit contributions | |
iler | -0.394 |
ilers | -0.342 |
fter | -0.337 |
ghan | -0.319 |
lder | -0.301 |
Token | much |
Token ID | 881 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
iler | +0.233 |
ilers | +0.201 |
fter | +0.197 |
ghan | +0.186 |
lder | +0.175 |
Neg logit contributions | |
ioned | -0.315 |
inatory | -0.307 |
eenth | -0.288 |
enance | -0.286 |
alities | -0.284 |
Token |
|
Token ID | 198 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
iler | +1.043 |
ilers | +0.887 |
fter | +0.874 |
ghan | +0.823 |
lder | +0.771 |
Neg logit contributions | |
ioned | -1.565 |
inatory | -1.525 |
eenth | -1.439 |
alities | -1.422 |
enance | -1.420 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ioned | +0.715 |
inatory | +0.683 |
enance | +0.646 |
eenth | +0.643 |
alities | +0.635 |
Neg logit contributions | |
iler | -0.773 |
ilers | -0.696 |
fter | -0.677 |
ghan | -0.642 |
�� | -0.629 |
Token | as |
Token ID | 292 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ioned | +0.744 |
inatory | +0.714 |
enance | +0.649 |
eenth | +0.648 |
alities | +0.642 |
Neg logit contributions | |
iler | -1.118 |
ilers | -1.014 |
fter | -0.998 |
ghan | -0.964 |
llor | -0.926 |
Token | petition |
Token ID | 8853 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
iler | +0.214 |
ilers | +0.190 |
fter | +0.189 |
ghan | +0.179 |
lder | +0.172 |
Neg logit contributions | |
ioned | -0.189 |
inatory | -0.182 |
eenth | -0.169 |
enance | -0.168 |
atural | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ioned | +4.369 |
inatory | +4.193 |
eenth | +3.906 |
alities | +3.902 |
enance | +3.886 |
Neg logit contributions | |
iler | -4.151 |
ilers | -3.651 |
fter | -3.570 |
ghan | -3.465 |
llor | -3.277 |
Token |
|
Token ID | 198 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
ioned | +1.498 |
inatory | +1.451 |
eenth | +1.354 |
enance | +1.344 |
alities | +1.336 |
Neg logit contributions | |
iler | -1.387 |
ilers | -1.220 |
fter | -1.203 |
ghan | -1.144 |
lder | -1.082 |
Token |
|
Token ID | 198 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
ioned | +0.776 |
inatory | +0.740 |
enance | +0.697 |
eenth | +0.697 |
alities | +0.685 |
Neg logit contributions | |
iler | -0.835 |
ilers | -0.751 |
fter | -0.727 |
ghan | -0.693 |
�� | -0.679 |
Token | Jack |
Token ID | 14295 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ioned | +0.451 |
inatory | +0.434 |
eenth | +0.400 |
enance | +0.396 |
alities | +0.393 |
Neg logit contributions | |
iler | -0.569 |
ilers | -0.509 |
fter | -0.504 |
ghan | -0.482 |
lder | -0.461 |
Token | now |
Token ID | 2197 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ioned | +1.833 |
inatory | +1.739 |
alities | +1.605 |
eenth | +1.599 |
enance | +1.594 |
Neg logit contributions | |
iler | -2.540 |
ilers | -2.292 |
fter | -2.214 |
ghan | -2.150 |
llor | -2.063 |
Token | , |
Token ID | 11 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ioned | +1.676 |
inatory | +1.619 |
eenth | +1.514 |
enance | +1.503 |
alities | +1.495 |
Neg logit contributions | |
iler | -1.497 |
ilers | -1.316 |
fter | -1.294 |
ghan | -1.230 |
lder | -1.161 |
Token | who |
Token ID | 508 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
iler | +1.207 |
ilers | +1.041 |
fter | +1.027 |
ghan | +0.968 |
lder | +0.913 |
Neg logit contributions | |
ioned | -1.577 |
inatory | -1.533 |
eenth | -1.437 |
enance | -1.427 |
alities | -1.420 |
Token | was |
Token ID | 373 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
iler | +2.929 |
fter | +2.547 |
ilers | +2.537 |
ghan | +2.397 |
lder | +2.314 |
Neg logit contributions | |
ioned | -3.095 |
inatory | -3.041 |
eenth | -2.828 |
enance | -2.797 |
atural | -2.788 |
Token | at |
Token ID | 379 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
iler | +2.196 |
ilers | +1.867 |
fter | +1.864 |
ghan | +1.749 |
lder | +1.693 |
Neg logit contributions | |
ioned | -2.861 |
inatory | -2.810 |
eenth | -2.623 |
alities | -2.593 |
atural | -2.586 |
Token | the |
Token ID | 262 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
ioned | +1.180 |
inatory | +1.143 |
eenth | +1.066 |
enance | +1.061 |
alities | +1.056 |
Neg logit contributions | |
iler | -1.056 |
ilers | -0.925 |
fter | -0.910 |
ghan | -0.865 |
lder | -0.822 |
Token | introduced |
Token ID | 5495 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ioned | +1.151 |
inatory | +1.116 |
eenth | +1.043 |
enance | +1.038 |
alities | +1.034 |
Neg logit contributions | |
iler | -0.961 |
ilers | -0.841 |
fter | -0.825 |
ghan | -0.783 |
llor | -0.739 |
Token | no |
Token ID | 645 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
iler | +1.515 |
ilers | +1.325 |
fter | +1.319 |
ghan | +1.250 |
lder | +1.179 |
Neg logit contributions | |
ioned | -1.707 |
inatory | -1.656 |
eenth | -1.552 |
atural | -1.547 |
enance | -1.544 |
Token | later |
Token ID | 1568 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
ioned | +2.829 |
inatory | +2.743 |
eenth | +2.563 |
enance | +2.540 |
alities | +2.532 |
Neg logit contributions | |
iler | -2.379 |
ilers | -2.085 |
fter | -2.046 |
ghan | -1.943 |
llor | -1.834 |
Token | than |
Token ID | 621 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
iler | +0.258 |
ilers | +0.220 |
fter | +0.216 |
ghan | +0.203 |
llor | +0.188 |
Neg logit contributions | |
ioned | -0.403 |
inatory | -0.391 |
eenth | -0.369 |
enance | -0.366 |
alities | -0.366 |
Token | next |
Token ID | 1306 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
iler | +0.846 |
ilers | +0.748 |
fter | +0.740 |
ghan | +0.703 |
lder | +0.669 |
Neg logit contributions | |
ioned | -0.848 |
inatory | -0.821 |
eenth | -0.761 |
enance | -0.758 |
atural | -0.754 |
Token | year |
Token ID | 614 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
iler | +2.107 |
ilers | +1.794 |
fter | +1.767 |
ghan | +1.656 |
lder | +1.579 |
Neg logit contributions | |
ioned | -3.032 |
inatory | -2.950 |
eenth | -2.763 |
enance | -2.762 |
atural | -2.755 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
iler | +0.991 |
ilers | +0.869 |
fter | +0.860 |
ghan | +0.817 |
lder | +0.774 |
Neg logit contributions | |
ioned | -1.089 |
inatory | -1.052 |
eenth | -0.983 |
enance | -0.976 |
atural | -0.972 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
iler | +1.689 |
ilers | +1.492 |
fter | +1.460 |
ghan | +1.387 |
llor | +1.314 |
Neg logit contributions | |
ioned | -1.829 |
inatory | -1.765 |
eenth | -1.655 |
enance | -1.645 |
alities | -1.631 |
Token | @ |
Token ID | 31 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
iler | +1.211 |
ilers | +1.068 |
fter | +1.062 |
ghan | +1.007 |
lder | +0.958 |
Neg logit contributions | |
ioned | -1.216 |
inatory | -1.174 |
eenth | -1.094 |
enance | -1.088 |
atural | -1.076 |
Token | O |
Token ID | 46 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
iler | +0.139 |
ilers | +0.123 |
fter | +0.122 |
ghan | +0.116 |
lder | +0.111 |
Neg logit contributions | |
ioned | -0.130 |
inatory | -0.126 |
eenth | -0.117 |
enance | -0.116 |
alities | -0.115 |
Token | mega |
Token ID | 13731 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
iler | +5.453 |
ilers | +4.888 |
fter | +4.801 |
ghan | +4.611 |
lder | +4.543 |
Neg logit contributions | |
ioned | -4.654 |
inatory | -4.594 |
eenth | -4.212 |
alities | -4.175 |
enance | -4.170 |
Token | . |
Token ID | 13 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
ioned | +0.288 |
inatory | +0.279 |
eenth | +0.260 |
enance | +0.257 |
atural | +0.256 |
Neg logit contributions | |
iler | -0.291 |
ilers | -0.257 |
fter | -0.253 |
ghan | -0.241 |
lder | -0.230 |
Token | It |
Token ID | 632 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
iler | +0.312 |
ilers | +0.274 |
fter | +0.271 |
ghan | +0.257 |
lder | +0.244 |
Neg logit contributions | |
ioned | -0.333 |
inatory | -0.323 |
eenth | -0.300 |
enance | -0.298 |
alities | -0.296 |
Token | is |
Token ID | 318 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ioned | +2.876 |
inatory | +2.760 |
eenth | +2.544 |
enance | +2.540 |
alities | +2.535 |
Neg logit contributions | |
iler | -3.482 |
ilers | -3.137 |
fter | -3.082 |
ghan | -2.954 |
lder | -2.807 |
Token | based |
Token ID | 1912 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
iler | +1.243 |
ilers | +1.070 |
fter | +1.058 |
ghan | +0.997 |
lder | +0.940 |
Neg logit contributions | |
ioned | -1.614 |
inatory | -1.574 |
eenth | -1.476 |
enance | -1.459 |
atural | -1.455 |
Token | on |
Token ID | 319 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
iler | +2.579 |
ilers | +2.245 |
fter | +2.213 |
ghan | +2.113 |
llor | +2.005 |
Neg logit contributions | |
ioned | -2.976 |
inatory | -2.904 |
eenth | -2.710 |
atural | -2.704 |
alities | -2.673 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
iler | +0.201 |
ilers | +0.176 |
fter | +0.173 |
ghan | +0.164 |
lder | +0.155 |
Neg logit contributions | |
ioned | -0.232 |
inatory | -0.225 |
eenth | -0.210 |
enance | -0.208 |
alities | -0.207 |
Token | K |
Token ID | 509 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
iler | +1.382 |
ilers | +1.204 |
fter | +1.190 |
ghan | +1.121 |
lder | +1.067 |
Neg logit contributions | |
ioned | -1.603 |
inatory | -1.555 |
eenth | -1.453 |
enance | -1.442 |
atural | -1.437 |
Token | VM |
Token ID | 15996 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ioned | +1.504 |
inatory | +1.448 |
eenth | +1.333 |
enance | +1.323 |
alities | +1.314 |
Neg logit contributions | |
iler | -1.869 |
ilers | -1.674 |
fter | -1.656 |
ghan | -1.586 |
lder | -1.514 |
Token | core |
Token ID | 4755 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
ioned | +1.495 |
inatory | +1.450 |
eenth | +1.356 |
enance | +1.347 |
alities | +1.341 |
Neg logit contributions | |
iler | -1.247 |
ilers | -1.088 |
fter | -1.073 |
ghan | -1.016 |
lder | -0.958 |
Token | kernel |
Token ID | 9720 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
iler | +2.936 |
ilers | +2.560 |
fter | +2.514 |
ghan | +2.361 |
lder | +2.292 |
Neg logit contributions | |
ioned | -3.330 |
inatory | -3.258 |
eenth | -3.041 |
enance | -2.992 |
atural | -2.984 |
Token | module |
Token ID | 8265 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
iler | +1.753 |
ilers | +1.530 |
fter | +1.505 |
ghan | +1.419 |
lder | +1.373 |
Neg logit contributions | |
ioned | -1.917 |
inatory | -1.870 |
eenth | -1.748 |
enance | -1.722 |
atural | -1.715 |
Token | will |
Token ID | 481 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
iler | +2.550 |
ilers | +2.190 |
fter | +2.165 |
ghan | +2.047 |
lder | +1.934 |
Neg logit contributions | |
ioned | -3.365 |
inatory | -3.283 |
eenth | -3.073 |
enance | -3.054 |
atural | -3.043 |
Token | begin |
Token ID | 2221 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
iler | +2.460 |
ilers | +2.098 |
fter | +2.074 |
ghan | +1.937 |
lder | +1.818 |
Neg logit contributions | |
ioned | -3.641 |
inatory | -3.553 |
eenth | -3.348 |
enance | -3.323 |
alities | -3.302 |
Token | as |
Token ID | 355 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
iler | +2.100 |
ilers | +1.818 |
fter | +1.803 |
ghan | +1.707 |
lder | +1.603 |
Neg logit contributions | |
ioned | -2.677 |
inatory | -2.604 |
eenth | -2.446 |
enance | -2.421 |
alities | -2.411 |
Token | President |
Token ID | 1992 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
iler | +2.047 |
fter | +1.775 |
ilers | +1.769 |
ghan | +1.677 |
lder | +1.591 |
Neg logit contributions | |
ioned | -2.467 |
inatory | -2.404 |
eenth | -2.246 |
enance | -2.236 |
atural | -2.211 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ioned | +0.365 |
inatory | +0.354 |
eenth | +0.332 |
enance | +0.330 |
alities | +0.328 |
Neg logit contributions | |
iler | -0.283 |
ilers | -0.245 |
fter | -0.242 |
ghan | -0.228 |
lder | -0.215 |
Token | CEO |
Token ID | 6123 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
ioned | +1.145 |
inatory | +1.106 |
eenth | +1.029 |
enance | +1.024 |
alities | +1.023 |
Neg logit contributions | |
iler | -1.105 |
ilers | -0.980 |
fter | -0.958 |
ghan | -0.917 |
lder | -0.864 |
Token | of |
Token ID | 286 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
iler | +1.594 |
ilers | +1.351 |
fter | +1.346 |
ghan | +1.256 |
llor | +1.184 |
Neg logit contributions | |
ioned | -2.455 |
inatory | -2.375 |
eenth | -2.251 |
enance | -2.218 |
alities | -2.210 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
iler | +0.288 |
ilers | +0.252 |
fter | +0.249 |
ghan | +0.237 |
lder | +0.224 |
Neg logit contributions | |
ioned | -0.320 |
inatory | -0.310 |
eenth | -0.290 |
enance | -0.288 |
alities | -0.285 |
Token | Better |
Token ID | 11625 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
iler | +1.752 |
ilers | +1.541 |
fter | +1.527 |
ghan | +1.459 |
lder | +1.388 |
Neg logit contributions | |
ioned | -1.774 |
inatory | -1.712 |
eenth | -1.595 |
enance | -1.585 |
atural | -1.577 |
Token | Medicare |
Token ID | 13771 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
iler | +3.247 |
ilers | +2.883 |
fter | +2.878 |
ghan | +2.802 |
lder | +2.645 |
Neg logit contributions | |
ioned | -2.854 |
inatory | -2.770 |
eenth | -2.571 |
atural | -2.549 |
enance | -2.547 |
Token | Alliance |
Token ID | 10302 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
iler | +2.263 |
ilers | +1.987 |
fter | +1.976 |
ghan | +1.895 |
lder | +1.806 |
Neg logit contributions | |
ioned | -2.289 |
inatory | -2.233 |
eenth | -2.072 |
atural | -2.058 |
enance | -2.047 |
Token | have |
Token ID | 423 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
iler | +0.726 |
ilers | +0.614 |
fter | +0.602 |
ghan | +0.562 |
llor | +0.523 |
Neg logit contributions | |
ioned | -1.230 |
inatory | -1.199 |
eenth | -1.131 |
enance | -1.126 |
alities | -1.124 |
Token | already |
Token ID | 1541 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
ioned | +0.562 |
inatory | +0.545 |
eenth | +0.512 |
enance | +0.510 |
alities | +0.507 |
Neg logit contributions | |
iler | -0.415 |
ilers | -0.358 |
fter | -0.353 |
ghan | -0.333 |
lder | -0.312 |
Token | tried |
Token ID | 3088 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
iler | +3.390 |
ilers | +2.856 |
fter | +2.826 |
ghan | +2.640 |
lder | +2.487 |
Neg logit contributions | |
ioned | -5.253 |
inatory | -5.159 |
eenth | -4.814 |
atural | -4.772 |
enance | -4.768 |
Token | the |
Token ID | 262 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ioned | +2.871 |
inatory | +2.779 |
eenth | +2.588 |
enance | +2.580 |
alities | +2.568 |
Neg logit contributions | |
iler | -2.630 |
ilers | -2.308 |
fter | -2.295 |
ghan | -2.170 |
lder | -2.039 |
Token | basic |
Token ID | 4096 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
ioned | +2.139 |
inatory | +2.077 |
eenth | +1.943 |
enance | +1.932 |
alities | +1.924 |
Neg logit contributions | |
iler | -1.827 |
ilers | -1.602 |
fter | -1.585 |
ghan | -1.505 |
llor | -1.410 |
Token | steps |
Token ID | 4831 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
ioned | +0.321 |
inatory | +0.311 |
eenth | +0.291 |
enance | +0.288 |
atural | +0.287 |
Neg logit contributions | |
iler | -0.289 |
ilers | -0.253 |
fter | -0.249 |
ghan | -0.237 |
lder | -0.225 |
Token | to |
Token ID | 284 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
iler | +3.359 |
ilers | +2.862 |
fter | +2.851 |
ghan | +2.653 |
lder | +2.546 |
Neg logit contributions | |
ioned | -4.779 |
inatory | -4.704 |
eenth | -4.369 |
atural | -4.358 |
enance | -4.342 |
Token | improve |
Token ID | 2987 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
iler | +1.128 |
ilers | +0.970 |
fter | +0.949 |
ghan | +0.893 |
lder | +0.838 |
Neg logit contributions | |
ioned | -1.596 |
inatory | -1.547 |
eenth | -1.457 |
enance | -1.447 |
atural | -1.441 |
Token | signal |
Token ID | 6737 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
iler | +4.074 |
ilers | +3.525 |
fter | +3.433 |
ghan | +3.254 |
lder | +3.055 |
Neg logit contributions | |
ioned | -4.753 |
inatory | -4.646 |
atural | -4.312 |
eenth | -4.302 |
alities | -4.191 |
Token | conditions |
Token ID | 3403 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
iler | +0.645 |
ilers | +0.562 |
fter | +0.557 |
ghan | +0.526 |
lder | +0.497 |
Neg logit contributions | |
ioned | -0.744 |
inatory | -0.718 |
eenth | -0.676 |
enance | -0.664 |
atural | -0.663 |
Token | by |
Token ID | 416 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
ioned | +1.330 |
inatory | +1.284 |
eenth | +1.197 |
enance | +1.193 |
alities | +1.187 |
Neg logit contributions | |
iler | -1.270 |
ilers | -1.121 |
fter | -1.105 |
ghan | -1.052 |
lder | -0.997 |
Token | and |
Token ID | 290 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
ioned | +4.434 |
inatory | +4.260 |
eenth | +3.990 |
enance | +3.965 |
alities | +3.911 |
Neg logit contributions | |
iler | -5.021 |
ilers | -4.492 |
fter | -4.429 |
ghan | -4.244 |
llor | -4.059 |
Token | tele |
Token ID | 5735 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
ioned | +4.254 |
inatory | +4.144 |
eenth | +3.855 |
enance | +3.836 |
alities | +3.833 |
Neg logit contributions | |
iler | -4.134 |
ilers | -3.655 |
fter | -3.609 |
ghan | -3.475 |
llor | -3.265 |
Token | phones |
Token ID | 9708 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
ioned | +2.083 |
inatory | +1.997 |
eenth | +1.773 |
alities | +1.753 |
atural | +1.743 |
Neg logit contributions | |
iler | -3.752 |
fter | -3.396 |
ilers | -3.395 |
ghan | -3.262 |
lder | -3.132 |
Token | before |
Token ID | 878 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ioned | +1.963 |
inatory | +1.896 |
eenth | +1.771 |
enance | +1.756 |
alities | +1.746 |
Neg logit contributions | |
iler | -1.913 |
ilers | -1.690 |
fter | -1.668 |
ghan | -1.588 |
lder | -1.504 |
Token | electrical |
Token ID | 12278 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
iler | +0.784 |
ilers | +0.684 |
fter | +0.672 |
ghan | +0.635 |
lder | +0.612 |
Neg logit contributions | |
ioned | -0.923 |
inatory | -0.892 |
enance | -0.831 |
eenth | -0.829 |
atural | -0.823 |
Token | generation |
Token ID | 5270 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
iler | +4.886 |
ilers | +4.319 |
fter | +4.242 |
ghan | +4.023 |
lder | +3.898 |
Neg logit contributions | |
ioned | -4.850 |
inatory | -4.652 |
eenth | -4.413 |
atural | -4.372 |
enance | -4.348 |
Token | was |
Token ID | 373 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
iler | +3.326 |
ilers | +2.897 |
fter | +2.838 |
ghan | +2.647 |
lder | +2.563 |
Neg logit contributions | |
ioned | -3.976 |
inatory | -3.905 |
eenth | -3.628 |
atural | -3.572 |
enance | -3.561 |
Token | perfected |
Token ID | 42155 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
iler | +0.494 |
ilers | +0.426 |
fter | +0.420 |
ghan | +0.395 |
lder | +0.372 |
Neg logit contributions | |
ioned | -0.670 |
inatory | -0.652 |
eenth | -0.611 |
enance | -0.606 |
alities | -0.605 |
Token | . |
Token ID | 13 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
iler | +1.072 |
ilers | +0.932 |
fter | +0.917 |
ghan | +0.870 |
lder | +0.820 |
Neg logit contributions | |
ioned | -1.275 |
inatory | -1.245 |
eenth | -1.156 |
enance | -1.152 |
alities | -1.142 |
Token |
|
Token ID | 198 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ioned | +0.288 |
inatory | +0.280 |
eenth | +0.259 |
enance | +0.259 |
alities | +0.257 |
Neg logit contributions | |
iler | -0.257 |
ilers | -0.225 |
fter | -0.223 |
ghan | -0.212 |
lder | -0.201 |
Token |
|
Token ID | 198 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ioned | +0.306 |
inatory | +0.292 |
eenth | +0.276 |
enance | +0.275 |
alities | +0.270 |
Neg logit contributions | |
iler | -0.316 |
ilers | -0.283 |
fter | -0.275 |
ghan | -0.262 |
llor | -0.251 |
Token | 4 |
Token ID | 604 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
iler | +5.059 |
fter | +4.251 |
ilers | +4.180 |
ghan | +3.893 |
lder | +3.621 |
Neg logit contributions | |
ioned | -8.381 |
inatory | -8.127 |
eenth | -7.645 |
atural | -7.570 |
enance | -7.542 |
Token | D |
Token ID | 360 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
ioned | +1.793 |
inatory | +1.735 |
eenth | +1.606 |
enance | +1.601 |
alities | +1.598 |
Neg logit contributions | |
iler | -1.817 |
ilers | -1.610 |
fter | -1.588 |
ghan | -1.516 |
lder | -1.439 |
Token | DoS |
Token ID | 46498 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
iler | +4.032 |
ilers | +3.501 |
fter | +3.451 |
ghan | +3.237 |
lder | +3.038 |
Neg logit contributions | |
ioned | -5.074 |
inatory | -4.894 |
eenth | -4.627 |
enance | -4.580 |
atural | -4.561 |
Token | attacks |
Token ID | 3434 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
iler | +5.441 |
ilers | +4.756 |
fter | +4.591 |
ghan | +4.404 |
lder | +4.116 |
Neg logit contributions | |
ioned | -5.910 |
inatory | -5.641 |
eenth | -5.373 |
enance | -5.299 |
atural | -5.244 |
Token | as |
Token ID | 355 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
iler | +4.010 |
ilers | +3.480 |
fter | +3.413 |
ghan | +3.252 |
lder | +3.010 |
Neg logit contributions | |
ioned | -5.045 |
inatory | -4.931 |
eenth | -4.587 |
atural | -4.507 |
enance | -4.497 |
Token | well |
Token ID | 880 |
Feature activation | -8.42e+00 |
Pos logit contributions | |
iler | +1.101 |
ilers | +0.900 |
fter | +0.884 |
ghan | +0.805 |
lder | +0.748 |
Neg logit contributions | |
ioned | -2.315 |
inatory | -2.264 |
eenth | -2.149 |
enance | -2.135 |
atural | -2.124 |
Token | as |
Token ID | 355 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
iler | +4.847 |
ilers | +4.042 |
fter | +3.920 |
ghan | +3.700 |
lder | +3.451 |
Neg logit contributions | |
ioned | -8.791 |
inatory | -8.541 |
eenth | -8.227 |
enance | -8.016 |
ogether | -8.002 |
Token | Customer |
Token ID | 22092 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
iler | +1.533 |
ilers | +1.342 |
fter | +1.324 |
ghan | +1.255 |
lder | +1.188 |
Neg logit contributions | |
ioned | -1.721 |
inatory | -1.662 |
eenth | -1.563 |
atural | -1.539 |
enance | -1.538 |
Token | Prem |
Token ID | 6929 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
ioned | +2.180 |
inatory | +2.114 |
eenth | +1.959 |
enance | +1.943 |
alities | +1.939 |
Neg logit contributions | |
iler | -2.153 |
ilers | -1.906 |
fter | -1.878 |
ghan | -1.789 |
llor | -1.700 |
Token | ise |
Token ID | 786 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
ioned | +2.136 |
inatory | +2.052 |
eenth | +1.868 |
enance | +1.850 |
alities | +1.838 |
Neg logit contributions | |
iler | -3.183 |
ilers | -2.875 |
fter | -2.844 |
ghan | -2.734 |
lder | -2.626 |
Token | Equipment |
Token ID | 22412 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
iler | +0.805 |
ilers | +0.708 |
fter | +0.698 |
ghan | +0.659 |
lder | +0.628 |
Neg logit contributions | |
ioned | -0.841 |
inatory | -0.817 |
eenth | -0.763 |
enance | -0.754 |
atural | -0.751 |
Token | . |
Token ID | 13 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
iler | +2.081 |
ilers | +1.807 |
fter | +1.776 |
ghan | +1.668 |
lder | +1.604 |
Neg logit contributions | |
ioned | -2.563 |
inatory | -2.496 |
eenth | -2.351 |
enance | -2.324 |
atural | -2.320 |
Token | There |
Token ID | 1318 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
iler | +0.696 |
ilers | +0.612 |
fter | +0.608 |
ghan | +0.580 |
lder | +0.554 |
Neg logit contributions | |
ioned | -0.700 |
inatory | -0.678 |
eenth | -0.626 |
enance | -0.622 |
atural | -0.621 |
Token | are |
Token ID | 389 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ioned | +4.039 |
inatory | +3.948 |
eenth | +3.591 |
enance | +3.567 |
atural | +3.566 |
Neg logit contributions | |
iler | -4.657 |
ilers | -4.173 |
fter | -4.098 |
ghan | -3.922 |
llor | -3.747 |
Token | some |
Token ID | 617 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ioned | +0.560 |
inatory | +0.544 |
eenth | +0.510 |
enance | +0.507 |
alities | +0.504 |
Neg logit contributions | |
iler | -0.437 |
ilers | -0.379 |
fter | -0.374 |
ghan | -0.353 |
lder | -0.332 |
Token | downs |
Token ID | 21838 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ioned | +1.753 |
inatory | +1.702 |
eenth | +1.590 |
enance | +1.577 |
alities | +1.572 |
Neg logit contributions | |
iler | -1.530 |
ilers | -1.342 |
fter | -1.318 |
ghan | -1.252 |
llor | -1.178 |
Token | ides |
Token ID | 1460 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
iler | +0.723 |
ilers | +0.608 |
fter | +0.598 |
ghan | +0.553 |
lder | +0.513 |
Neg logit contributions | |
ioned | -1.265 |
inatory | -1.236 |
enance | -1.163 |
eenth | -1.161 |
atural | -1.147 |
Token | , |
Token ID | 11 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
iler | +5.568 |
fter | +4.773 |
ilers | +4.751 |
ghan | +4.435 |
lder | +4.260 |
Neg logit contributions | |
ioned | -7.781 |
inatory | -7.646 |
eenth | -7.128 |
atural | -7.054 |
inators | -7.004 |
Token | like |
Token ID | 588 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
iler | +0.520 |
ilers | +0.453 |
fter | +0.446 |
ghan | +0.423 |
lder | +0.399 |
Neg logit contributions | |
ioned | -0.627 |
inatory | -0.608 |
eenth | -0.569 |
enance | -0.565 |
alities | -0.562 |
Token | having |
Token ID | 1719 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
iler | +1.580 |
ilers | +1.371 |
fter | +1.363 |
ghan | +1.288 |
lder | +1.236 |
Neg logit contributions | |
ioned | -1.878 |
inatory | -1.824 |
eenth | -1.711 |
atural | -1.689 |
enance | -1.689 |
Token | to |
Token ID | 284 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
ioned | +2.843 |
inatory | +2.769 |
eenth | +2.575 |
enance | +2.562 |
alities | +2.547 |
Neg logit contributions | |
iler | -2.511 |
ilers | -2.205 |
fter | -2.171 |
ghan | -2.054 |
llor | -1.932 |
Token | wait |
Token ID | 4043 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
iler | +1.811 |
ilers | +1.554 |
fter | +1.529 |
ghan | +1.438 |
lder | +1.346 |
Neg logit contributions | |
ioned | -2.606 |
inatory | -2.534 |
eenth | -2.384 |
enance | -2.369 |
alities | -2.357 |
Token | b |
Token ID | 65 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
iler | +3.168 |
fter | +2.706 |
ilers | +2.705 |
ghan | +2.548 |
lder | +2.416 |
Neg logit contributions | |
ioned | -4.183 |
inatory | -4.084 |
eenth | -3.825 |
enance | -3.796 |
alities | -3.757 |
Token | ] |
Token ID | 60 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
iler | +2.014 |
ilers | +1.711 |
fter | +1.694 |
ghan | +1.604 |
lder | +1.518 |
Neg logit contributions | |
ioned | -2.514 |
inatory | -2.423 |
eenth | -2.271 |
enance | -2.250 |
atural | -2.238 |
Token | Personal |
Token ID | 30228 |
Feature activation | +8.86e+00 |
Pos logit contributions | |
iler | +1.871 |
ilers | +1.638 |
fter | +1.632 |
ghan | +1.553 |
lder | +1.469 |
Neg logit contributions | |
ioned | -1.886 |
inatory | -1.830 |
eenth | -1.694 |
enance | -1.682 |
alities | -1.668 |
Token | best |
Token ID | 1266 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
ioned | +7.659 |
inatory | +7.376 |
alities | +7.037 |
eenth | +6.949 |
atural | +6.919 |
Neg logit contributions | |
iler | -6.640 |
ilers | -5.951 |
fter | -5.727 |
ghan | -5.423 |
lder | -5.270 |
Token | : |
Token ID | 25 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ioned | +0.038 |
inatory | +0.037 |
eenth | +0.034 |
enance | +0.034 |
atural | +0.034 |
Neg logit contributions | |
iler | -0.033 |
ilers | -0.029 |
fter | -0.029 |
ghan | -0.027 |
lder | -0.026 |
Token | [/ |
Token ID | 13412 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
iler | +0.130 |
ilers | +0.118 |
fter | +0.118 |
ghan | +0.114 |
lder | +0.110 |
Neg logit contributions | |
ioned | -0.061 |
inatory | -0.058 |
eenth | -0.051 |
enance | -0.050 |
alities | -0.050 |
Token | b |
Token ID | 65 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
iler | +6.885 |
fter | +6.128 |
ilers | +5.887 |
ghan | +5.793 |
lder | +5.378 |
Neg logit contributions | |
ioned | -9.195 |
inatory | -8.962 |
eenth | -8.421 |
nesday | -8.324 |
enance | -8.282 |
Token | ] |
Token ID | 60 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
iler | +1.671 |
ilers | +1.422 |
fter | +1.409 |
ghan | +1.337 |
lder | +1.254 |
Neg logit contributions | |
ioned | -2.236 |
inatory | -2.157 |
eenth | -2.023 |
enance | -2.003 |
atural | -1.993 |
Token | 1 |
Token ID | 352 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
iler | +1.365 |
ilers | +1.182 |
fter | +1.175 |
ghan | +1.117 |
lder | +1.049 |
Neg logit contributions | |
ioned | -1.634 |
inatory | -1.587 |
eenth | -1.483 |
enance | -1.474 |
alities | -1.467 |
Token | : |
Token ID | 25 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
ioned | +0.757 |
inatory | +0.736 |
eenth | +0.688 |
enance | +0.683 |
alities | +0.680 |
Neg logit contributions | |
iler | -0.614 |
ilers | -0.534 |
fter | -0.526 |
ghan | -0.498 |
lder | -0.469 |
Token | 07 |
Token ID | 2998 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
iler | +2.288 |
ilers | +1.980 |
fter | +1.969 |
ghan | +1.861 |
lder | +1.752 |
Neg logit contributions | |
ioned | -2.858 |
inatory | -2.782 |
eenth | -2.583 |
atural | -2.573 |
enance | -2.566 |
Token | up |
Token ID | 510 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ioned | +2.936 |
inatory | +2.834 |
eenth | +2.656 |
enance | +2.642 |
alities | +2.628 |
Neg logit contributions | |
iler | -2.676 |
ilers | -2.370 |
fter | -2.315 |
ghan | -2.205 |
llor | -2.088 |
Token | with |
Token ID | 351 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ioned | +1.877 |
inatory | +1.817 |
eenth | +1.694 |
enance | +1.685 |
alities | +1.673 |
Neg logit contributions | |
iler | -1.725 |
ilers | -1.518 |
fter | -1.493 |
ghan | -1.419 |
lder | -1.344 |
Token | the |
Token ID | 262 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
ioned | +0.962 |
inatory | +0.932 |
eenth | +0.870 |
enance | +0.863 |
alities | +0.859 |
Neg logit contributions | |
iler | -0.868 |
ilers | -0.762 |
fter | -0.751 |
ghan | -0.714 |
lder | -0.675 |
Token | two |
Token ID | 734 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ioned | +0.041 |
inatory | +0.040 |
eenth | +0.038 |
enance | +0.037 |
alities | +0.037 |
Neg logit contributions | |
iler | -0.034 |
ilers | -0.030 |
fter | -0.029 |
ghan | -0.028 |
lder | -0.026 |
Token | top |
Token ID | 1353 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ioned | +1.585 |
inatory | +1.528 |
eenth | +1.440 |
alities | +1.421 |
enance | +1.420 |
Neg logit contributions | |
iler | -1.384 |
ilers | -1.217 |
fter | -1.196 |
ghan | -1.145 |
llor | -1.071 |
Token | yo |
Token ID | 27406 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
iler | +1.451 |
ilers | +1.275 |
fter | +1.254 |
ghan | +1.186 |
lder | +1.129 |
Neg logit contributions | |
ioned | -1.575 |
inatory | -1.527 |
enance | -1.414 |
eenth | -1.413 |
atural | -1.395 |
Token | - |
Token ID | 12 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
iler | +8.602 |
ilers | +7.456 |
fter | +7.036 |
ghan | +6.677 |
lder | +6.129 |
Neg logit contributions | |
ioned | -12.632 |
inatory | -12.092 |
enance | -11.707 |
eenth | -11.588 |
nesday | -11.223 |
Token | y |
Token ID | 88 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
iler | +2.171 |
ilers | +1.892 |
fter | +1.846 |
ghan | +1.737 |
lder | +1.617 |
Neg logit contributions | |
ioned | -2.952 |
inatory | -2.865 |
enance | -2.688 |
eenth | -2.671 |
alities | -2.628 |
Token | os |
Token ID | 418 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
iler | +3.021 |
ilers | +2.726 |
fter | +2.687 |
ghan | +2.570 |
lder | +2.457 |
Neg logit contributions | |
ioned | -2.296 |
inatory | -2.206 |
eenth | -2.022 |
enance | -2.001 |
atural | -1.962 |
Token | in |
Token ID | 287 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
iler | +4.114 |
ilers | +3.548 |
fter | +3.477 |
ghan | +3.292 |
lder | +3.135 |
Neg logit contributions | |
ioned | -5.199 |
inatory | -5.142 |
eenth | -4.754 |
enance | -4.731 |
atural | -4.725 |
Token | this |
Token ID | 428 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
iler | +2.332 |
ilers | +2.025 |
fter | +1.991 |
ghan | +1.881 |
lder | +1.798 |
Neg logit contributions | |
ioned | -2.785 |
inatory | -2.696 |
eenth | -2.529 |
enance | -2.516 |
alities | -2.483 |
Token | ke |
Token ID | 885 |
Feature activation | -9.94e+00 |
Pos logit contributions | |
iler | +5.633 |
fter | +4.915 |
ilers | +4.820 |
ghan | +4.648 |
lder | +4.311 |
Neg logit contributions | |
ioned | -6.810 |
inatory | -6.597 |
eenth | -6.240 |
enance | -6.210 |
alities | -6.073 |
Token | ke |
Token ID | 885 |
Feature activation | -9.41e+00 |
Pos logit contributions | |
iler | +7.758 |
fter | +6.785 |
ilers | +6.650 |
ghan | +6.377 |
lder | +6.016 |
Neg logit contributions | |
ioned | -8.232 |
inatory | -8.054 |
eenth | -7.578 |
enance | -7.436 |
atural | -7.403 |
Token | iki |
Token ID | 5580 |
Feature activation | -7.29e+00 |
Pos logit contributions | |
iler | +7.184 |
fter | +6.289 |
ilers | +6.135 |
ghan | +5.881 |
lder | +5.531 |
Neg logit contributions | |
ioned | -8.057 |
inatory | -7.854 |
eenth | -7.422 |
enance | -7.298 |
atural | -7.250 |
Token | e |
Token ID | 304 |
Feature activation | -9.88e+00 |
Pos logit contributions | |
iler | +5.111 |
fter | +4.409 |
ilers | +4.338 |
ghan | +4.119 |
lder | +3.837 |
Neg logit contributions | |
ioned | -6.803 |
inatory | -6.658 |
eenth | -6.273 |
enance | -6.182 |
alities | -6.153 |
Token | ki |
Token ID | 47748 |
Feature activation | -9.75e+00 |
Pos logit contributions | |
iler | +7.225 |
fter | +6.385 |
ilers | +6.148 |
ghan | +5.929 |
lder | +5.511 |
Neg logit contributions | |
ioned | -8.659 |
inatory | -8.402 |
eenth | -7.945 |
enance | -7.827 |
inators | -7.743 |
Token | � |
Token ID | 134 |
Feature activation | -9.93e+00 |
Pos logit contributions | |
iler | +6.972 |
fter | +5.998 |
ilers | +5.864 |
ghan | +5.711 |
lder | +5.326 |
Neg logit contributions | |
ioned | -8.807 |
inatory | -8.541 |
enance | -8.050 |
eenth | -8.011 |
alities | -7.977 |
Token | � |
Token ID | 119 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
iler | +4.001 |
fter | +3.211 |
ilers | +2.914 |
ghan | +2.855 |
lder | +2.587 |
Neg logit contributions | |
ioned | -12.182 |
inatory | -11.899 |
alities | -11.284 |
atural | -11.201 |
eenth | -11.170 |
Token | i |
Token ID | 72 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
iler | +1.718 |
ilers | +1.516 |
fter | +1.500 |
ghan | +1.428 |
lder | +1.361 |
Neg logit contributions | |
ioned | -1.577 |
inatory | -1.528 |
eenth | -1.420 |
enance | -1.404 |
alities | -1.401 |
Token | i |
Token ID | 1312 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
iler | +3.639 |
fter | +3.143 |
ilers | +3.102 |
ghan | +2.953 |
lder | +2.751 |
Neg logit contributions | |
ioned | -4.733 |
inatory | -4.617 |
eenth | -4.362 |
enance | -4.298 |
alities | -4.292 |
Token | n |
Token ID | 299 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
iler | +4.277 |
fter | +3.703 |
ilers | +3.640 |
ghan | +3.492 |
lder | +3.264 |
Neg logit contributions | |
ioned | -5.475 |
inatory | -5.337 |
eenth | -5.031 |
enance | -4.985 |
alities | -4.977 |
Token | ā |
Token ID | 10235 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
iler | +0.692 |
ilers | +0.611 |
fter | +0.605 |
ghan | +0.579 |
lder | +0.550 |
Neg logit contributions | |
ioned | -0.636 |
inatory | -0.616 |
eenth | -0.572 |
enance | -0.565 |
alities | -0.563 |