Token | = |
Token ID | 796 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
arine | +0.026 |
hess | +0.025 |
illin | +0.025 |
PF | +0.025 |
igan | +0.024 |
Neg logit contributions | |
� | -0.021 |
� | -0.019 |
verning | -0.018 |
Crim | -0.018 |
� | -0.018 |
Token | c |
Token ID | 269 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
arine | +0.228 |
hess | +0.213 |
illin | +0.212 |
PF | +0.211 |
igan | +0.208 |
Neg logit contributions | |
� | -0.334 |
� | -0.305 |
verning | -0.298 |
�� | -0.297 |
� | -0.295 |
Token | v |
Token ID | 85 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
� | +1.349 |
� | +1.211 |
wat | +1.191 |
verning | +1.185 |
Crim | +1.166 |
Neg logit contributions | |
arine | -1.382 |
illin | -1.311 |
hess | -1.300 |
PF | -1.300 |
�� | -1.283 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
� | +1.323 |
� | +1.174 |
Crim | +1.134 |
verning | +1.130 |
wat | +1.125 |
Neg logit contributions | |
arine | -1.607 |
illin | -1.530 |
hess | -1.521 |
PF | -1.505 |
�� | -1.489 |
Token | . |
Token ID | 764 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
arine | +1.099 |
hess | +1.034 |
PF | +1.027 |
illin | +1.019 |
igan | +1.012 |
Neg logit contributions | |
� | -1.771 |
� | -1.630 |
�� | -1.609 |
verning | -1.585 |
� | -1.574 |
Token | Ga |
Token ID | 12822 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
arine | +5.406 |
igan | +5.364 |
hess | +5.348 |
payoff | +5.306 |
illin | +5.243 |
Neg logit contributions | |
� | -7.834 |
� | -7.152 |
� | -7.144 |
verning | -7.129 |
wat | -7.078 |
Token | ussian |
Token ID | 31562 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
arine | +4.395 |
igan | +4.240 |
hess | +4.030 |
illin | +3.779 |
PF | +3.682 |
Neg logit contributions | |
� | -14.498 |
�� | -13.736 |
� | -13.631 |
Crim | -13.437 |
� | -13.380 |
Token | Bl |
Token ID | 3629 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
PF | +5.942 |
BG | +5.891 |
arine | +5.848 |
KR | +5.664 |
igan | +5.660 |
Neg logit contributions | |
� | -7.094 |
�� | -6.678 |
� | -6.559 |
�� | -6.465 |
verning | -6.409 |
Token | ur |
Token ID | 333 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
arine | +5.787 |
igan | +5.278 |
illin | +5.230 |
hess | +5.194 |
flame | +5.022 |
Neg logit contributions | |
� | -9.361 |
�� | -8.670 |
� | -8.521 |
�� | -8.333 |
Crim | -8.289 |
Token | ( |
Token ID | 357 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
arine | +3.474 |
PF | +3.425 |
igan | +3.269 |
hess | +3.230 |
illin | +3.187 |
Neg logit contributions | |
� | -6.649 |
�� | -6.367 |
� | -6.240 |
� | -6.066 |
�� | -6.040 |
Token | gray |
Token ID | 12768 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
arine | +5.073 |
hess | +4.917 |
igan | +4.897 |
payoff | +4.842 |
illin | +4.783 |
Neg logit contributions | |
� | -7.713 |
� | -6.895 |
�� | -6.881 |
verning | -6.708 |
� | -6.708 |
Token | uring |
Token ID | 870 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
arine | +2.455 |
illin | +2.233 |
PF | +2.223 |
igan | +2.164 |
hess | +2.163 |
Neg logit contributions | |
� | -5.498 |
� | -5.187 |
�� | -5.082 |
� | -5.021 |
� | -5.014 |
Token | Element |
Token ID | 20180 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
arine | +3.452 |
PF | +3.319 |
hess | +3.270 |
illin | +3.201 |
igan | +3.196 |
Neg logit contributions | |
� | -5.336 |
� | -4.865 |
�� | -4.850 |
verning | -4.764 |
�� | -4.722 |
Token | ( |
Token ID | 7 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
arine | +0.842 |
PF | +0.803 |
hess | +0.803 |
illin | +0.801 |
igan | +0.793 |
Neg logit contributions | |
� | -0.647 |
� | -0.574 |
�� | -0.557 |
verning | -0.550 |
� | -0.544 |
Token | cv |
Token ID | 33967 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
arine | +1.270 |
hess | +1.204 |
illin | +1.199 |
PF | +1.195 |
igan | +1.180 |
Neg logit contributions | |
� | -1.388 |
� | -1.253 |
�� | -1.217 |
verning | -1.217 |
Crim | -1.204 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
arine | +0.995 |
hess | +0.945 |
PF | +0.942 |
illin | +0.940 |
igan | +0.931 |
Neg logit contributions | |
� | -0.992 |
� | -0.892 |
�� | -0.877 |
verning | -0.868 |
� | -0.852 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
arine | +0.785 |
hess | +0.745 |
PF | +0.743 |
illin | +0.738 |
igan | +0.733 |
Neg logit contributions | |
� | -0.873 |
� | -0.791 |
�� | -0.779 |
verning | -0.765 |
� | -0.758 |
Token | M |
Token ID | 44 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
PF | +6.168 |
RFC | +5.611 |
BG | +5.567 |
KR | +5.554 |
arine | +5.278 |
Neg logit contributions | |
� | -12.181 |
� | -11.278 |
verning | -11.100 |
�� | -11.088 |
� | -10.967 |
Token | OR |
Token ID | 1581 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
arine | +1.617 |
PF | +1.502 |
hess | +1.423 |
illin | +1.406 |
igan | +1.381 |
Neg logit contributions | |
� | -5.576 |
� | -5.236 |
verning | -5.169 |
�� | -5.159 |
Crim | -5.106 |
Token | PH |
Token ID | 11909 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
PF | +2.454 |
arine | +2.426 |
hess | +2.253 |
BG | +2.197 |
RFC | +2.164 |
Neg logit contributions | |
� | -6.892 |
� | -6.462 |
�� | -6.352 |
verning | -6.325 |
� | -6.251 |
Token | _ |
Token ID | 62 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
arine | +3.378 |
PF | +3.280 |
hess | +3.190 |
igan | +3.171 |
illin | +3.157 |
Neg logit contributions | |
� | -3.729 |
�� | -3.408 |
� | -3.376 |
verning | -3.271 |
� | -3.262 |
Token | RECT |
Token ID | 23988 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
PF | +5.558 |
BG | +5.277 |
arine | +5.184 |
RFC | +5.180 |
KR | +5.069 |
Neg logit contributions | |
� | -9.029 |
�� | -8.355 |
� | -8.315 |
verning | -8.295 |
Crim | -8.184 |
Token | 2 |
Token ID | 17 |
Feature activation | -9.13e-04 |
Pos logit contributions | |
� | +1.638 |
� | +1.446 |
Crim | +1.400 |
verning | +1.393 |
wat | +1.393 |
Neg logit contributions | |
arine | -2.046 |
illin | -1.947 |
hess | -1.938 |
PF | -1.917 |
�� | -1.916 |
Token | . |
Token ID | 764 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
� | +0.007 |
� | +0.006 |
verning | +0.006 |
�� | +0.006 |
Crim | +0.006 |
Neg logit contributions | |
arine | -0.005 |
hess | -0.004 |
illin | -0.004 |
PF | -0.004 |
igan | -0.004 |
Token | MOR |
Token ID | 35208 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
arine | +5.120 |
PF | +5.113 |
igan | +4.981 |
illin | +4.910 |
payoff | +4.865 |
Neg logit contributions | |
� | -10.700 |
� | -9.982 |
� | -9.853 |
verning | -9.811 |
wat | -9.732 |
Token | PH |
Token ID | 11909 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
arine | +1.675 |
PF | +1.643 |
hess | +1.549 |
igan | +1.501 |
illin | +1.491 |
Neg logit contributions | |
� | -4.302 |
� | -4.051 |
verning | -3.966 |
�� | -3.960 |
� | -3.920 |
Token | _ |
Token ID | 62 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
arine | +4.591 |
PF | +4.503 |
igan | +4.333 |
hess | +4.332 |
BG | +4.290 |
Neg logit contributions | |
� | -5.436 |
�� | -5.072 |
� | -4.974 |
� | -4.834 |
�� | -4.825 |
Token | BL |
Token ID | 9148 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
BG | +3.676 |
PF | +3.645 |
KR | +3.462 |
arine | +3.461 |
RFC | +3.441 |
Neg logit contributions | |
� | -8.540 |
�� | -7.999 |
verning | -7.954 |
� | -7.911 |
� | -7.750 |
Token | ACK |
Token ID | 8120 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
BG | +5.100 |
PF | +4.985 |
KR | +4.969 |
arine | +4.805 |
RFC | +4.595 |
Neg logit contributions | |
� | -12.587 |
verning | -11.903 |
�� | -11.778 |
� | -11.519 |
Crim | -11.347 |
Token | H |
Token ID | 39 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
PF | +3.720 |
arine | +3.707 |
hess | +3.647 |
BG | +3.609 |
RFC | +3.530 |
Neg logit contributions | |
� | -6.144 |
verning | -5.608 |
�� | -5.605 |
� | -5.519 |
Crim | -5.388 |
Token | AT |
Token ID | 1404 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
arine | +0.968 |
hess | +0.905 |
PF | +0.903 |
illin | +0.896 |
igan | +0.891 |
Neg logit contributions | |
� | -1.334 |
� | -1.218 |
verning | -1.196 |
�� | -1.193 |
Crim | -1.181 |
Token | , |
Token ID | 837 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
arine | +1.298 |
PF | +1.195 |
hess | +1.191 |
illin | +1.171 |
igan | +1.171 |
Neg logit contributions | |
� | -3.151 |
� | -2.928 |
�� | -2.897 |
verning | -2.859 |
� | -2.841 |
Token | rect |
Token ID | 13621 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
arine | +2.708 |
hess | +2.571 |
illin | +2.528 |
PF | +2.525 |
igan | +2.512 |
Neg logit contributions | |
� | -3.219 |
� | -2.940 |
verning | -2.881 |
�� | -2.845 |
� | -2.819 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
� | +1.187 |
� | +1.062 |
verning | +1.037 |
Crim | +1.026 |
wat | +1.020 |
Neg logit contributions | |
arine | -1.211 |
illin | -1.148 |
hess | -1.145 |
PF | -1.128 |
igan | -1.119 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
arine | +1.102 |
hess | +1.044 |
PF | +1.041 |
illin | +1.029 |
igan | +1.024 |
Neg logit contributions | |
� | -1.517 |
� | -1.391 |
�� | -1.373 |
� | -1.348 |
� | -1.348 |
Token | R |
Token ID | 49 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
PF | +2.959 |
arine | +2.944 |
RFC | +2.794 |
illin | +2.738 |
hess | +2.717 |
Neg logit contributions | |
� | -8.763 |
�� | -8.246 |
� | -8.241 |
verning | -8.114 |
� | -8.041 |
Token | iff |
Token ID | 733 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
arine | +1.901 |
illin | +1.772 |
hess | +1.758 |
PF | +1.733 |
igan | +1.720 |
Neg logit contributions | |
� | -4.656 |
� | -4.334 |
�� | -4.271 |
� | -4.225 |
� | -4.222 |
Token | Tra |
Token ID | 15721 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
� | +0.099 |
� | +0.089 |
verning | +0.086 |
Crim | +0.085 |
�� | +0.085 |
Neg logit contributions | |
arine | -0.101 |
hess | -0.096 |
illin | -0.096 |
PF | -0.095 |
igan | -0.094 |
Token | x |
Token ID | 87 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
arine | +0.877 |
hess | +0.836 |
illin | +0.829 |
PF | +0.828 |
igan | +0.821 |
Neg logit contributions | |
� | -0.833 |
� | -0.748 |
�� | -0.738 |
verning | -0.722 |
� | -0.717 |
Token |
|
Token ID | 198 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
arine | +6.582 |
PF | +6.434 |
illin | +6.190 |
igan | +6.162 |
payoff | +5.977 |
Neg logit contributions | |
� | -10.389 |
� | -9.636 |
�� | -9.615 |
� | -9.586 |
verning | -9.470 |
Token |
|
Token ID | 198 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
arine | +3.964 |
PF | +3.851 |
igan | +3.794 |
hess | +3.765 |
illin | +3.669 |
Neg logit contributions | |
� | -7.023 |
�� | -6.828 |
� | -6.529 |
�� | -6.429 |
� | -6.406 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
arine | +2.359 |
PF | +2.277 |
hess | +2.214 |
illin | +2.188 |
igan | +2.132 |
Neg logit contributions | |
� | -4.710 |
� | -4.384 |
�� | -4.320 |
verning | -4.314 |
Crim | -4.256 |
Token | : |
Token ID | 25 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
� | +2.481 |
� | +2.189 |
wat | +2.146 |
Crim | +2.135 |
verning | +2.119 |
Neg logit contributions | |
arine | -2.703 |
illin | -2.569 |
hess | -2.540 |
�� | -2.522 |
PF | -2.511 |
Token | V |
Token ID | 569 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
arine | +3.484 |
illin | +3.321 |
PF | +3.318 |
hess | +3.313 |
igan | +3.262 |
Neg logit contributions | |
� | -3.815 |
� | -3.444 |
verning | -3.390 |
�� | -3.351 |
� | -3.299 |
Token | resize |
Token ID | 47558 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
arine | +3.504 |
payoff | +3.221 |
backfield | +3.156 |
illin | +3.125 |
igan | +3.119 |
Neg logit contributions | |
� | -11.127 |
�� | -10.564 |
� | -10.387 |
� | -10.289 |
� | -10.177 |
Token | ( |
Token ID | 357 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
arine | +3.844 |
PF | +3.820 |
hess | +3.620 |
igan | +3.616 |
illin | +3.539 |
Neg logit contributions | |
� | -7.811 |
�� | -7.397 |
� | -7.291 |
verning | -7.015 |
� | -7.014 |
Token | image |
Token ID | 2939 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
arine | +1.854 |
igan | +1.621 |
hess | +1.618 |
illin | +1.611 |
PF | +1.555 |
Neg logit contributions | |
� | -6.769 |
� | -6.304 |
�� | -6.265 |
verning | -6.247 |
Crim | -6.163 |
Token | , |
Token ID | 837 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
arine | +2.505 |
PF | +2.385 |
hess | +2.304 |
igan | +2.250 |
illin | +2.191 |
Neg logit contributions | |
� | -7.486 |
� | -7.028 |
�� | -7.006 |
�� | -6.848 |
verning | -6.798 |
Token | height |
Token ID | 6001 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
arine | +1.498 |
hess | +1.358 |
PF | +1.267 |
igan | +1.228 |
payoff | +1.219 |
Neg logit contributions | |
� | -9.119 |
� | -8.559 |
�� | -8.526 |
verning | -8.370 |
� | -8.255 |
Token | = |
Token ID | 796 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
arine | +3.464 |
PF | +3.354 |
hess | +3.314 |
igan | +3.285 |
illin | +3.278 |
Neg logit contributions | |
� | -3.572 |
� | -3.247 |
�� | -3.184 |
verning | -3.099 |
� | -3.085 |
Token | 600 |
Token ID | 10053 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
arine | +5.301 |
PF | +5.280 |
illin | +5.048 |
PG | +5.045 |
enrol | +4.872 |
Neg logit contributions | |
� | -12.127 |
� | -11.345 |
�� | -11.095 |
wat | -10.772 |
verning | -10.741 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
arine | +2.217 |
hess | +2.096 |
PF | +2.094 |
illin | +2.084 |
igan | +2.065 |
Neg logit contributions | |
� | -2.916 |
� | -2.673 |
�� | -2.646 |
verning | -2.576 |
� | -2.557 |
Token | gray |
Token ID | 12768 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
arine | +5.470 |
payoff | +5.280 |
igan | +5.252 |
hess | +5.238 |
illin | +5.075 |
Neg logit contributions | |
� | -8.136 |
� | -7.278 |
verning | -7.246 |
�� | -7.129 |
wat | -7.090 |
Token | = |
Token ID | 796 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
arine | +2.444 |
hess | +2.327 |
PF | +2.320 |
illin | +2.315 |
igan | +2.311 |
Neg logit contributions | |
� | -2.363 |
� | -2.125 |
�� | -2.079 |
verning | -2.059 |
� | -2.025 |
Token | c |
Token ID | 269 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
arine | +1.095 |
hess | +1.021 |
illin | +1.015 |
PF | +1.012 |
igan | +1.002 |
Neg logit contributions | |
� | -1.762 |
� | -1.622 |
�� | -1.595 |
verning | -1.580 |
� | -1.566 |
Token | image |
Token ID | 2939 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
arine | +0.617 |
hess | +0.561 |
illin | +0.559 |
PF | +0.553 |
igan | +0.535 |
Neg logit contributions | |
� | -1.612 |
� | -1.500 |
verning | -1.468 |
Crim | -1.459 |
�� | -1.459 |
Token | = |
Token ID | 796 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
arine | +2.299 |
PF | +2.191 |
hess | +2.183 |
illin | +2.175 |
igan | +2.157 |
Neg logit contributions | |
� | -2.186 |
� | -1.972 |
�� | -1.912 |
verning | -1.910 |
� | -1.871 |
Token | c |
Token ID | 269 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
arine | +2.355 |
hess | +2.196 |
illin | +2.186 |
PF | +2.173 |
igan | +2.163 |
Neg logit contributions | |
� | -4.206 |
� | -3.900 |
�� | -3.857 |
verning | -3.816 |
� | -3.764 |
Token | v |
Token ID | 85 |
Feature activation | +5.45e-03 |
Pos logit contributions | |
arine | +2.093 |
hess | +1.989 |
illin | +1.966 |
PF | +1.959 |
igan | +1.953 |
Neg logit contributions | |
� | -2.566 |
� | -2.327 |
�� | -2.292 |
verning | -2.244 |
� | -2.235 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
arine | +0.036 |
hess | +0.034 |
illin | +0.034 |
PF | +0.034 |
igan | +0.033 |
Neg logit contributions | |
� | -0.033 |
� | -0.029 |
verning | -0.028 |
�� | -0.028 |
Crim | -0.028 |
Token | . |
Token ID | 764 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
arine | +2.177 |
PF | +2.060 |
hess | +2.059 |
igan | +2.030 |
illin | +2.013 |
Neg logit contributions | |
� | -3.983 |
� | -3.703 |
�� | -3.702 |
verning | -3.578 |
� | -3.576 |
Token | im |
Token ID | 545 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
igan | +4.614 |
payoff | +4.473 |
arine | +4.458 |
backfield | +4.380 |
illin | +4.269 |
Neg logit contributions | |
� | -12.404 |
�� | -11.779 |
verning | -11.660 |
� | -11.564 |
� | -11.510 |
Token | read |
Token ID | 961 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
arine | +4.132 |
hess | +3.853 |
flame | +3.598 |
igan | +3.510 |
illin | +3.490 |
Neg logit contributions | |
� | -9.964 |
�� | -9.535 |
� | -9.454 |
� | -9.258 |
�� | -9.205 |
Token | ( |
Token ID | 357 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
arine | +4.013 |
PF | +3.894 |
igan | +3.745 |
hess | +3.734 |
illin | +3.681 |
Neg logit contributions | |
� | -8.504 |
�� | -8.212 |
� | -7.973 |
� | -7.794 |
�� | -7.774 |
Token | image |
Token ID | 2939 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
arine | +1.663 |
igan | +1.459 |
hess | +1.453 |
illin | +1.448 |
PF | +1.402 |
Neg logit contributions | |
� | -5.921 |
� | -5.515 |
�� | -5.481 |
verning | -5.468 |
Crim | -5.392 |
Token | Path |
Token ID | 15235 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
arine | +1.146 |
PF | +1.088 |
hess | +1.086 |
illin | +1.082 |
igan | +1.067 |
Neg logit contributions | |
� | -1.148 |
� | -1.036 |
verning | -1.006 |
�� | -1.004 |
� | -0.988 |
Token | import |
Token ID | 1330 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
arine | +1.654 |
hess | +1.541 |
PF | +1.536 |
illin | +1.528 |
igan | +1.515 |
Neg logit contributions | |
� | -2.496 |
� | -2.291 |
�� | -2.237 |
verning | -2.232 |
� | -2.214 |
Token | n |
Token ID | 299 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
arine | +3.606 |
igan | +3.415 |
hess | +3.394 |
payoff | +3.344 |
PF | +3.316 |
Neg logit contributions | |
� | -7.910 |
� | -7.531 |
verning | -7.451 |
� | -7.194 |
� | -7.183 |
Token | umpy |
Token ID | 32152 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
arine | +3.370 |
hess | +3.030 |
igan | +3.002 |
illin | +2.966 |
PF | +2.904 |
Neg logit contributions | |
� | -7.777 |
� | -7.301 |
� | -7.155 |
�� | -7.144 |
� | -7.058 |
Token | as |
Token ID | 355 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
arine | +0.883 |
hess | +0.821 |
illin | +0.816 |
PF | +0.811 |
igan | +0.803 |
Neg logit contributions | |
� | -1.383 |
� | -1.271 |
�� | -1.242 |
verning | -1.238 |
Crim | -1.225 |
Token | np |
Token ID | 45941 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
arine | +5.761 |
PF | +5.593 |
hess | +5.551 |
payoff | +5.496 |
igan | +5.460 |
Neg logit contributions | |
� | -5.215 |
� | -4.847 |
�� | -4.581 |
� | -4.500 |
verning | -4.470 |
Token | import |
Token ID | 1330 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
arine | +4.206 |
igan | +3.916 |
payoff | +3.782 |
hess | +3.766 |
backfield | +3.747 |
Neg logit contributions | |
� | -8.887 |
� | -8.292 |
verning | -8.152 |
�� | -8.144 |
� | -7.995 |
Token | arg |
Token ID | 1822 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
arine | +8.776 |
igan | +8.516 |
payoff | +8.418 |
illin | +8.406 |
PF | +8.288 |
Neg logit contributions | |
� | -8.242 |
verning | -7.545 |
� | -7.284 |
wat | -7.018 |
�� | -6.938 |
Token | parse |
Token ID | 29572 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
arine | +2.985 |
hess | +2.796 |
PF | +2.772 |
illin | +2.762 |
igan | +2.736 |
Neg logit contributions | |
� | -3.688 |
� | -3.385 |
�� | -3.287 |
Crim | -3.250 |
verning | -3.239 |
Token | import |
Token ID | 1330 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
arine | +1.101 |
hess | +1.029 |
illin | +1.027 |
PF | +1.023 |
igan | +1.009 |
Neg logit contributions | |
� | -1.633 |
� | -1.495 |
�� | -1.463 |
verning | -1.458 |
� | -1.444 |
Token | im |
Token ID | 545 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
arine | +2.667 |
igan | +2.497 |
hess | +2.483 |
illin | +2.474 |
payoff | +2.438 |
Neg logit contributions | |
� | -5.581 |
�� | -5.183 |
� | -5.158 |
verning | -5.141 |
� | -5.027 |
Token | utils |
Token ID | 26791 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
arine | +0.304 |
hess | +0.285 |
illin | +0.283 |
PF | +0.282 |
igan | +0.278 |
Neg logit contributions | |
� | -0.486 |
� | -0.447 |
�� | -0.436 |
verning | -0.435 |
� | -0.433 |
Token | download |
Token ID | 4321 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
� | +0.098 |
� | +0.089 |
verning | +0.087 |
�� | +0.086 |
� | +0.086 |
Neg logit contributions | |
arine | -0.084 |
hess | -0.079 |
illin | -0.079 |
PF | -0.078 |
igan | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
arine | +0.968 |
PF | +0.920 |
hess | +0.909 |
igan | +0.905 |
illin | +0.905 |
Neg logit contributions | |
� | -1.028 |
� | -0.932 |
verning | -0.899 |
�� | -0.894 |
� | -0.885 |
Token | Sh |
Token ID | 911 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
arine | +1.601 |
PF | +1.507 |
illin | +1.488 |
hess | +1.487 |
igan | +1.483 |
Neg logit contributions | |
� | -1.788 |
� | -1.616 |
�� | -1.568 |
verning | -1.556 |
� | -1.548 |
Token | river |
Token ID | 38291 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
arine | +3.269 |
illin | +3.041 |
igan | +3.036 |
hess | +2.983 |
PF | +2.896 |
Neg logit contributions | |
� | -5.307 |
� | -4.899 |
�� | -4.838 |
Crim | -4.703 |
� | -4.699 |
Token | Award |
Token ID | 11289 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
arine | +4.265 |
igan | +4.030 |
PF | +3.983 |
illin | +3.939 |
hess | +3.928 |
Neg logit contributions | |
� | -4.322 |
� | -3.920 |
�� | -3.826 |
verning | -3.784 |
wat | -3.774 |
Token | nomination |
Token ID | 11872 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
arine | +4.613 |
igan | +4.347 |
PF | +4.264 |
payoff | +4.254 |
illin | +4.223 |
Neg logit contributions | |
� | -5.329 |
� | -4.919 |
�� | -4.778 |
verning | -4.749 |
wat | -4.727 |
Token | packet |
Token ID | 19638 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
payoff | +2.803 |
arine | +2.628 |
backfield | +2.412 |
PF | +2.356 |
enrol | +2.351 |
Neg logit contributions | |
� | -14.142 |
� | -13.550 |
�� | -13.388 |
�� | -13.049 |
� | -13.047 |
Token | and |
Token ID | 290 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
arine | +3.417 |
PF | +3.241 |
igan | +3.241 |
hess | +3.144 |
illin | +3.117 |
Neg logit contributions | |
� | -4.605 |
� | -4.173 |
�� | -4.110 |
verning | -4.088 |
� | -4.059 |
Token | submit |
Token ID | 9199 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
arine | +0.972 |
PF | +0.925 |
hess | +0.921 |
illin | +0.921 |
igan | +0.912 |
Neg logit contributions | |
� | -0.742 |
� | -0.655 |
�� | -0.638 |
verning | -0.633 |
� | -0.629 |
Token | all |
Token ID | 477 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
arine | +1.052 |
PF | +0.974 |
illin | +0.970 |
igan | +0.959 |
hess | +0.951 |
Neg logit contributions | |
� | -1.679 |
� | -1.552 |
�� | -1.518 |
verning | -1.515 |
wat | -1.498 |
Token | materials |
Token ID | 5696 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
� | +1.931 |
� | +1.710 |
verning | +1.654 |
� | +1.639 |
�� | +1.638 |
Neg logit contributions | |
arine | -2.210 |
hess | -2.132 |
illin | -2.116 |
PF | -2.096 |
igan | -2.062 |
Token |
|
Token ID | 198 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
arine | +2.050 |
PF | +1.946 |
hess | +1.943 |
illin | +1.924 |
igan | +1.920 |
Neg logit contributions | |
� | -2.736 |
�� | -2.507 |
� | -2.501 |
verning | -2.429 |
� | -2.414 |
Token | And |
Token ID | 1870 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
arine | +2.326 |
PF | +2.227 |
hess | +2.209 |
illin | +2.187 |
igan | +2.164 |
Neg logit contributions | |
� | -2.685 |
� | -2.437 |
verning | -2.395 |
�� | -2.377 |
Crim | -2.343 |
Token | there |
Token ID | 612 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
arine | +2.923 |
hess | +2.728 |
illin | +2.724 |
PF | +2.714 |
igan | +2.692 |
Neg logit contributions | |
� | -3.660 |
� | -3.338 |
verning | -3.301 |
�� | -3.289 |
� | -3.216 |
Token | you |
Token ID | 345 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
arine | +4.464 |
hess | +4.107 |
illin | +4.092 |
PF | +4.089 |
igan | +4.081 |
Neg logit contributions | |
� | -6.400 |
verning | -5.962 |
� | -5.931 |
�� | -5.883 |
� | -5.688 |
Token | have |
Token ID | 423 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
arine | +5.454 |
PF | +5.207 |
igan | +5.177 |
payoff | +5.094 |
hess | +5.046 |
Neg logit contributions | |
� | -7.108 |
�� | -6.601 |
� | -6.490 |
verning | -6.287 |
�� | -6.232 |
Token | it |
Token ID | 340 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
arine | +5.362 |
igan | +5.133 |
PF | +5.100 |
hess | +4.986 |
KR | +4.870 |
Neg logit contributions | |
� | -8.191 |
� | -7.714 |
�� | -7.674 |
verning | -7.653 |
� | -7.367 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
arine | +6.285 |
PF | +6.091 |
igan | +6.022 |
hess | +5.888 |
BG | +5.800 |
Neg logit contributions | |
� | -9.617 |
� | -8.932 |
verning | -8.818 |
�� | -8.804 |
� | -8.609 |
Token | straight |
Token ID | 3892 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
arine | +5.451 |
PF | +5.237 |
igan | +5.128 |
payoff | +5.120 |
illin | +5.103 |
Neg logit contributions | |
� | -6.972 |
� | -6.440 |
�� | -6.361 |
verning | -6.313 |
� | -6.214 |
Token | from |
Token ID | 422 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
arine | +4.525 |
PF | +4.352 |
illin | +4.249 |
hess | +4.245 |
igan | +4.235 |
Neg logit contributions | |
� | -6.311 |
� | -5.762 |
�� | -5.745 |
verning | -5.656 |
Crim | -5.572 |
Token | the |
Token ID | 262 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
arine | +0.686 |
hess | +0.647 |
PF | +0.647 |
illin | +0.645 |
igan | +0.636 |
Neg logit contributions | |
� | -0.753 |
� | -0.681 |
verning | -0.663 |
�� | -0.659 |
� | -0.653 |
Token | horse |
Token ID | 8223 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
arine | +0.293 |
hess | +0.276 |
illin | +0.276 |
PF | +0.274 |
igan | +0.271 |
Neg logit contributions | |
� | -0.347 |
� | -0.315 |
verning | -0.306 |
�� | -0.305 |
Crim | -0.303 |
Token | gray |
Token ID | 12768 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
arine | +2.947 |
hess | +2.814 |
illin | +2.787 |
igan | +2.775 |
PF | +2.757 |
Neg logit contributions | |
� | -3.606 |
� | -3.231 |
�� | -3.182 |
verning | -3.146 |
� | -3.115 |
Token | , |
Token ID | 837 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
arine | +0.576 |
hess | +0.528 |
illin | +0.523 |
PF | +0.522 |
igan | +0.513 |
Neg logit contributions | |
� | -1.307 |
� | -1.212 |
�� | -1.189 |
verning | -1.185 |
� | -1.176 |
Token | c |
Token ID | 269 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
� | +1.729 |
� | +1.558 |
Crim | +1.530 |
verning | +1.527 |
� | +1.504 |
Neg logit contributions | |
arine | -1.375 |
illin | -1.292 |
hess | -1.286 |
PF | -1.285 |
igan | -1.256 |
Token | v |
Token ID | 85 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
� | +1.855 |
� | +1.659 |
wat | +1.648 |
verning | +1.630 |
Crim | +1.597 |
Neg logit contributions | |
arine | -1.954 |
illin | -1.857 |
PF | -1.844 |
hess | -1.839 |
�� | -1.833 |
Token | 2 |
Token ID | 17 |
Feature activation | -9.13e-04 |
Pos logit contributions | |
� | +1.638 |
� | +1.446 |
Crim | +1.400 |
verning | +1.393 |
wat | +1.393 |
Neg logit contributions | |
arine | -2.046 |
illin | -1.947 |
hess | -1.938 |
PF | -1.917 |
�� | -1.916 |
Token | . |
Token ID | 764 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
� | +0.007 |
� | +0.006 |
verning | +0.006 |
�� | +0.006 |
Crim | +0.006 |
Neg logit contributions | |
arine | -0.005 |
hess | -0.004 |
illin | -0.004 |
PF | -0.004 |
igan | -0.004 |
Token | MOR |
Token ID | 35208 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
arine | +5.120 |
PF | +5.113 |
igan | +4.981 |
illin | +4.910 |
payoff | +4.865 |
Neg logit contributions | |
� | -10.700 |
� | -9.982 |
� | -9.853 |
verning | -9.811 |
wat | -9.732 |
Token | PH |
Token ID | 11909 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
arine | +1.675 |
PF | +1.643 |
hess | +1.549 |
igan | +1.501 |
illin | +1.491 |
Neg logit contributions | |
� | -4.302 |
� | -4.051 |
verning | -3.966 |
�� | -3.960 |
� | -3.920 |
Token | _ |
Token ID | 62 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
arine | +4.591 |
PF | +4.503 |
igan | +4.333 |
hess | +4.332 |
BG | +4.290 |
Neg logit contributions | |
� | -5.436 |
�� | -5.072 |
� | -4.974 |
� | -4.834 |
�� | -4.825 |
Token | BL |
Token ID | 9148 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
BG | +3.676 |
PF | +3.645 |
KR | +3.462 |
arine | +3.461 |
RFC | +3.441 |
Neg logit contributions | |
� | -8.540 |
�� | -7.999 |
verning | -7.954 |
� | -7.911 |
� | -7.750 |
Token | ACK |
Token ID | 8120 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
BG | +5.100 |
PF | +4.985 |
KR | +4.969 |
arine | +4.805 |
RFC | +4.595 |
Neg logit contributions | |
� | -12.587 |
verning | -11.903 |
�� | -11.778 |
� | -11.519 |
Crim | -11.347 |
Token | ing |
Token ID | 278 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
� | +1.665 |
� | +1.475 |
verning | +1.438 |
Crim | +1.406 |
� | +1.405 |
Neg logit contributions | |
arine | -2.059 |
hess | -1.981 |
illin | -1.970 |
PF | -1.960 |
�� | -1.923 |
Token | . |
Token ID | 13 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
� | +0.506 |
� | +0.454 |
verning | +0.441 |
�� | +0.438 |
Crim | +0.436 |
Neg logit contributions | |
arine | -0.499 |
hess | -0.472 |
illin | -0.472 |
PF | -0.469 |
igan | -0.463 |
Token | Graphics |
Token ID | 18172 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
arine | +3.120 |
PF | +2.920 |
BG | +2.854 |
hess | +2.795 |
igan | +2.757 |
Neg logit contributions | |
� | -6.631 |
� | -6.255 |
verning | -6.201 |
�� | -6.082 |
Crim | -6.062 |
Token | ] |
Token ID | 60 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
� | +1.186 |
� | +1.083 |
verning | +1.057 |
�� | +1.054 |
Crim | +1.045 |
Neg logit contributions | |
arine | -0.855 |
hess | -0.800 |
PF | -0.797 |
illin | -0.796 |
igan | -0.783 |
Token | :: |
Token ID | 3712 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
� | +0.478 |
� | +0.421 |
verning | +0.409 |
Crim | +0.402 |
� | +0.401 |
Neg logit contributions | |
arine | -0.603 |
hess | -0.574 |
illin | -0.574 |
PF | -0.568 |
igan | -0.564 |
Token | From |
Token ID | 4863 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
arine | +2.679 |
PF | +2.584 |
BG | +2.504 |
hess | +2.467 |
igan | +2.457 |
Neg logit contributions | |
� | -3.551 |
� | -3.280 |
verning | -3.272 |
�� | -3.239 |
Crim | -3.222 |
Token | Image |
Token ID | 5159 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
BG | +3.892 |
PF | +3.846 |
arine | +3.826 |
RFC | +3.552 |
GC | +3.414 |
Neg logit contributions | |
� | -12.035 |
verning | -11.563 |
�� | -11.431 |
� | -11.391 |
Crim | -11.290 |
Token | ($ |
Token ID | 16763 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
� | +0.163 |
� | +0.144 |
�� | +0.139 |
verning | +0.139 |
Crim | +0.137 |
Neg logit contributions | |
arine | -0.214 |
PF | -0.203 |
hess | -0.203 |
illin | -0.202 |
igan | -0.200 |
Token | b |
Token ID | 65 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
� | +0.273 |
� | +0.242 |
verning | +0.234 |
�� | +0.230 |
� | +0.230 |
Neg logit contributions | |
arine | -0.341 |
hess | -0.325 |
illin | -0.325 |
PF | -0.323 |
igan | -0.319 |
Token | mp |
Token ID | 3149 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
� | +0.871 |
� | +0.786 |
verning | +0.768 |
wat | +0.762 |
Crim | +0.759 |
Neg logit contributions | |
arine | -0.762 |
hess | -0.717 |
illin | -0.715 |
PF | -0.713 |
igan | -0.699 |
Token | ) |
Token ID | 8 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
� | +0.854 |
� | +0.750 |
verning | +0.725 |
�� | +0.721 |
Crim | +0.712 |
Neg logit contributions | |
arine | -1.204 |
hess | -1.147 |
illin | -1.142 |
PF | -1.142 |
igan | -1.128 |
Token | image |
Token ID | 2939 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
arine | +1.732 |
igan | +1.524 |
hess | +1.518 |
illin | +1.504 |
PF | +1.453 |
Neg logit contributions | |
� | -6.267 |
� | -5.835 |
�� | -5.792 |
verning | -5.773 |
Crim | -5.687 |
Token | , |
Token ID | 837 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
arine | +1.245 |
PF | +1.144 |
hess | +1.138 |
illin | +1.112 |
igan | +1.111 |
Neg logit contributions | |
� | -3.106 |
� | -2.894 |
�� | -2.853 |
verning | -2.821 |
� | -2.799 |
Token | c |
Token ID | 269 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
arine | +0.844 |
hess | +0.791 |
illin | +0.787 |
PF | +0.784 |
igan | +0.772 |
Neg logit contributions | |
� | -1.258 |
� | -1.153 |
verning | -1.124 |
�� | -1.123 |
� | -1.111 |
Token | v |
Token ID | 85 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
� | +0.689 |
� | +0.619 |
verning | +0.605 |
wat | +0.600 |
Crim | +0.595 |
Neg logit contributions | |
arine | -0.671 |
illin | -0.635 |
hess | -0.632 |
PF | -0.631 |
igan | -0.619 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
� | +1.577 |
� | +1.391 |
Crim | +1.348 |
verning | +1.342 |
wat | +1.339 |
Neg logit contributions | |
arine | -1.969 |
illin | -1.874 |
hess | -1.861 |
PF | -1.842 |
�� | -1.840 |
Token | . |
Token ID | 764 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
� | +0.298 |
� | +0.271 |
verning | +0.265 |
Crim | +0.263 |
�� | +0.262 |
Neg logit contributions | |
arine | -0.215 |
illin | -0.201 |
hess | -0.201 |
PF | -0.199 |
igan | -0.196 |
Token | COL |
Token ID | 20444 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
arine | +5.687 |
BG | +5.625 |
igan | +5.588 |
PF | +5.484 |
PG | +5.403 |
Neg logit contributions | |
� | -9.927 |
verning | -9.091 |
� | -8.992 |
wat | -8.878 |
� | -8.846 |
Token | OR |
Token ID | 1581 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
arine | +3.926 |
PF | +3.915 |
BG | +3.722 |
KR | +3.645 |
igan | +3.580 |
Neg logit contributions | |
� | -8.574 |
verning | -8.263 |
� | -8.000 |
�� | -7.983 |
wat | -7.900 |
Token | _ |
Token ID | 62 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
arine | +4.990 |
PF | +4.940 |
hess | +4.793 |
BG | +4.786 |
igan | +4.750 |
Neg logit contributions | |
� | -6.151 |
�� | -5.650 |
� | -5.558 |
verning | -5.469 |
� | -5.382 |
Token | B |
Token ID | 33 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
BG | +4.981 |
PF | +4.772 |
RFC | +4.440 |
KR | +4.422 |
arine | +4.284 |
Neg logit contributions | |
� | -10.533 |
verning | -9.840 |
� | -9.741 |
�� | -9.717 |
� | -9.452 |
Token | GR |
Token ID | 10761 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
arine | +3.195 |
BG | +3.153 |
PF | +3.093 |
KR | +3.052 |
igan | +3.026 |
Neg logit contributions | |
� | -9.543 |
verning | -8.968 |
�� | -8.931 |
� | -8.872 |
Crim | -8.767 |
Token | amount |
Token ID | 2033 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
arine | +0.779 |
hess | +0.738 |
illin | +0.735 |
PF | +0.733 |
igan | +0.723 |
Neg logit contributions | |
� | -0.797 |
� | -0.718 |
verning | -0.695 |
�� | -0.694 |
� | -0.687 |
Token | " |
Token ID | 1 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
arine | +1.363 |
hess | +1.283 |
PF | +1.272 |
illin | +1.267 |
igan | +1.257 |
Neg logit contributions | |
� | -1.953 |
� | -1.786 |
�� | -1.745 |
verning | -1.728 |
� | -1.725 |
Token | , |
Token ID | 837 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
arine | +2.130 |
hess | +1.989 |
PF | +1.972 |
illin | +1.944 |
igan | +1.943 |
Neg logit contributions | |
� | -5.654 |
� | -5.261 |
�� | -5.152 |
� | -5.115 |
� | -5.113 |
Token | Range |
Token ID | 13667 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
arine | +3.875 |
PF | +3.596 |
hess | +3.585 |
igan | +3.585 |
illin | +3.498 |
Neg logit contributions | |
� | -6.157 |
� | -5.731 |
�� | -5.509 |
verning | -5.508 |
wat | -5.485 |
Token | ( |
Token ID | 357 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
arine | +1.351 |
PF | +1.273 |
hess | +1.271 |
illin | +1.260 |
igan | +1.245 |
Neg logit contributions | |
� | -2.044 |
� | -1.883 |
�� | -1.843 |
verning | -1.823 |
� | -1.809 |
Token | 0 |
Token ID | 657 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
arine | +2.781 |
hess | +2.645 |
PF | +2.576 |
illin | +2.551 |
igan | +2.534 |
Neg logit contributions | |
� | -6.028 |
� | -5.572 |
�� | -5.556 |
� | -5.444 |
verning | -5.421 |
Token | , |
Token ID | 837 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
arine | +3.615 |
igan | +3.613 |
PF | +3.552 |
hess | +3.389 |
illin | +3.218 |
Neg logit contributions | |
� | -12.315 |
�� | -12.027 |
� | -11.568 |
�� | -11.339 |
� | -11.313 |
Token | 0 |
Token ID | 657 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
arine | +0.997 |
hess | +0.928 |
illin | +0.922 |
PF | +0.919 |
igan | +0.904 |
Neg logit contributions | |
� | -1.741 |
� | -1.601 |
�� | -1.565 |
verning | -1.564 |
� | -1.549 |
Token | . |
Token ID | 13 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
arine | +3.746 |
PF | +3.584 |
igan | +3.582 |
hess | +3.565 |
illin | +3.493 |
Neg logit contributions | |
� | -6.708 |
�� | -6.466 |
� | -6.254 |
�� | -6.037 |
� | -6.036 |
Token | 5 |
Token ID | 20 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
arine | +3.602 |
PF | +3.486 |
igan | +3.439 |
hess | +3.369 |
illin | +3.352 |
Neg logit contributions | |
� | -5.618 |
�� | -5.228 |
� | -5.192 |
�� | -5.016 |
� | -5.000 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
arine | +1.550 |
hess | +1.464 |
illin | +1.464 |
PF | +1.462 |
igan | +1.431 |
Neg logit contributions | |
� | -1.903 |
� | -1.732 |
�� | -1.697 |
verning | -1.676 |
� | -1.665 |
Token | HA |
Token ID | 7801 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
� | +0.109 |
� | +0.098 |
verning | +0.096 |
�� | +0.095 |
Crim | +0.094 |
Neg logit contributions | |
arine | -0.099 |
hess | -0.093 |
illin | -0.093 |
PF | -0.093 |
igan | -0.092 |
Token | V |
Token ID | 53 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
arine | +0.980 |
PF | +0.927 |
hess | +0.925 |
illin | +0.919 |
igan | +0.910 |
Neg logit contributions | |
� | -1.222 |
� | -1.110 |
verning | -1.087 |
�� | -1.079 |
Crim | -1.068 |
Token | ANA |
Token ID | 31574 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
igan | +3.361 |
arine | +3.323 |
PF | +3.284 |
illin | +3.133 |
KR | +3.100 |
Neg logit contributions | |
� | -8.090 |
� | -7.524 |
�� | -7.509 |
verning | -7.407 |
Crim | -7.275 |
Token | ( |
Token ID | 357 |
Feature activation | -9.74e-02 |
Pos logit contributions | |
arine | +1.767 |
PF | +1.681 |
hess | +1.678 |
illin | +1.671 |
igan | +1.654 |
Neg logit contributions | |
� | -2.286 |
� | -2.074 |
�� | -2.024 |
verning | -2.023 |
Crim | -1.995 |
Token | Reuters |
Token ID | 12637 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
� | +0.719 |
� | +0.654 |
verning | +0.639 |
� | +0.634 |
wat | +0.631 |
Neg logit contributions | |
arine | -0.510 |
hess | -0.475 |
illin | -0.473 |
igan | -0.463 |
PF | -0.461 |
Token | ) |
Token ID | 8 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
arine | +0.085 |
illin | +0.081 |
hess | +0.081 |
PF | +0.081 |
igan | +0.080 |
Neg logit contributions | |
� | -0.060 |
� | -0.053 |
�� | -0.051 |
verning | -0.051 |
� | -0.050 |
Token | - |
Token ID | 532 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
PF | +2.820 |
igan | +2.776 |
arine | +2.623 |
illin | +2.586 |
hess | +2.557 |
Neg logit contributions | |
� | -12.771 |
�� | -12.509 |
� | -12.195 |
�� | -11.959 |
� | -11.790 |
Token | Latin |
Token ID | 9133 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
arine | +5.796 |
igan | +5.752 |
PF | +5.623 |
illin | +5.575 |
hess | +5.473 |
Neg logit contributions | |
� | -5.817 |
�� | -5.331 |
� | -5.300 |
� | -5.065 |
�� | -4.996 |
Token | American |
Token ID | 1605 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
� | +0.204 |
� | +0.182 |
verning | +0.177 |
�� | +0.176 |
Crim | +0.175 |
Neg logit contributions | |
arine | -0.219 |
hess | -0.208 |
illin | -0.207 |
PF | -0.206 |
igan | -0.203 |
Token | and |
Token ID | 290 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
� | +0.171 |
� | +0.153 |
verning | +0.149 |
Crim | +0.148 |
�� | +0.147 |
Neg logit contributions | |
arine | -0.174 |
hess | -0.165 |
illin | -0.165 |
PF | -0.164 |
igan | -0.162 |
Token | Caribbean |
Token ID | 18020 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
� | +2.310 |
� | +2.008 |
Crim | +1.960 |
verning | +1.943 |
� | +1.891 |
Neg logit contributions | |
arine | -3.765 |
hess | -3.650 |
illin | -3.648 |
PF | -3.626 |
igan | -3.551 |
Token | BR |
Token ID | 11473 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
� | +0.202 |
� | +0.182 |
verning | +0.177 |
�� | +0.176 |
Crim | +0.175 |
Neg logit contributions | |
arine | -0.183 |
hess | -0.172 |
illin | -0.172 |
PF | -0.171 |
igan | -0.169 |
Token | USS |
Token ID | 32835 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
� | +0.089 |
� | +0.080 |
verning | +0.078 |
�� | +0.077 |
Crim | +0.077 |
Neg logit contributions | |
arine | -0.084 |
hess | -0.079 |
illin | -0.079 |
PF | -0.079 |
igan | -0.078 |
Token | ELS |
Token ID | 37142 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
arine | +1.092 |
illin | +1.026 |
hess | +1.021 |
PF | +1.020 |
igan | +1.008 |
Neg logit contributions | |
� | -2.035 |
� | -1.870 |
�� | -1.842 |
verning | -1.832 |
� | -1.819 |
Token | ( |
Token ID | 357 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
arine | +1.383 |
hess | +1.303 |
illin | +1.300 |
PF | +1.297 |
igan | +1.278 |
Neg logit contributions | |
� | -1.901 |
� | -1.730 |
verning | -1.691 |
�� | -1.691 |
� | -1.669 |
Token | Reuters |
Token ID | 12637 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
� | +0.726 |
� | +0.659 |
verning | +0.644 |
� | +0.639 |
Crim | +0.638 |
Neg logit contributions | |
arine | -0.509 |
hess | -0.476 |
illin | -0.474 |
igan | -0.465 |
PF | -0.463 |
Token | ) |
Token ID | 8 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
� | +0.542 |
� | +0.473 |
verning | +0.456 |
�� | +0.450 |
Crim | +0.450 |
Neg logit contributions | |
arine | -0.799 |
hess | -0.764 |
illin | -0.762 |
PF | -0.758 |
igan | -0.750 |
Token | - |
Token ID | 532 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
PF | +2.809 |
igan | +2.744 |
arine | +2.622 |
illin | +2.580 |
hess | +2.551 |
Neg logit contributions | |
� | -12.745 |
�� | -12.484 |
� | -12.174 |
�� | -11.938 |
� | -11.767 |
Token | The |
Token ID | 383 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
arine | +4.770 |
igan | +4.668 |
illin | +4.576 |
PF | +4.551 |
hess | +4.511 |
Neg logit contributions | |
� | -6.316 |
� | -5.896 |
�� | -5.859 |
� | -5.619 |
� | -5.533 |
Token | world |
Token ID | 995 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
arine | +2.144 |
illin | +2.029 |
PF | +2.007 |
igan | +1.999 |
hess | +1.999 |
Neg logit contributions | |
� | -2.644 |
� | -2.409 |
verning | -2.336 |
�� | -2.331 |
� | -2.306 |
Token | � |
Token ID | 447 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
arine | +1.697 |
hess | +1.582 |
PF | +1.570 |
illin | +1.564 |
igan | +1.545 |
Neg logit contributions | |
� | -2.832 |
� | -2.601 |
�� | -2.546 |
verning | -2.535 |
� | -2.515 |
Token | � |
Token ID | 247 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
arine | +1.527 |
PF | +1.482 |
illin | +1.481 |
hess | +1.478 |
igan | +1.474 |
Neg logit contributions | |
� | -0.466 |
verning | -0.408 |
Crim | -0.403 |
wat | -0.392 |
�� | -0.372 |
Token | ( |
Token ID | 357 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
arine | +2.718 |
PF | +2.557 |
hess | +2.541 |
igan | +2.532 |
illin | +2.529 |
Neg logit contributions | |
� | -4.629 |
� | -4.298 |
�� | -4.235 |
verning | -4.145 |
� | -4.122 |
Token | 21 |
Token ID | 2481 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
arine | +4.408 |
hess | +4.380 |
PF | +4.360 |
illin | +4.098 |
igan | +4.041 |
Neg logit contributions | |
� | -7.361 |
� | -6.795 |
�� | -6.721 |
� | -6.605 |
verning | -6.598 |
Token | , |
Token ID | 11 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
arine | +3.533 |
PF | +3.417 |
igan | +3.351 |
hess | +3.338 |
illin | +3.259 |
Neg logit contributions | |
� | -5.008 |
�� | -4.659 |
� | -4.583 |
� | -4.450 |
� | -4.435 |
Token | 21 |
Token ID | 2310 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
arine | +3.063 |
hess | +2.886 |
PF | +2.841 |
igan | +2.798 |
illin | +2.749 |
Neg logit contributions | |
� | -5.778 |
� | -5.375 |
�� | -5.329 |
� | -5.236 |
verning | -5.186 |
Token | )) |
Token ID | 4008 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
arine | +0.896 |
illin | +0.841 |
PF | +0.840 |
hess | +0.840 |
igan | +0.824 |
Neg logit contributions | |
� | -1.144 |
� | -1.039 |
�� | -1.016 |
verning | -1.011 |
� | -0.999 |
Token | # |
Token ID | 1303 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
arine | +4.251 |
PF | +3.946 |
igan | +3.908 |
illin | +3.878 |
hess | +3.868 |
Neg logit contributions | |
� | -7.516 |
� | -7.042 |
verning | -6.879 |
�� | -6.846 |
� | -6.726 |
Token | loop |
Token ID | 9052 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
arine | +4.939 |
payoff | +4.844 |
igan | +4.781 |
PF | +4.739 |
hess | +4.656 |
Neg logit contributions | |
� | -10.393 |
�� | -9.599 |
�� | -9.507 |
� | -9.426 |
verning | -9.397 |
Token | over |
Token ID | 625 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
arine | +3.023 |
hess | +2.877 |
PF | +2.872 |
igan | +2.857 |
illin | +2.816 |
Neg logit contributions | |
� | -2.885 |
�� | -2.595 |
� | -2.586 |
� | -2.511 |
� | -2.502 |
Token | the |
Token ID | 262 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
arine | +2.761 |
PF | +2.628 |
igan | +2.594 |
hess | +2.593 |
illin | +2.558 |
Neg logit contributions | |
� | -3.212 |
�� | -2.924 |
� | -2.922 |
verning | -2.801 |
�� | -2.797 |
Token | input |
Token ID | 5128 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
arine | +4.745 |
PF | +4.460 |
igan | +4.455 |
illin | +4.383 |
payoff | +4.378 |
Neg logit contributions | |
� | -5.887 |
�� | -5.503 |
� | -5.301 |
�� | -5.202 |
� | -5.186 |
Token | image |
Token ID | 2939 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
arine | +2.270 |
igan | +1.969 |
illin | +1.852 |
PF | +1.831 |
payoff | +1.824 |
Neg logit contributions | |
� | -9.238 |
�� | -8.726 |
� | -8.635 |
verning | -8.513 |
� | -8.502 |
Token | ONG |
Token ID | 18494 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
� | +1.262 |
� | +1.143 |
verning | +1.112 |
�� | +1.100 |
� | +1.098 |
Neg logit contributions | |
arine | -1.060 |
hess | -0.999 |
illin | -0.994 |
PF | -0.989 |
igan | -0.973 |
Token | K |
Token ID | 509 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
arine | +2.958 |
PF | +2.805 |
illin | +2.674 |
igan | +2.647 |
KR | +2.646 |
Neg logit contributions | |
� | -6.713 |
�� | -6.269 |
� | -6.233 |
verning | -6.211 |
� | -6.082 |
Token | ONG |
Token ID | 18494 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
arine | +1.061 |
hess | +0.997 |
PF | +0.996 |
illin | +0.995 |
igan | +0.978 |
Neg logit contributions | |
� | -1.347 |
� | -1.224 |
verning | -1.195 |
�� | -1.193 |
Crim | -1.183 |
Token | ( |
Token ID | 357 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
arine | +1.060 |
illin | +0.994 |
hess | +0.993 |
PF | +0.993 |
igan | +0.975 |
Neg logit contributions | |
� | -1.321 |
� | -1.202 |
verning | -1.170 |
�� | -1.168 |
Crim | -1.154 |
Token | Reuters |
Token ID | 12637 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
arine | +2.533 |
PF | +2.389 |
hess | +2.334 |
illin | +2.315 |
igan | +2.297 |
Neg logit contributions | |
� | -4.293 |
� | -3.994 |
�� | -3.919 |
verning | -3.868 |
Crim | -3.833 |
Token | ) |
Token ID | 8 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
arine | +0.457 |
PF | +0.438 |
illin | +0.436 |
hess | +0.435 |
igan | +0.431 |
Neg logit contributions | |
� | -0.332 |
� | -0.293 |
�� | -0.283 |
verning | -0.282 |
� | -0.277 |
Token | - |
Token ID | 532 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
PF | +2.714 |
igan | +2.644 |
arine | +2.484 |
hess | +2.405 |
illin | +2.395 |
Neg logit contributions | |
� | -12.749 |
�� | -12.553 |
� | -12.313 |
�� | -12.114 |
� | -11.894 |
Token | One |
Token ID | 1881 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
arine | +5.131 |
PF | +4.930 |
illin | +4.901 |
igan | +4.837 |
hess | +4.707 |
Neg logit contributions | |
� | -5.616 |
�� | -5.146 |
� | -5.125 |
� | -4.961 |
�� | -4.931 |
Token | needs |
Token ID | 2476 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
arine | +2.299 |
illin | +2.171 |
PF | +2.152 |
hess | +2.147 |
igan | +2.120 |
Neg logit contributions | |
� | -2.683 |
� | -2.424 |
�� | -2.366 |
verning | -2.361 |
Crim | -2.335 |
Token | to |
Token ID | 284 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
arine | +0.130 |
illin | +0.123 |
hess | +0.123 |
PF | +0.122 |
igan | +0.121 |
Neg logit contributions | |
� | -0.137 |
� | -0.124 |
verning | -0.120 |
�� | -0.120 |
Crim | -0.119 |
Token | look |
Token ID | 804 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
arine | +0.434 |
hess | +0.409 |
illin | +0.409 |
PF | +0.406 |
igan | +0.401 |
Neg logit contributions | |
� | -0.515 |
� | -0.466 |
verning | -0.453 |
�� | -0.452 |
� | -0.449 |
Token | replied |
Token ID | 8712 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
� | +2.216 |
� | +2.002 |
verning | +1.920 |
Crim | +1.917 |
� | +1.911 |
Neg logit contributions | |
arine | -2.329 |
illin | -2.205 |
hess | -2.197 |
PF | -2.196 |
igan | -2.131 |
Token | : |
Token ID | 25 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
arine | +0.311 |
hess | +0.293 |
illin | +0.292 |
PF | +0.291 |
igan | +0.289 |
Neg logit contributions | |
� | -0.363 |
� | -0.328 |
verning | -0.321 |
�� | -0.319 |
� | -0.316 |
Token | what |
Token ID | 644 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
� | +2.147 |
� | +1.934 |
verning | +1.862 |
�� | +1.860 |
Crim | +1.854 |
Neg logit contributions | |
arine | -2.126 |
hess | -2.017 |
illin | -2.007 |
PF | -1.996 |
igan | -1.969 |
Token | do |
Token ID | 466 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
� | +0.118 |
� | +0.106 |
�� | +0.103 |
verning | +0.103 |
Crim | +0.103 |
Neg logit contributions | |
arine | -0.106 |
hess | -0.100 |
illin | -0.100 |
PF | -0.099 |
igan | -0.098 |
Token | you |
Token ID | 345 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
arine | +0.484 |
hess | +0.456 |
illin | +0.455 |
PF | +0.453 |
igan | +0.447 |
Neg logit contributions | |
� | -0.571 |
� | -0.518 |
verning | -0.504 |
�� | -0.501 |
Crim | -0.498 |
Token | expect |
Token ID | 1607 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
arine | +2.487 |
illin | +2.335 |
hess | +2.319 |
PF | +2.309 |
igan | +2.307 |
Neg logit contributions | |
� | -2.979 |
� | -2.697 |
verning | -2.628 |
�� | -2.613 |
� | -2.590 |
Token | when |
Token ID | 618 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
arine | +6.341 |
igan | +5.765 |
hess | +5.694 |
illin | +5.662 |
PF | +5.655 |
Neg logit contributions | |
� | -9.377 |
verning | -8.570 |
� | -8.556 |
wat | -8.343 |
�� | -8.329 |
Token | you |
Token ID | 345 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
arine | +2.405 |
illin | +2.247 |
hess | +2.240 |
PF | +2.239 |
igan | +2.217 |
Neg logit contributions | |
� | -3.030 |
� | -2.763 |
verning | -2.702 |
�� | -2.685 |
wat | -2.653 |
Token | put |
Token ID | 1234 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
arine | +1.271 |
hess | +1.196 |
illin | +1.195 |
PF | +1.187 |
igan | +1.177 |
Neg logit contributions | |
� | -1.490 |
� | -1.349 |
verning | -1.312 |
�� | -1.311 |
� | -1.296 |
Token | men |
Token ID | 1450 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
arine | +0.762 |
hess | +0.718 |
illin | +0.717 |
PF | +0.714 |
igan | +0.704 |
Neg logit contributions | |
� | -0.899 |
� | -0.814 |
verning | -0.792 |
�� | -0.788 |
Crim | -0.783 |
Token | and |
Token ID | 290 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
� | +2.138 |
� | +1.946 |
verning | +1.899 |
Crim | +1.873 |
� | +1.866 |
Neg logit contributions | |
arine | -1.794 |
hess | -1.707 |
illin | -1.702 |
PF | -1.689 |
igan | -1.651 |
Token | ernel |
Token ID | 7948 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
arine | +1.922 |
illin | +1.780 |
hess | +1.753 |
PF | +1.749 |
igan | +1.739 |
Neg logit contributions | |
� | -3.514 |
� | -3.266 |
�� | -3.189 |
Crim | -3.159 |
� | -3.140 |
Token | = |
Token ID | 796 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
arine | +3.297 |
PF | +3.162 |
igan | +3.132 |
hess | +3.121 |
illin | +3.108 |
Neg logit contributions | |
� | -3.451 |
� | -3.146 |
�� | -3.104 |
verning | -3.014 |
� | -3.001 |
Token | c |
Token ID | 269 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
arine | +1.812 |
hess | +1.681 |
PF | +1.671 |
illin | +1.670 |
igan | +1.669 |
Neg logit contributions | |
� | -3.301 |
� | -3.064 |
�� | -3.041 |
verning | -2.977 |
� | -2.959 |
Token | v |
Token ID | 85 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
arine | +1.416 |
hess | +1.340 |
illin | +1.328 |
PF | +1.326 |
igan | +1.318 |
Neg logit contributions | |
� | -1.702 |
� | -1.544 |
�� | -1.515 |
verning | -1.492 |
� | -1.485 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
� | +0.227 |
� | +0.202 |
verning | +0.196 |
�� | +0.194 |
Crim | +0.194 |
Neg logit contributions | |
arine | -0.248 |
hess | -0.236 |
illin | -0.235 |
PF | -0.234 |
igan | -0.231 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
arine | +1.558 |
hess | +1.480 |
PF | +1.472 |
igan | +1.463 |
illin | +1.458 |
Neg logit contributions | |
� | -1.837 |
� | -1.673 |
�� | -1.667 |
verning | -1.611 |
� | -1.605 |
Token | get |
Token ID | 1136 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
arine | +4.766 |
PF | +4.759 |
igan | +4.703 |
RFC | +4.514 |
flame | +4.495 |
Neg logit contributions | |
� | -10.761 |
�� | -10.052 |
� | -9.956 |
verning | -9.829 |
Crim | -9.782 |
Token | Struct |
Token ID | 44909 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
arine | +2.851 |
PF | +2.804 |
hess | +2.743 |
RFC | +2.705 |
illin | +2.692 |
Neg logit contributions | |
� | -2.245 |
� | -2.029 |
�� | -1.980 |
� | -1.932 |
� | -1.929 |
Token | uring |
Token ID | 870 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
arine | +2.375 |
illin | +2.166 |
PF | +2.162 |
hess | +2.109 |
igan | +2.095 |
Neg logit contributions | |
� | -5.215 |
� | -4.910 |
�� | -4.819 |
� | -4.755 |
� | -4.745 |
Token | Element |
Token ID | 20180 |
Feature activation | +8.65e-02 |
Pos logit contributions | |
arine | +2.466 |
PF | +2.344 |
hess | +2.334 |
illin | +2.305 |
igan | +2.284 |
Neg logit contributions | |
� | -3.486 |
� | -3.170 |
�� | -3.131 |
verning | -3.102 |
Crim | -3.061 |
Token | ( |
Token ID | 7 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
arine | +0.612 |
PF | +0.584 |
hess | +0.583 |
illin | +0.582 |
igan | +0.576 |
Neg logit contributions | |
� | -0.474 |
� | -0.421 |
�� | -0.410 |
verning | -0.404 |
� | -0.399 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
arine | +0.976 |
illin | +0.920 |
hess | +0.920 |
PF | +0.915 |
igan | +0.905 |
Neg logit contributions | |
� | -1.156 |
� | -1.049 |
�� | -1.018 |
verning | -1.018 |
� | -1.007 |
Token | A |
Token ID | 317 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
arine | +0.219 |
hess | +0.207 |
illin | +0.207 |
PF | +0.206 |
igan | +0.204 |
Neg logit contributions | |
� | -0.206 |
� | -0.185 |
verning | -0.179 |
�� | -0.178 |
Crim | -0.177 |
Token | 25 |
Token ID | 1679 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
arine | +0.854 |
illin | +0.804 |
hess | +0.803 |
PF | +0.800 |
igan | +0.787 |
Neg logit contributions | |
� | -0.988 |
� | -0.896 |
verning | -0.870 |
�� | -0.868 |
Crim | -0.860 |
Token | % |
Token ID | 4 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
arine | +2.871 |
PF | +2.761 |
illin | +2.750 |
hess | +2.681 |
igan | +2.674 |
Neg logit contributions | |
� | -4.955 |
� | -4.595 |
�� | -4.469 |
verning | -4.461 |
Crim | -4.449 |
Token | to |
Token ID | 284 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
arine | +0.932 |
illin | +0.876 |
hess | +0.874 |
PF | +0.871 |
igan | +0.855 |
Neg logit contributions | |
� | -1.236 |
� | -1.129 |
verning | -1.096 |
�� | -1.093 |
� | -1.084 |
Token | 50 |
Token ID | 2026 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
arine | +3.986 |
PF | +3.706 |
hess | +3.657 |
illin | +3.652 |
igan | +3.621 |
Neg logit contributions | |
� | -6.212 |
�� | -5.719 |
� | -5.698 |
verning | -5.573 |
� | -5.489 |
Token | % |
Token ID | 4 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
PF | +4.841 |
arine | +4.786 |
igan | +4.513 |
illin | +4.437 |
hess | +4.311 |
Neg logit contributions | |
� | -10.373 |
� | -9.672 |
�� | -9.555 |
Crim | -9.539 |
verning | -9.527 |
Token | loss |
Token ID | 2994 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
arine | +3.142 |
illin | +2.976 |
PF | +2.967 |
hess | +2.943 |
payoff | +2.908 |
Neg logit contributions | |
� | -4.485 |
� | -4.136 |
�� | -4.010 |
verning | -3.988 |
� | -3.957 |
Token | of |
Token ID | 286 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
arine | +0.995 |
illin | +0.940 |
hess | +0.934 |
PF | +0.933 |
igan | +0.923 |
Neg logit contributions | |
� | -1.205 |
� | -1.095 |
verning | -1.067 |
�� | -1.067 |
� | -1.056 |
Token | efficiency |
Token ID | 9332 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
arine | +0.193 |
hess | +0.176 |
illin | +0.175 |
PF | +0.174 |
igan | +0.170 |
Neg logit contributions | |
� | -0.471 |
� | -0.437 |
verning | -0.429 |
�� | -0.427 |
Crim | -0.425 |
Token | is |
Token ID | 318 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
arine | +1.829 |
illin | +1.729 |
hess | +1.721 |
PF | +1.718 |
igan | +1.702 |
Neg logit contributions | |
� | -2.089 |
� | -1.888 |
�� | -1.854 |
verning | -1.837 |
� | -1.823 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
� | +1.650 |
� | +1.500 |
verning | +1.450 |
� | +1.437 |
Crim | +1.436 |
Neg logit contributions | |
arine | -1.505 |
PF | -1.418 |
hess | -1.415 |
illin | -1.409 |
igan | -1.384 |
Token | When |
Token ID | 1649 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
� | +1.153 |
� | +1.037 |
verning | +1.003 |
Crim | +0.998 |
�� | +0.992 |
Neg logit contributions | |
arine | -1.166 |
hess | -1.103 |
illin | -1.100 |
PF | -1.094 |
igan | -1.079 |
Token | Re |
Token ID | 797 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
arine | +0.899 |
hess | +0.847 |
PF | +0.846 |
illin | +0.845 |
igan | +0.836 |
Neg logit contributions | |
� | -1.081 |
� | -0.978 |
verning | -0.963 |
�� | -0.962 |
� | -0.941 |
Token | |
Token ID | 3907 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
� | +1.992 |
� | +1.774 |
verning | +1.703 |
Crim | +1.682 |
� | +1.680 |
Neg logit contributions | |
arine | -2.525 |
hess | -2.415 |
illin | -2.406 |
PF | -2.404 |
igan | -2.354 |
Token | pub |
Token ID | 12984 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
� | +7.235 |
� | +6.737 |
� | +6.332 |
� | +6.262 |
verning | +6.252 |
Neg logit contributions | |
arine | -8.090 |
�� | -7.835 |
hess | -7.780 |
PF | -7.662 |
illin | -7.533 |
Token | |
Token ID | 3907 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
� | +4.233 |
� | +3.737 |
Crim | +3.571 |
verning | +3.520 |
wat | +3.513 |
Neg logit contributions | |
arine | -6.129 |
PF | -5.941 |
hess | -5.855 |
illin | -5.852 |
igan | -5.756 |
Token | lic |
Token ID | 677 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
� | +6.967 |
wat | +6.380 |
� | +6.371 |
sa | +6.317 |
amed | +6.083 |
Neg logit contributions | |
�� | -13.145 |
PF | -12.178 |
arine | -12.166 |
KR | -11.920 |
payoff | -11.915 |
Token | |
Token ID | 3907 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
� | +1.961 |
� | +1.739 |
Crim | +1.668 |
verning | +1.666 |
� | +1.660 |
Neg logit contributions | |
arine | -2.390 |
illin | -2.270 |
hess | -2.267 |
PF | -2.264 |
igan | -2.238 |
Token | ans |
Token ID | 504 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
� | +6.670 |
� | +6.061 |
wat | +6.030 |
� | +5.839 |
� | +5.788 |
Neg logit contributions | |
�� | -6.491 |
PF | -6.254 |
arine | -6.138 |
payoff | -6.101 |
RFC | -6.033 |
Token | want |
Token ID | 765 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
� | +1.110 |
� | +1.005 |
verning | +0.975 |
Crim | +0.969 |
� | +0.963 |
Neg logit contributions | |
arine | -0.972 |
hess | -0.918 |
PF | -0.913 |
illin | -0.912 |
igan | -0.891 |
Token | to |
Token ID | 284 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
� | +0.569 |
� | +0.513 |
verning | +0.500 |
�� | +0.499 |
Crim | +0.493 |
Neg logit contributions | |
arine | -0.507 |
hess | -0.480 |
illin | -0.479 |
PF | -0.476 |
igan | -0.471 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
arine | +1.010 |
hess | +0.957 |
illin | +0.949 |
PF | +0.946 |
igan | +0.939 |
Neg logit contributions | |
� | -1.151 |
� | -1.035 |
�� | -1.021 |
verning | -1.014 |
Crim | -1.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
� | +0.959 |
� | +0.865 |
verning | +0.839 |
Crim | +0.832 |
�� | +0.832 |
Neg logit contributions | |
arine | -0.887 |
illin | -0.835 |
hess | -0.835 |
PF | -0.826 |
igan | -0.817 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
� | +0.874 |
� | +0.787 |
verning | +0.766 |
Crim | +0.761 |
wat | +0.756 |
Neg logit contributions | |
arine | -0.830 |
illin | -0.783 |
hess | -0.783 |
PF | -0.775 |
igan | -0.764 |
Token | CH |
Token ID | 3398 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
� | +1.047 |
� | +0.943 |
verning | +0.909 |
� | +0.903 |
�� | +0.901 |
Neg logit contributions | |
arine | -0.995 |
illin | -0.940 |
hess | -0.934 |
igan | -0.916 |
PF | -0.915 |
Token | IC |
Token ID | 2149 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
arine | +0.635 |
PF | +0.596 |
illin | +0.594 |
hess | +0.592 |
igan | +0.583 |
Neg logit contributions | |
� | -0.942 |
� | -0.861 |
verning | -0.843 |
�� | -0.842 |
Crim | -0.831 |
Token | AG |
Token ID | 4760 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
arine | +0.779 |
hess | +0.727 |
illin | +0.725 |
PF | +0.720 |
igan | +0.709 |
Neg logit contributions | |
� | -1.185 |
� | -1.085 |
verning | -1.058 |
�� | -1.054 |
Crim | -1.049 |
Token | O |
Token ID | 46 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
� | +9.094 |
� | +7.798 |
� | +7.628 |
� | +7.388 |
� | +7.388 |
Neg logit contributions | |
�� | -12.197 |
arine | -11.502 |
igan | -10.956 |
illin | -10.936 |
stiffness | -10.835 |
Token | -- |
Token ID | 1377 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
arine | +0.463 |
hess | +0.434 |
illin | +0.434 |
PF | +0.431 |
igan | +0.425 |
Neg logit contributions | |
� | -0.625 |
� | -0.570 |
verning | -0.555 |
�� | -0.553 |
Crim | -0.550 |
Token | It |
Token ID | 632 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
arine | +1.421 |
PF | +1.357 |
hess | +1.356 |
illin | +1.356 |
igan | +1.339 |
Neg logit contributions | |
� | -1.419 |
� | -1.273 |
�� | -1.250 |
verning | -1.238 |
� | -1.219 |
Token | 's |
Token ID | 338 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
arine | +0.731 |
hess | +0.689 |
illin | +0.687 |
PF | +0.681 |
igan | +0.676 |
Neg logit contributions | |
� | -0.913 |
� | -0.829 |
�� | -0.809 |
verning | -0.809 |
� | -0.799 |
Token | going |
Token ID | 1016 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
� | +1.072 |
� | +0.971 |
verning | +0.941 |
Crim | +0.936 |
�� | +0.931 |
Neg logit contributions | |
arine | -0.960 |
hess | -0.903 |
illin | -0.901 |
PF | -0.900 |
igan | -0.884 |
Token | party |
Token ID | 2151 |
Feature activation | -9.66e-03 |
Pos logit contributions | |
arine | +1.832 |
illin | +1.737 |
PF | +1.733 |
hess | +1.722 |
igan | +1.716 |
Neg logit contributions | |
� | -2.228 |
� | -2.006 |
�� | -1.979 |
verning | -1.976 |
� | -1.938 |
Token | � |
Token ID | 447 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
� | +0.065 |
� | +0.059 |
verning | +0.058 |
�� | +0.058 |
� | +0.057 |
Neg logit contributions | |
arine | -0.055 |
hess | -0.053 |
PF | -0.052 |
illin | -0.052 |
igan | -0.052 |
Token | � |
Token ID | 247 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
� | +0.265 |
verning | +0.200 |
� | +0.199 |
Crim | +0.195 |
�� | +0.191 |
Neg logit contributions | |
arine | -0.948 |
hess | -0.916 |
illin | -0.916 |
PF | -0.914 |
igan | -0.907 |
Token | s |
Token ID | 82 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
arine | +1.733 |
hess | +1.661 |
PF | +1.643 |
illin | +1.640 |
igan | +1.634 |
Neg logit contributions | |
� | -1.809 |
� | -1.605 |
�� | -1.601 |
verning | -1.576 |
Crim | -1.567 |
Token | con |
Token ID | 369 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
arine | +1.803 |
hess | +1.725 |
illin | +1.721 |
igan | +1.719 |
PF | +1.716 |
Neg logit contributions | |
� | -2.189 |
� | -1.960 |
�� | -1.939 |
verning | -1.927 |
� | -1.905 |
Token | |
Token ID | 3907 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
� | +2.589 |
� | +2.307 |
verning | +2.214 |
Crim | +2.197 |
�� | +2.180 |
Neg logit contributions | |
arine | -3.383 |
hess | -3.210 |
PF | -3.203 |
illin | -3.200 |
igan | -3.150 |
Token | ven |
Token ID | 574 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
� | +9.437 |
� | +8.948 |
wat | +8.529 |
sa | +8.419 |
Crim | +8.403 |
Neg logit contributions | |
arine | -8.332 |
�� | -8.022 |
PF | -7.702 |
KR | -7.596 |
hess | -7.559 |
Token | |
Token ID | 3907 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
� | +4.725 |
� | +4.237 |
� | +3.971 |
Crim | +3.941 |
� | +3.925 |
Neg logit contributions | |
arine | -7.318 |
PF | -7.106 |
illin | -6.911 |
hess | -6.900 |
igan | -6.860 |
Token | tion |
Token ID | 5378 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
� | +5.606 |
� | +5.047 |
� | +4.832 |
wat | +4.794 |
verning | +4.770 |
Neg logit contributions | |
arine | -6.849 |
PF | -6.738 |
RFC | -6.433 |
illin | -6.397 |
hess | -6.397 |
Token | in |
Token ID | 287 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
� | +0.161 |
� | +0.145 |
verning | +0.142 |
�� | +0.142 |
� | +0.140 |
Neg logit contributions | |
arine | -0.139 |
hess | -0.131 |
illin | -0.131 |
PF | -0.130 |
igan | -0.129 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
arine | +0.189 |
hess | +0.179 |
illin | +0.179 |
PF | +0.178 |
igan | +0.177 |
Neg logit contributions | |
� | -0.193 |
� | -0.172 |
verning | -0.168 |
�� | -0.168 |
� | -0.166 |
Token | opened |
Token ID | 4721 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
arine | +0.697 |
hess | +0.655 |
illin | +0.654 |
PF | +0.650 |
igan | +0.647 |
Neg logit contributions | |
� | -0.851 |
� | -0.771 |
verning | -0.756 |
�� | -0.750 |
� | -0.741 |
Token | with |
Token ID | 351 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
� | +1.013 |
� | +0.917 |
verning | +0.893 |
�� | +0.888 |
� | +0.880 |
Neg logit contributions | |
arine | -0.865 |
hess | -0.816 |
illin | -0.814 |
PF | -0.809 |
igan | -0.800 |
Token | 2 |
Token ID | 362 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
� | +1.452 |
� | +1.326 |
verning | +1.291 |
Crim | +1.288 |
�� | +1.284 |
Neg logit contributions | |
arine | -1.028 |
hess | -0.964 |
illin | -0.964 |
PF | -0.957 |
igan | -0.938 |
Token | . |
Token ID | 13 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
� | +3.177 |
� | +2.824 |
�� | +2.733 |
� | +2.718 |
verning | +2.703 |
Neg logit contributions | |
arine | -3.360 |
hess | -3.207 |
PF | -3.172 |
illin | -3.171 |
igan | -3.103 |
Token | 1 |
Token ID | 16 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
� | +2.681 |
� | +2.382 |
verning | +2.291 |
Crim | +2.277 |
�� | +2.275 |
Neg logit contributions | |
arine | -3.097 |
illin | -2.942 |
hess | -2.939 |
PF | -2.922 |
igan | -2.886 |
Token | mil |
Token ID | 1465 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
� | +3.142 |
� | +2.822 |
�� | +2.743 |
� | +2.729 |
verning | +2.727 |
Neg logit contributions | |
arine | -2.645 |
hess | -2.528 |
PF | -2.477 |
illin | -2.475 |
igan | -2.426 |
Token | / |
Token ID | 14 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
� | +6.290 |
� | +5.326 |
wat | +5.172 |
Crim | +5.051 |
� | +4.964 |
Neg logit contributions | |
arine | -11.229 |
hess | -10.923 |
illin | -10.864 |
PF | -10.739 |
RFC | -10.492 |
Token | 0 |
Token ID | 15 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
� | +2.399 |
� | +2.093 |
verning | +2.014 |
wat | +2.002 |
� | +2.000 |
Neg logit contributions | |
arine | -3.355 |
hess | -3.202 |
illin | -3.197 |
PF | -3.178 |
igan | -3.119 |
Token | . |
Token ID | 13 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
� | +2.362 |
� | +2.089 |
verning | +2.046 |
Crim | +2.042 |
wat | +2.041 |
Neg logit contributions | |
arine | -2.678 |
illin | -2.538 |
hess | -2.535 |
PF | -2.516 |
�� | -2.497 |
Token | 6 |
Token ID | 21 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
� | +2.273 |
� | +2.041 |
verning | +1.963 |
Crim | +1.962 |
�� | +1.947 |
Neg logit contributions | |
arine | -2.276 |
illin | -2.153 |
hess | -2.145 |
PF | -2.130 |
igan | -2.097 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
� | +1.388 |
� | +1.252 |
verning | +1.213 |
�� | +1.205 |
Crim | +1.203 |
Neg logit contributions | |
arine | -1.312 |
hess | -1.241 |
illin | -1.236 |
PF | -1.232 |
igan | -1.213 |
Token | – |
Token ID | 784 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
� | +0.888 |
� | +0.804 |
Crim | +0.777 |
verning | +0.777 |
�� | +0.773 |
Neg logit contributions | |
arine | -0.875 |
illin | -0.827 |
hess | -0.826 |
PF | -0.821 |
igan | -0.808 |
Token | Instit |
Token ID | 37931 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
� | +2.077 |
� | +1.879 |
Crim | +1.832 |
verning | +1.823 |
� | +1.801 |
Neg logit contributions | |
arine | -1.882 |
hess | -1.775 |
illin | -1.768 |
PF | -1.747 |
igan | -1.730 |
Token | uto |
Token ID | 9390 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
� | +3.388 |
� | +2.877 |
Crim | +2.700 |
verning | +2.694 |
�� | +2.687 |
Neg logit contributions | |
arine | -6.256 |
PF | -6.070 |
hess | -6.054 |
illin | -6.035 |
RFC | -5.998 |
Token | de |
Token ID | 390 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
� | +1.154 |
� | +1.036 |
verning | +1.005 |
Crim | +1.000 |
�� | +0.997 |
Neg logit contributions | |
arine | -1.183 |
hess | -1.120 |
illin | -1.119 |
PF | -1.111 |
igan | -1.098 |
Token | Pol |
Token ID | 2165 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
� | +0.896 |
� | +0.793 |
verning | +0.765 |
�� | +0.761 |
Crim | +0.759 |
Neg logit contributions | |
arine | -1.136 |
hess | -1.081 |
illin | -1.080 |
PF | -1.075 |
igan | -1.063 |
Token | í |
Token ID | 8836 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
� | +2.275 |
� | +2.065 |
verning | +2.013 |
Crim | +1.999 |
�� | +1.990 |
Neg logit contributions | |
arine | -1.819 |
PF | -1.713 |
illin | -1.709 |
hess | -1.708 |
igan | -1.667 |
Token | tic |
Token ID | 13370 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
� | +8.399 |
� | +7.693 |
Crim | +7.389 |
verning | +7.079 |
� | +7.030 |
Neg logit contributions | |
arine | -8.814 |
�� | -8.704 |
hess | -8.552 |
payoff | -8.460 |
backfield | -8.412 |
Token | as |
Token ID | 292 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
� | +0.699 |
� | +0.624 |
verning | +0.603 |
Crim | +0.598 |
�� | +0.597 |
Neg logit contributions | |
arine | -0.787 |
hess | -0.749 |
illin | -0.749 |
PF | -0.747 |
igan | -0.734 |
Token | y |
Token ID | 331 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
� | +3.497 |
Crim | +3.155 |
� | +3.145 |
verning | +3.065 |
�� | +2.992 |
Neg logit contributions | |
arine | -3.565 |
illin | -3.367 |
hess | -3.357 |
PF | -3.330 |
igan | -3.256 |
Token | B |
Token ID | 347 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
� | +1.152 |
� | +1.028 |
verning | +0.998 |
Crim | +0.996 |
�� | +0.984 |
Neg logit contributions | |
arine | -1.301 |
illin | -1.234 |
hess | -1.233 |
PF | -1.225 |
igan | -1.206 |
Token | ien |
Token ID | 2013 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
� | +1.352 |
� | +1.223 |
verning | +1.191 |
Crim | +1.180 |
�� | +1.172 |
Neg logit contributions | |
arine | -1.184 |
hess | -1.114 |
illin | -1.111 |
PF | -1.109 |
igan | -1.084 |
Token | Un |
Token ID | 791 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
arine | +0.859 |
hess | +0.814 |
illin | +0.812 |
PF | +0.810 |
igan | +0.800 |
Neg logit contributions | |
� | -0.864 |
� | -0.777 |
verning | -0.753 |
�� | -0.752 |
� | -0.743 |
Token | em |
Token ID | 368 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
� | +1.159 |
� | +1.048 |
verning | +1.022 |
wat | +1.008 |
Crim | +1.008 |
Neg logit contributions | |
arine | -1.043 |
illin | -0.985 |
hess | -0.982 |
PF | -0.977 |
igan | -0.965 |
Token | otional |
Token ID | 25453 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
arine | +2.183 |
illin | +2.056 |
hess | +2.022 |
PF | +2.008 |
igan | +1.994 |
Neg logit contributions | |
� | -2.836 |
� | -2.608 |
�� | -2.574 |
� | -2.529 |
� | -2.519 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
� | +1.247 |
� | +1.127 |
verning | +1.095 |
Crim | +1.089 |
�� | +1.084 |
Neg logit contributions | |
arine | -1.169 |
hess | -1.106 |
illin | -1.106 |
PF | -1.098 |
igan | -1.081 |
Token | Sub |
Token ID | 3834 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
� | +0.974 |
� | +0.877 |
verning | +0.850 |
Crim | +0.850 |
�� | +0.842 |
Neg logit contributions | |
arine | -0.943 |
hess | -0.895 |
illin | -0.892 |
PF | -0.886 |
igan | -0.872 |
Token | serv |
Token ID | 3168 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
� | +2.355 |
� | +2.130 |
verning | +2.081 |
Crim | +2.049 |
�� | +2.042 |
Neg logit contributions | |
arine | -2.242 |
hess | -2.144 |
PF | -2.129 |
illin | -2.129 |
igan | -2.101 |
Token | ient |
Token ID | 1153 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
� | +3.570 |
verning | +2.893 |
� | +2.834 |
wat | +2.643 |
� | +2.466 |
Neg logit contributions | |
�� | -12.495 |
PF | -12.388 |
hess | -12.271 |
RFC | -12.170 |
payoff | -12.146 |
Token | , |
Token ID | 11 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
� | +3.202 |
� | +2.883 |
Crim | +2.814 |
verning | +2.806 |
�� | +2.775 |
Neg logit contributions | |
arine | -3.089 |
illin | -2.921 |
PF | -2.913 |
hess | -2.913 |
igan | -2.854 |
Token | Violent |
Token ID | 35615 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
� | +0.343 |
� | +0.309 |
verning | +0.300 |
Crim | +0.298 |
�� | +0.297 |
Neg logit contributions | |
arine | -0.336 |
hess | -0.319 |
illin | -0.318 |
PF | -0.317 |
igan | -0.312 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
� | +2.142 |
� | +1.937 |
Crim | +1.885 |
verning | +1.880 |
�� | +1.860 |
Neg logit contributions | |
arine | -1.999 |
illin | -1.891 |
hess | -1.886 |
PF | -1.879 |
igan | -1.848 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
� | +1.055 |
� | +0.948 |
verning | +0.924 |
Crim | +0.920 |
wat | +0.913 |
Neg logit contributions | |
arine | -1.014 |
illin | -0.957 |
hess | -0.956 |
PF | -0.948 |
igan | -0.934 |
Token | ox |
Token ID | 1140 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
arine | +1.087 |
illin | +1.012 |
hess | +1.012 |
PF | +0.999 |
igan | +0.988 |
Neg logit contributions | |
� | -1.832 |
� | -1.686 |
verning | -1.649 |
�� | -1.645 |
Crim | -1.635 |
Token | et |
Token ID | 316 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
arine | +2.582 |
illin | +2.413 |
hess | +2.373 |
PF | +2.364 |
igan | +2.345 |
Neg logit contributions | |
� | -3.596 |
� | -3.272 |
�� | -3.228 |
Crim | -3.191 |
verning | -3.189 |
Token | ine |
Token ID | 500 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
� | +0.288 |
� | +0.263 |
verning | +0.255 |
Crim | +0.252 |
� | +0.252 |
Neg logit contributions | |
arine | -0.226 |
hess | -0.214 |
PF | -0.214 |
illin | -0.212 |
igan | -0.209 |
Token | ( |
Token ID | 357 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
arine | +0.916 |
illin | +0.863 |
hess | +0.859 |
PF | +0.858 |
igan | +0.844 |
Neg logit contributions | |
� | -1.124 |
� | -1.021 |
verning | -0.995 |
�� | -0.994 |
Crim | -0.982 |
Token | 30 |
Token ID | 1270 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
arine | +1.699 |
PF | +1.630 |
illin | +1.615 |
hess | +1.610 |
igan | +1.583 |
Neg logit contributions | |
� | -1.811 |
� | -1.634 |
�� | -1.596 |
verning | -1.596 |
Crim | -1.574 |
Token | mg |
Token ID | 11296 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
� | +1.096 |
� | +1.004 |
verning | +0.980 |
�� | +0.974 |
Crim | +0.970 |
Neg logit contributions | |
arine | -0.751 |
illin | -0.704 |
hess | -0.702 |
PF | -0.699 |
igan | -0.687 |
Token | / |
Token ID | 14 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
� | +5.431 |
Crim | +4.374 |
wat | +4.372 |
verning | +4.340 |
� | +4.271 |
Neg logit contributions | |
�� | -10.967 |
arine | -10.616 |
hess | -10.380 |
�醒 | -10.320 |
illin | -10.156 |
Token | kg |
Token ID | 10025 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
arine | +1.148 |
illin | +1.078 |
hess | +1.078 |
PF | +1.075 |
igan | +1.062 |
Neg logit contributions | |
� | -1.656 |
� | -1.518 |
�� | -1.481 |
verning | -1.471 |
Crim | -1.466 |
Token | ) |
Token ID | 8 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
� | +2.592 |
� | +2.261 |
verning | +2.173 |
�� | +2.159 |
� | +2.155 |
Neg logit contributions | |
arine | -3.781 |
hess | -3.632 |
illin | -3.604 |
PF | -3.587 |
igan | -3.565 |
Token | administration |
Token ID | 3662 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
arine | +2.909 |
illin | +2.750 |
PF | +2.741 |
hess | +2.705 |
igan | +2.689 |
Neg logit contributions | |
� | -3.342 |
� | -3.029 |
�� | -2.993 |
verning | -2.951 |
Crim | -2.914 |
Token | for |
Token ID | 329 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
arine | +0.950 |
hess | +0.897 |
illin | +0.897 |
PF | +0.892 |
igan | +0.881 |
Neg logit contributions | |
� | -1.049 |
� | -0.948 |
�� | -0.922 |
verning | -0.922 |
Crim | -0.909 |
Token | his |
Token ID | 465 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
arine | +0.426 |
illin | +0.403 |
hess | +0.403 |
PF | +0.402 |
igan | +0.399 |
Neg logit contributions | |
� | -0.456 |
� | -0.409 |
�� | -0.401 |
verning | -0.400 |
� | -0.393 |
Token | fel |
Token ID | 10756 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
� | +2.442 |
� | +2.215 |
verning | +2.147 |
Crim | +2.147 |
� | +2.117 |
Neg logit contributions | |
arine | -2.246 |
hess | -2.122 |
illin | -2.109 |
PF | -2.098 |
igan | -2.063 |
Token | |
Token ID | 3907 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
� | +1.506 |
� | +1.335 |
verning | +1.290 |
�� | +1.281 |
Crim | +1.273 |
Neg logit contributions | |
arine | -1.859 |
hess | -1.769 |
illin | -1.766 |
PF | -1.760 |
igan | -1.739 |
Token | low |
Token ID | 9319 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
� | +2.128 |
� | +1.951 |
verning | +1.899 |
wat | +1.893 |
Crim | +1.879 |
Neg logit contributions | |
arine | -1.826 |
PF | -1.734 |
illin | -1.723 |
hess | -1.715 |
payoff | -1.674 |
Token | Demo |
Token ID | 34588 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
arine | +0.337 |
hess | +0.321 |
illin | +0.318 |
igan | +0.316 |
PF | +0.316 |
Neg logit contributions | |
� | -0.350 |
� | -0.313 |
�� | -0.307 |
verning | -0.305 |
� | -0.299 |
Token | |
Token ID | 3907 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
� | +2.056 |
� | +1.837 |
Crim | +1.762 |
verning | +1.739 |
� | +1.724 |
Neg logit contributions | |
arine | -2.814 |
illin | -2.660 |
PF | -2.659 |
hess | -2.653 |
igan | -2.604 |
Token | cr |
Token ID | 6098 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
� | +3.693 |
� | +3.301 |
� | +2.811 |
wat | +2.803 |
� | +2.730 |
Neg logit contributions | |
�� | -13.037 |
arine | -12.697 |
hess | -12.058 |
backfield | -11.963 |
payoff | -11.862 |
Token | ats |
Token ID | 1381 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
� | +2.225 |
� | +1.993 |
Crim | +1.901 |
� | +1.898 |
wat | +1.881 |
Neg logit contributions | |
arine | -2.470 |
hess | -2.316 |
PF | -2.306 |
illin | -2.295 |
igan | -2.289 |
Token | . |
Token ID | 13 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
� | +1.112 |
� | +1.007 |
verning | +0.975 |
�� | +0.965 |
Crim | +0.965 |
Neg logit contributions | |
arine | -1.024 |
hess | -0.966 |
illin | -0.962 |
PF | -0.960 |
igan | -0.941 |
Token | At |
Token ID | 1629 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
arine | +0.049 |
illin | +0.046 |
hess | +0.046 |
PF | +0.046 |
igan | +0.046 |
Neg logit contributions | |
� | -0.048 |
� | -0.043 |
verning | -0.042 |
�� | -0.042 |
� | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
� | +3.054 |
� | +2.775 |
Crim | +2.685 |
verning | +2.670 |
� | +2.651 |
Neg logit contributions | |
arine | -2.792 |
hess | -2.645 |
illin | -2.622 |
PF | -2.605 |
igan | -2.557 |
Token | ; |
Token ID | 26 |
Feature activation | -9.59e-03 |
Pos logit contributions | |
arine | +0.971 |
hess | +0.920 |
PF | +0.912 |
illin | +0.911 |
igan | +0.907 |
Neg logit contributions | |
� | -0.860 |
� | -0.765 |
�� | -0.740 |
verning | -0.740 |
� | -0.732 |
Token | Christmas |
Token ID | 6786 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
� | +0.066 |
� | +0.060 |
verning | +0.058 |
�� | +0.058 |
Crim | +0.058 |
Neg logit contributions | |
arine | -0.054 |
hess | -0.051 |
illin | -0.051 |
PF | -0.051 |
igan | -0.050 |
Token | Island |
Token ID | 5451 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
arine | +2.988 |
hess | +2.743 |
igan | +2.693 |
illin | +2.642 |
PF | +2.615 |
Neg logit contributions | |
� | -5.776 |
� | -5.262 |
�� | -5.237 |
� | -5.146 |
verning | -5.142 |
Token | ; |
Token ID | 26 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
� | +0.663 |
� | +0.590 |
verning | +0.571 |
�� | +0.566 |
Crim | +0.564 |
Neg logit contributions | |
arine | -0.773 |
illin | -0.736 |
hess | -0.736 |
PF | -0.731 |
igan | -0.722 |
Token | Coc |
Token ID | 18490 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
arine | +0.673 |
hess | +0.634 |
illin | +0.631 |
PF | +0.628 |
igan | +0.621 |
Neg logit contributions | |
� | -0.777 |
� | -0.704 |
verning | -0.683 |
�� | -0.681 |
� | -0.675 |
Token | os |
Token ID | 418 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
arine | +2.520 |
illin | +2.415 |
hess | +2.398 |
igan | +2.351 |
PF | +2.342 |
Neg logit contributions | |
� | -1.860 |
� | -1.643 |
�� | -1.592 |
verning | -1.574 |
� | -1.568 |
Token | ( |
Token ID | 357 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
� | +7.748 |
Crim | +7.215 |
� | +7.137 |
� | +6.631 |
� | +6.558 |
Neg logit contributions | |
�� | -8.743 |
hess | -8.162 |
arine | -8.097 |
RFC | -7.866 |
igan | -7.784 |
Token | Ke |
Token ID | 8896 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
� | +5.053 |
� | +4.258 |
� | +4.069 |
� | +4.032 |
Crim | +3.963 |
Neg logit contributions | |
�� | -8.517 |
arine | -8.507 |
illin | -7.921 |
hess | -7.917 |
payoff | -7.912 |
Token | eling |
Token ID | 10809 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
� | +0.894 |
� | +0.798 |
verning | +0.785 |
� | +0.775 |
Crim | +0.774 |
Neg logit contributions | |
arine | -0.875 |
hess | -0.836 |
illin | -0.830 |
PF | -0.818 |
igan | -0.809 |
Token | ) |
Token ID | 8 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
� | +0.427 |
� | +0.375 |
verning | +0.361 |
�� | +0.358 |
Crim | +0.356 |
Neg logit contributions | |
arine | -0.607 |
hess | -0.580 |
illin | -0.579 |
PF | -0.577 |
igan | -0.570 |
Token | Islands |
Token ID | 12010 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
� | +1.052 |
� | +0.927 |
Crim | +0.894 |
verning | +0.883 |
� | +0.882 |
Neg logit contributions | |
arine | -1.463 |
illin | -1.409 |
hess | -1.408 |
PF | -1.394 |
igan | -1.377 |
Token | ). |
Token ID | 6739 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
� | +2.084 |
� | +1.899 |
verning | +1.836 |
� | +1.827 |
Crim | +1.816 |
Neg logit contributions | |
arine | -1.622 |
illin | -1.524 |
hess | -1.519 |
PF | -1.495 |
igan | -1.484 |
Token |
|
Token ID | 198 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
arine | +2.165 |
hess | +2.046 |
igan | +2.042 |
illin | +2.042 |
PF | +2.030 |
Neg logit contributions | |
� | -2.450 |
� | -2.220 |
�� | -2.211 |
verning | -2.160 |
� | -2.140 |
Token |
|
Token ID | 198 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
� | +1.169 |
� | +1.049 |
verning | +1.023 |
Crim | +1.021 |
wat | +1.012 |
Neg logit contributions | |
arine | -1.143 |
illin | -1.080 |
hess | -1.078 |
PF | -1.068 |
igan | -1.051 |
Token | Program |
Token ID | 15167 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
� | +3.074 |
� | +2.745 |
verning | +2.657 |
Crim | +2.634 |
� | +2.633 |
Neg logit contributions | |
arine | -3.208 |
illin | -3.043 |
hess | -3.040 |
PF | -3.011 |
igan | -2.977 |
Token | of |
Token ID | 286 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
� | +5.169 |
� | +4.583 |
Crim | +4.429 |
verning | +4.394 |
� | +4.374 |
Neg logit contributions | |
arine | -5.445 |
hess | -5.253 |
illin | -5.246 |
PF | -5.210 |
igan | -5.118 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
� | +6.350 |
� | +5.512 |
�� | +5.414 |
Crim | +5.334 |
� | +5.292 |
Neg logit contributions | |
arine | -8.050 |
illin | -7.731 |
hess | -7.728 |
PF | -7.645 |
RFC | -7.485 |
Token | Year |
Token ID | 6280 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
� | +6.918 |
� | +5.971 |
Crim | +5.764 |
� | +5.725 |
� | +5.713 |
Neg logit contributions | |
arine | -9.788 |
illin | -9.460 |
hess | -9.438 |
PF | -9.408 |
RFC | -9.169 |
Token |
|
Token ID | 198 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
� | +0.437 |
� | +0.396 |
verning | +0.385 |
�� | +0.383 |
� | +0.380 |
Neg logit contributions | |
arine | -0.387 |
hess | -0.364 |
illin | -0.362 |
PF | -0.361 |
igan | -0.358 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
� | +1.620 |
� | +1.448 |
Crim | +1.415 |
verning | +1.413 |
wat | +1.404 |
Neg logit contributions | |
arine | -1.626 |
illin | -1.537 |
hess | -1.536 |
PF | -1.517 |
�� | -1.496 |
Token | Out |
Token ID | 7975 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
� | +1.494 |
� | +1.342 |
verning | +1.302 |
�� | +1.295 |
Crim | +1.287 |
Neg logit contributions | |
arine | -1.477 |
hess | -1.399 |
illin | -1.396 |
PF | -1.387 |
igan | -1.371 |
Token | standing |
Token ID | 5646 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
� | +1.671 |
� | +1.511 |
verning | +1.470 |
Crim | +1.452 |
� | +1.452 |
Neg logit contributions | |
arine | -1.447 |
hess | -1.372 |
PF | -1.362 |
illin | -1.362 |
igan | -1.338 |
Token | th |
Token ID | 400 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
� | +1.090 |
� | +0.961 |
verning | +0.913 |
�� | +0.911 |
� | +0.910 |
Neg logit contributions | |
arine | -1.499 |
illin | -1.431 |
hess | -1.430 |
PF | -1.419 |
igan | -1.403 |
Token | lamp |
Token ID | 20450 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
� | +1.165 |
� | +1.054 |
verning | +1.010 |
� | +1.009 |
�� | +1.009 |
Neg logit contributions | |
arine | -1.063 |
hess | -1.012 |
illin | -1.007 |
PF | -1.000 |
igan | -0.982 |
Token | - |
Token ID | 12 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
arine | +0.125 |
hess | +0.117 |
illin | +0.117 |
PF | +0.117 |
igan | +0.115 |
Neg logit contributions | |
� | -0.161 |
� | -0.147 |
verning | -0.143 |
�� | -0.142 |
Crim | -0.141 |
Token | l |
Token ID | 75 |
Feature activation | +2.73e-03 |
Pos logit contributions | |
� | +1.957 |
� | +1.795 |
wat | +1.742 |
Crim | +1.739 |
verning | +1.739 |
Neg logit contributions | |
arine | -1.363 |
hess | -1.284 |
PF | -1.275 |
illin | -1.270 |
igan | -1.246 |
Token | ighter |
Token ID | 4799 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
arine | +0.016 |
hess | +0.015 |
illin | +0.015 |
PF | +0.015 |
igan | +0.015 |
Neg logit contributions | |
� | -0.018 |
� | -0.017 |
verning | -0.016 |
�� | -0.016 |
Crim | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
� | +1.520 |
� | +1.379 |
verning | +1.320 |
�� | +1.318 |
� | +1.317 |
Neg logit contributions | |
arine | -1.423 |
hess | -1.349 |
PF | -1.344 |
illin | -1.344 |
igan | -1.315 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
� | +6.797 |
� | +6.183 |
� | +5.803 |
� | +5.754 |
Crim | +5.721 |
Neg logit contributions | |
arine | -9.516 |
illin | -9.142 |
hess | -9.142 |
PF | -9.060 |
BG | -8.827 |
Token | season |
Token ID | 1622 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
� | +5.982 |
� | +5.483 |
Crim | +5.274 |
� | +5.213 |
� | +5.136 |
Neg logit contributions | |
arine | -6.394 |
hess | -6.152 |
illin | -6.051 |
PF | -6.014 |
BG | -5.853 |
Token | – |
Token ID | 784 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
� | +0.089 |
� | +0.081 |
verning | +0.079 |
�� | +0.078 |
Crim | +0.078 |
Neg logit contributions | |
arine | -0.076 |
hess | -0.071 |
illin | -0.071 |
PF | -0.071 |
igan | -0.070 |
Token | to |
Token ID | 284 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
arine | +1.788 |
hess | +1.689 |
illin | +1.688 |
PF | +1.676 |
igan | +1.665 |
Neg logit contributions | |
� | -2.330 |
� | -2.111 |
�� | -2.084 |
verning | -2.065 |
� | -2.036 |
Token | ensure |
Token ID | 4155 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
arine | +0.475 |
hess | +0.446 |
illin | +0.446 |
PF | +0.443 |
igan | +0.437 |
Neg logit contributions | |
� | -0.607 |
� | -0.552 |
verning | -0.538 |
�� | -0.535 |
Crim | -0.532 |
Token | 2000 |
Token ID | 11024 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
� | +0.384 |
� | +0.353 |
verning | +0.344 |
�� | +0.342 |
Crim | +0.341 |
Neg logit contributions | |
arine | -0.228 |
hess | -0.212 |
illin | -0.211 |
PF | -0.209 |
igan | -0.206 |
Token | The |
Token ID | 383 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
arine | +1.874 |
illin | +1.769 |
hess | +1.767 |
PF | +1.759 |
igan | +1.744 |
Neg logit contributions | |
� | -2.092 |
� | -1.889 |
�� | -1.844 |
verning | -1.827 |
� | -1.809 |
Token | Office |
Token ID | 4452 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
arine | +0.822 |
illin | +0.773 |
hess | +0.771 |
PF | +0.768 |
igan | +0.757 |
Neg logit contributions | |
� | -1.021 |
� | -0.928 |
verning | -0.905 |
�� | -0.900 |
� | -0.893 |
Token | of |
Token ID | 286 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
� | +3.086 |
� | +2.767 |
verning | +2.662 |
Crim | +2.662 |
�� | +2.649 |
Neg logit contributions | |
arine | -3.114 |
hess | -2.958 |
illin | -2.939 |
PF | -2.912 |
igan | -2.887 |
Token | Science |
Token ID | 5800 |
Feature activation | -7.13e-03 |
Pos logit contributions | |
arine | +0.259 |
illin | +0.245 |
PF | +0.244 |
hess | +0.244 |
igan | +0.241 |
Neg logit contributions | |
� | -0.249 |
� | -0.224 |
�� | -0.217 |
verning | -0.217 |
� | -0.214 |
Token | and |
Token ID | 290 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
� | +0.048 |
� | +0.043 |
verning | +0.042 |
�� | +0.042 |
Crim | +0.041 |
Neg logit contributions | |
arine | -0.042 |
hess | -0.040 |
illin | -0.040 |
PF | -0.039 |
igan | -0.039 |
Token | Technology |
Token ID | 8987 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
� | +5.418 |
� | +4.678 |
Crim | +4.549 |
�� | +4.514 |
� | +4.464 |
Neg logit contributions | |
arine | -10.499 |
hess | -10.046 |
BG | -9.980 |
PF | -9.879 |
RFC | -9.871 |
Token | Policy |
Token ID | 7820 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
� | +0.237 |
� | +0.214 |
verning | +0.207 |
Crim | +0.207 |
�� | +0.207 |
Neg logit contributions | |
arine | -0.219 |
hess | -0.207 |
illin | -0.206 |
PF | -0.204 |
igan | -0.203 |
Token | final |
Token ID | 2457 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
� | +2.957 |
� | +2.683 |
verning | +2.617 |
Crim | +2.612 |
� | +2.579 |
Neg logit contributions | |
arine | -2.629 |
hess | -2.533 |
illin | -2.505 |
PF | -2.483 |
igan | -2.410 |
Token | izes |
Token ID | 4340 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
arine | +1.021 |
illin | +0.865 |
PF | +0.855 |
igan | +0.846 |
hess | +0.841 |
Neg logit contributions | |
� | -3.842 |
� | -3.573 |
�� | -3.551 |
verning | -3.516 |
� | -3.491 |
Token | a |
Token ID | 257 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
� | +1.561 |
� | +1.408 |
verning | +1.367 |
�� | +1.356 |
Crim | +1.355 |
Neg logit contributions | |
arine | -1.457 |
hess | -1.385 |
illin | -1.378 |
PF | -1.370 |
igan | -1.352 |
Token | focused |
Token ID | 5670 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
arine | +1.020 |
hess | +0.964 |
illin | +0.961 |
PF | +0.958 |
igan | +0.948 |
Neg logit contributions | |
� | -1.117 |
� | -1.008 |
verning | -0.978 |
�� | -0.977 |
� | -0.966 |
Token | intensely |
Token ID | 31146 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
arine | +0.306 |
hess | +0.287 |
illin | +0.287 |
PF | +0.285 |
igan | +0.281 |
Neg logit contributions | |
� | -0.413 |
� | -0.377 |
verning | -0.367 |
�� | -0.366 |
Crim | -0.363 |
Token | on |
Token ID | 319 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
� | +0.682 |
� | +0.621 |
verning | +0.605 |
�� | +0.602 |
Crim | +0.599 |
Neg logit contributions | |
arine | -0.513 |
hess | -0.482 |
illin | -0.481 |
PF | -0.478 |
igan | -0.471 |
Token | WikiLeaks |
Token ID | 19766 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
� | +1.479 |
� | +1.329 |
verning | +1.295 |
Crim | +1.289 |
�� | +1.276 |
Neg logit contributions | |
arine | -1.452 |
hess | -1.389 |
illin | -1.382 |
PF | -1.374 |
igan | -1.351 |
Token | exp |
Token ID | 1033 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
� | +0.357 |
� | +0.324 |
verning | +0.316 |
�� | +0.314 |
Crim | +0.313 |
Neg logit contributions | |
arine | -0.277 |
hess | -0.260 |
illin | -0.259 |
PF | -0.258 |
igan | -0.254 |
Token | os |
Token ID | 418 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
� | +1.380 |
� | +1.189 |
verning | +1.155 |
Crim | +1.126 |
� | +1.126 |
Neg logit contributions | |
arine | -2.098 |
hess | -2.022 |
PF | -2.013 |
illin | -2.003 |
igan | -1.987 |
Token | és |
Token ID | 20954 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
� | +7.625 |
verning | +6.842 |
� | +6.836 |
� | +6.696 |
Crim | +6.659 |
Neg logit contributions | |
arine | -7.885 |
illin | -7.676 |
hess | -7.644 |
PF | -7.639 |
�� | -7.484 |
Token | in |
Token ID | 287 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
� | +2.390 |
� | +2.163 |
Crim | +2.092 |
verning | +2.091 |
� | +2.057 |
Neg logit contributions | |
arine | -2.270 |
illin | -2.154 |
hess | -2.142 |
PF | -2.139 |
igan | -2.066 |
Token | regard |
Token ID | 2754 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
� | +0.012 |
� | +0.011 |
verning | +0.011 |
�� | +0.011 |
Crim | +0.011 |
Neg logit contributions | |
arine | -0.011 |
hess | -0.011 |
illin | -0.011 |
PF | -0.011 |
igan | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
� | +2.907 |
� | +2.589 |
verning | +2.544 |
Crim | +2.520 |
wat | +2.496 |
Neg logit contributions | |
arine | -3.147 |
illin | -2.996 |
PF | -2.993 |
hess | -2.977 |
igan | -2.933 |
Token | Libyan |
Token ID | 28661 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
� | +1.938 |
� | +1.751 |
verning | +1.703 |
Crim | +1.702 |
�� | +1.675 |
Neg logit contributions | |
arine | -1.824 |
hess | -1.753 |
illin | -1.742 |
PF | -1.727 |
igan | -1.693 |
Token | s |
Token ID | 82 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
� | +4.807 |
� | +4.431 |
verning | +4.284 |
Crim | +4.232 |
� | +4.222 |
Neg logit contributions | |
arine | -5.009 |
PF | -4.810 |
illin | -4.779 |
hess | -4.683 |
igan | -4.668 |
Token | ult |
Token ID | 586 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
� | +1.625 |
� | +1.464 |
verning | +1.424 |
�� | +1.409 |
Crim | +1.408 |
Neg logit contributions | |
arine | -1.501 |
PF | -1.414 |
hess | -1.414 |
illin | -1.413 |
igan | -1.391 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
� | +1.650 |
� | +1.500 |
verning | +1.450 |
� | +1.437 |
Crim | +1.436 |
Neg logit contributions | |
arine | -1.505 |
PF | -1.418 |
hess | -1.415 |
illin | -1.409 |
igan | -1.384 |
Token | When |
Token ID | 1649 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
� | +1.153 |
� | +1.037 |
verning | +1.003 |
Crim | +0.998 |
�� | +0.992 |
Neg logit contributions | |
arine | -1.166 |
hess | -1.103 |
illin | -1.100 |
PF | -1.094 |
igan | -1.079 |
Token | Re |
Token ID | 797 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
arine | +0.899 |
hess | +0.847 |
PF | +0.846 |
illin | +0.845 |
igan | +0.836 |
Neg logit contributions | |
� | -1.081 |
� | -0.978 |
verning | -0.963 |
�� | -0.962 |
� | -0.941 |
Token | |
Token ID | 3907 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
� | +1.992 |
� | +1.774 |
verning | +1.703 |
Crim | +1.682 |
� | +1.680 |
Neg logit contributions | |
arine | -2.525 |
hess | -2.415 |
illin | -2.406 |
PF | -2.404 |
igan | -2.354 |
Token | pub |
Token ID | 12984 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
� | +7.235 |
� | +6.737 |
� | +6.332 |
� | +6.262 |
verning | +6.252 |
Neg logit contributions | |
arine | -8.090 |
�� | -7.835 |
hess | -7.780 |
PF | -7.662 |
illin | -7.533 |
Token | |
Token ID | 3907 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
� | +4.233 |
� | +3.737 |
Crim | +3.571 |
verning | +3.520 |
wat | +3.513 |
Neg logit contributions | |
arine | -6.129 |
PF | -5.941 |
hess | -5.855 |
illin | -5.852 |
igan | -5.756 |
Token | lic |
Token ID | 677 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
� | +6.967 |
wat | +6.380 |
� | +6.371 |
sa | +6.317 |
amed | +6.083 |
Neg logit contributions | |
�� | -13.145 |
PF | -12.178 |
arine | -12.166 |
KR | -11.920 |
payoff | -11.915 |
Token | |
Token ID | 3907 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
� | +1.961 |
� | +1.739 |
Crim | +1.668 |
verning | +1.666 |
� | +1.660 |
Neg logit contributions | |
arine | -2.390 |
illin | -2.270 |
hess | -2.267 |
PF | -2.264 |
igan | -2.238 |
Token | ans |
Token ID | 504 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
� | +6.670 |
� | +6.061 |
wat | +6.030 |
� | +5.839 |
� | +5.788 |
Neg logit contributions | |
�� | -6.491 |
PF | -6.254 |
arine | -6.138 |
payoff | -6.101 |
RFC | -6.033 |
Token | hours |
Token ID | 2250 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
� | +1.066 |
� | +0.960 |
verning | +0.930 |
Crim | +0.925 |
� | +0.923 |
Neg logit contributions | |
arine | -0.997 |
hess | -0.944 |
illin | -0.942 |
PF | -0.934 |
igan | -0.925 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
� | +2.918 |
� | +2.622 |
Crim | +2.546 |
verning | +2.543 |
wat | +2.535 |
Neg logit contributions | |
arine | -2.717 |
hess | -2.590 |
illin | -2.581 |
PF | -2.547 |
igan | -2.519 |
Token | Anyway |
Token ID | 23795 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
� | +0.803 |
� | +0.720 |
verning | +0.696 |
Crim | +0.696 |
� | +0.692 |
Neg logit contributions | |
arine | -0.795 |
hess | -0.752 |
illin | -0.749 |
PF | -0.741 |
igan | -0.736 |
Token | like |
Token ID | 588 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
arine | +1.232 |
hess | +1.163 |
illin | +1.162 |
PF | +1.158 |
igan | +1.147 |
Neg logit contributions | |
� | -1.456 |
� | -1.318 |
verning | -1.289 |
�� | -1.286 |
� | -1.266 |
Token | Pink |
Token ID | 14657 |
Feature activation | +9.53e-03 |
Pos logit contributions | |
� | +0.849 |
� | +0.772 |
Crim | +0.748 |
verning | +0.747 |
� | +0.741 |
Neg logit contributions | |
arine | -0.711 |
hess | -0.672 |
illin | -0.669 |
PF | -0.664 |
igan | -0.656 |
Token | ie |
Token ID | 494 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
arine | +0.056 |
hess | +0.053 |
illin | +0.052 |
PF | +0.052 |
igan | +0.051 |
Neg logit contributions | |
� | -0.064 |
� | -0.058 |
verning | -0.056 |
�� | -0.056 |
Crim | -0.056 |
Token | said |
Token ID | 531 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
� | +7.701 |
Crim | +6.769 |
� | +6.707 |
wat | +6.633 |
� | +6.538 |
Neg logit contributions | |
arine | -7.619 |
hess | -7.337 |
illin | -7.037 |
�� | -7.034 |
PF | -7.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
� | +1.280 |
� | +1.156 |
verning | +1.120 |
Crim | +1.117 |
�� | +1.112 |
Neg logit contributions | |
arine | -1.180 |
hess | -1.115 |
illin | -1.111 |
PF | -1.104 |
igan | -1.089 |
Token | I |
Token ID | 314 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
arine | +0.949 |
hess | +0.893 |
illin | +0.892 |
PF | +0.888 |
igan | +0.875 |
Neg logit contributions | |
� | -1.174 |
� | -1.066 |
verning | -1.040 |
�� | -1.035 |
� | -1.025 |
Token | 'm |
Token ID | 1101 |
Feature activation | +6.87e-03 |
Pos logit contributions | |
� | +1.358 |
� | +1.225 |
verning | +1.184 |
Crim | +1.182 |
� | +1.168 |
Neg logit contributions | |
arine | -1.333 |
hess | -1.262 |
PF | -1.260 |
illin | -1.256 |
igan | -1.223 |
Token | sorry |
Token ID | 7926 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
arine | +0.037 |
hess | +0.035 |
illin | +0.034 |
PF | +0.034 |
igan | +0.034 |
Neg logit contributions | |
� | -0.049 |
� | -0.045 |
verning | -0.044 |
Crim | -0.044 |
�� | -0.043 |
Token | he |
Token ID | 339 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
� | +0.689 |
� | +0.626 |
verning | +0.608 |
�� | +0.604 |
Crim | +0.603 |
Neg logit contributions | |
arine | -0.563 |
hess | -0.530 |
illin | -0.529 |
PF | -0.527 |
igan | -0.519 |
Token | p |
Token ID | 279 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
arine | +1.021 |
hess | +0.966 |
illin | +0.965 |
PF | +0.960 |
igan | +0.951 |
Neg logit contributions | |
� | -1.034 |
� | -0.929 |
verning | -0.904 |
�� | -0.903 |
� | -0.890 |
Token | ales |
Token ID | 2040 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
� | +1.049 |
� | +0.948 |
verning | +0.920 |
�� | +0.913 |
Crim | +0.909 |
Neg logit contributions | |
arine | -0.971 |
hess | -0.916 |
illin | -0.912 |
PF | -0.912 |
igan | -0.897 |
Token | in |
Token ID | 287 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
� | +0.137 |
� | +0.124 |
verning | +0.121 |
�� | +0.120 |
Crim | +0.120 |
Neg logit contributions | |
arine | -0.107 |
hess | -0.101 |
illin | -0.101 |
PF | -0.100 |
igan | -0.099 |
Token | com |
Token ID | 401 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
arine | +0.322 |
hess | +0.301 |
illin | +0.301 |
PF | +0.299 |
igan | +0.295 |
Neg logit contributions | |
� | -0.475 |
� | -0.435 |
verning | -0.427 |
�� | -0.425 |
� | -0.420 |
Token | |
Token ID | 3907 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
� | +2.146 |
� | +1.892 |
verning | +1.809 |
Crim | +1.802 |
� | +1.786 |
Neg logit contributions | |
arine | -2.831 |
hess | -2.697 |
illin | -2.691 |
PF | -2.685 |
igan | -2.649 |
Token | par |
Token ID | 1845 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
� | +7.153 |
wat | +6.591 |
aund | +6.302 |
� | +6.268 |
verning | +6.150 |
Neg logit contributions | |
arine | -7.585 |
�� | -7.408 |
hess | -7.316 |
KR | -7.224 |
PF | -7.161 |
Token | |
Token ID | 3907 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
� | +2.810 |
� | +2.493 |
Crim | +2.392 |
wat | +2.385 |
verning | +2.363 |
Neg logit contributions | |
arine | -3.931 |
PF | -3.826 |
hess | -3.780 |
illin | -3.748 |
RFC | -3.686 |
Token | is |
Token ID | 271 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
� | +6.100 |
wat | +5.691 |
� | +5.625 |
verning | +5.461 |
� | +5.378 |
Neg logit contributions | |
PF | -5.200 |
�� | -5.118 |
RFC | -5.106 |
arine | -5.087 |
hess | -5.015 |
Token | |
Token ID | 3907 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
� | +2.774 |
� | +2.452 |
verning | +2.341 |
Crim | +2.330 |
� | +2.317 |
Neg logit contributions | |
arine | -3.725 |
PF | -3.566 |
hess | -3.551 |
illin | -3.542 |
igan | -3.480 |
Token | on |
Token ID | 261 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
� | +3.984 |
� | +3.596 |
wat | +3.463 |
� | +3.406 |
verning | +3.372 |
Neg logit contributions | |
arine | -4.349 |
PF | -4.289 |
hess | -4.201 |
illin | -4.111 |
RFC | -4.097 |
Token | � |
Token ID | 247 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
arine | +0.507 |
illin | +0.490 |
PF | +0.489 |
hess | +0.489 |
igan | +0.486 |
Neg logit contributions | |
� | -0.169 |
verning | -0.138 |
Crim | -0.136 |
wat | -0.132 |
� | -0.132 |
Token | ve |
Token ID | 303 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
arine | +0.544 |
hess | +0.515 |
illin | +0.515 |
PF | +0.512 |
igan | +0.508 |
Neg logit contributions | |
� | -0.522 |
� | -0.467 |
verning | -0.454 |
�� | -0.453 |
Crim | -0.448 |
Token | had |
Token ID | 550 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
� | +1.123 |
� | +1.007 |
verning | +0.977 |
�� | +0.972 |
Crim | +0.964 |
Neg logit contributions | |
arine | -1.167 |
hess | -1.107 |
illin | -1.105 |
PF | -1.100 |
igan | -1.087 |
Token | as |
Token ID | 355 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
� | +1.332 |
� | +1.209 |
verning | +1.172 |
Crim | +1.166 |
�� | +1.161 |
Neg logit contributions | |
arine | -1.172 |
hess | -1.102 |
illin | -1.101 |
PF | -1.099 |
igan | -1.077 |
Token | pres |
Token ID | 906 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
� | +2.001 |
� | +1.811 |
verning | +1.750 |
Crim | +1.747 |
�� | +1.742 |
Neg logit contributions | |
arine | -1.786 |
hess | -1.686 |
illin | -1.681 |
PF | -1.675 |
igan | -1.641 |
Token | |
Token ID | 3907 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
� | +4.733 |
� | +4.138 |
wat | +4.010 |
Crim | +3.932 |
verning | +3.873 |
Neg logit contributions | |
arine | -7.670 |
PF | -7.345 |
�� | -7.336 |
illin | -7.290 |
RFC | -7.200 |
Token | id |
Token ID | 312 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
� | +6.645 |
� | +6.098 |
wat | +6.005 |
verning | +5.778 |
aund | +5.732 |
Neg logit contributions | |
PF | -8.074 |
arine | -7.857 |
hess | -7.791 |
�� | -7.774 |
backfield | -7.731 |
Token | |
Token ID | 3907 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
� | +2.198 |
� | +1.945 |
verning | +1.869 |
� | +1.854 |
Crim | +1.841 |
Neg logit contributions | |
arine | -2.949 |
illin | -2.816 |
PF | -2.807 |
hess | -2.799 |
igan | -2.758 |
Token | ent |
Token ID | 298 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
� | +3.796 |
� | +3.390 |
verning | +3.312 |
� | +3.257 |
wat | +3.255 |
Neg logit contributions | |
arine | -5.280 |
PF | -5.276 |
illin | -5.103 |
RFC | -5.075 |
�� | -5.070 |
Token | since |
Token ID | 1201 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
arine | +0.973 |
hess | +0.924 |
illin | +0.916 |
PF | +0.913 |
igan | +0.908 |
Neg logit contributions | |
� | -1.078 |
� | -0.969 |
verning | -0.948 |
�� | -0.946 |
� | -0.933 |
Token | at |
Token ID | 379 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
� | +1.233 |
� | +1.118 |
verning | +1.085 |
�� | +1.079 |
Crim | +1.079 |
Neg logit contributions | |
arine | -1.056 |
hess | -0.997 |
illin | -0.994 |
PF | -0.990 |
igan | -0.974 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
� | +0.840 |
� | +0.753 |
verning | +0.731 |
Crim | +0.728 |
�� | +0.720 |
Neg logit contributions | |
arine | -0.852 |
hess | -0.806 |
illin | -0.804 |
PF | -0.798 |
igan | -0.789 |
Token |
|
Token ID | 198 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
� | +1.175 |
� | +1.055 |
verning | +1.027 |
Crim | +1.025 |
wat | +1.019 |
Neg logit contributions | |
arine | -1.157 |
illin | -1.093 |
hess | -1.092 |
PF | -1.078 |
igan | -1.064 |
Token | This |
Token ID | 1212 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
� | +0.377 |
� | +0.341 |
verning | +0.330 |
�� | +0.327 |
Crim | +0.327 |
Neg logit contributions | |
arine | -0.338 |
illin | -0.319 |
hess | -0.319 |
PF | -0.314 |
igan | -0.313 |
Token | dream |
Token ID | 4320 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
� | +1.517 |
� | +1.373 |
Crim | +1.325 |
verning | +1.324 |
� | +1.312 |
Neg logit contributions | |
arine | -1.454 |
hess | -1.380 |
illin | -1.364 |
PF | -1.360 |
igan | -1.343 |
Token | gives |
Token ID | 3607 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
� | +3.061 |
� | +2.772 |
� | +2.638 |
verning | +2.633 |
� | +2.632 |
Neg logit contributions | |
arine | -3.203 |
PF | -3.083 |
hess | -3.070 |
illin | -3.062 |
RFC | -2.975 |
Token | me |
Token ID | 502 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
� | +3.422 |
� | +3.070 |
Crim | +2.971 |
� | +2.970 |
verning | +2.959 |
Neg logit contributions | |
arine | -2.955 |
hess | -2.787 |
illin | -2.775 |
PF | -2.767 |
igan | -2.709 |
Token | the |
Token ID | 262 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
� | +7.938 |
� | +7.137 |
� | +6.847 |
Crim | +6.773 |
wat | +6.758 |
Neg logit contributions | |
arine | -7.061 |
�� | -6.718 |
hess | -6.710 |
PF | -6.576 |
RFC | -6.540 |
Token | idea |
Token ID | 2126 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
� | +4.207 |
� | +3.824 |
Crim | +3.653 |
� | +3.636 |
wat | +3.619 |
Neg logit contributions | |
arine | -3.647 |
hess | -3.464 |
PF | -3.402 |
illin | -3.388 |
igan | -3.302 |
Token | that |
Token ID | 326 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
� | +3.691 |
� | +3.313 |
Crim | +3.138 |
� | +3.131 |
wat | +3.130 |
Neg logit contributions | |
arine | -3.713 |
hess | -3.504 |
PF | -3.495 |
illin | -3.495 |
igan | -3.375 |
Token | it |
Token ID | 340 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
� | +2.918 |
� | +2.638 |
Crim | +2.570 |
verning | +2.555 |
wat | +2.527 |
Neg logit contributions | |
arine | -2.641 |
hess | -2.514 |
illin | -2.495 |
PF | -2.493 |
igan | -2.452 |
Token | � |
Token ID | 447 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
arine | +0.328 |
hess | +0.310 |
illin | +0.310 |
PF | +0.309 |
igan | +0.305 |
Neg logit contributions | |
� | -0.320 |
� | -0.287 |
verning | -0.278 |
�� | -0.277 |
Crim | -0.275 |
Token | Conference |
Token ID | 8785 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
� | +2.583 |
� | +2.317 |
Crim | +2.259 |
verning | +2.254 |
� | +2.252 |
Neg logit contributions | |
arine | -2.450 |
hess | -2.350 |
illin | -2.343 |
RFC | -2.268 |
igan | -2.263 |
Token | Men |
Token ID | 6065 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
arine | +0.561 |
hess | +0.527 |
illin | +0.526 |
PF | +0.522 |
igan | +0.515 |
Neg logit contributions | |
� | -0.745 |
� | -0.678 |
verning | -0.661 |
�� | -0.657 |
Crim | -0.656 |
Token | 's |
Token ID | 338 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
� | +2.861 |
� | +2.617 |
verning | +2.581 |
Crim | +2.576 |
wat | +2.528 |
Neg logit contributions | |
arine | -2.007 |
illin | -1.901 |
hess | -1.878 |
PF | -1.863 |
igan | -1.820 |
Token | Basketball |
Token ID | 25911 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
� | +3.524 |
� | +3.211 |
Crim | +3.159 |
verning | +3.075 |
� | +3.057 |
Neg logit contributions | |
arine | -3.688 |
hess | -3.546 |
illin | -3.521 |
igan | -3.458 |
RFC | -3.451 |
Token | Player |
Token ID | 7853 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
� | +0.869 |
� | +0.791 |
verning | +0.772 |
Crim | +0.767 |
�� | +0.763 |
Neg logit contributions | |
arine | -0.648 |
hess | -0.609 |
illin | -0.609 |
PF | -0.602 |
igan | -0.595 |
Token | of |
Token ID | 286 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
� | +0.990 |
� | +0.893 |
verning | +0.870 |
�� | +0.865 |
Crim | +0.858 |
Neg logit contributions | |
arine | -0.907 |
hess | -0.856 |
illin | -0.854 |
PF | -0.853 |
igan | -0.841 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
� | +5.729 |
Crim | +5.118 |
� | +4.874 |
wat | +4.867 |
verning | +4.800 |
Neg logit contributions | |
arine | -9.297 |
�� | -9.024 |
hess | -8.936 |
illin | -8.914 |
�醒 | -8.649 |
Token | Year |
Token ID | 6280 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
� | +5.446 |
� | +4.863 |
Crim | +4.835 |
� | +4.683 |
verning | +4.644 |
Neg logit contributions | |
arine | -6.934 |
hess | -6.698 |
illin | -6.669 |
PF | -6.519 |
�� | -6.395 |
Token | by |
Token ID | 416 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
arine | +1.181 |
hess | +1.102 |
illin | +1.100 |
PF | +1.099 |
igan | +1.085 |
Neg logit contributions | |
� | -1.488 |
� | -1.345 |
�� | -1.319 |
verning | -1.309 |
� | -1.296 |
Token | both |
Token ID | 1111 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
� | +1.408 |
� | +1.268 |
verning | +1.244 |
Crim | +1.230 |
�� | +1.223 |
Neg logit contributions | |
arine | -1.238 |
hess | -1.172 |
illin | -1.167 |
PF | -1.155 |
igan | -1.144 |
Token | the |
Token ID | 262 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
� | +5.761 |
verning | +5.167 |
Crim | +5.123 |
� | +5.106 |
� | +4.967 |
Neg logit contributions | |
arine | -5.247 |
hess | -4.960 |
illin | -4.930 |
�� | -4.863 |
PF | -4.797 |
Token | , |
Token ID | 11 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
arine | +1.661 |
illin | +1.565 |
PF | +1.563 |
hess | +1.536 |
igan | +1.519 |
Neg logit contributions | |
� | -2.527 |
� | -2.337 |
verning | -2.288 |
�� | -2.268 |
Crim | -2.258 |
Token | 30 |
Token ID | 1542 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
arine | +2.241 |
PF | +2.109 |
hess | +2.076 |
illin | +2.074 |
igan | +2.031 |
Neg logit contributions | |
� | -3.121 |
� | -2.865 |
�� | -2.812 |
verning | -2.790 |
Crim | -2.751 |
Token | , |
Token ID | 11 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
arine | +1.838 |
illin | +1.751 |
PF | +1.744 |
hess | +1.724 |
igan | +1.705 |
Neg logit contributions | |
� | -2.109 |
� | -1.910 |
verning | -1.874 |
�� | -1.855 |
Crim | -1.841 |
Token | or |
Token ID | 393 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
arine | +4.436 |
PF | +4.133 |
illin | +4.092 |
hess | +3.978 |
igan | +3.961 |
Neg logit contributions | |
� | -6.068 |
� | -5.613 |
�� | -5.530 |
verning | -5.483 |
�� | -5.428 |
Token | 100 |
Token ID | 1802 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
arine | +4.354 |
PF | +4.004 |
illin | +3.968 |
payoff | +3.900 |
igan | +3.871 |
Neg logit contributions | |
� | -7.079 |
�� | -6.600 |
� | -6.577 |
verning | -6.504 |
�� | -6.336 |
Token | mg |
Token ID | 11296 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
arine | +1.196 |
illin | +1.122 |
PF | +1.118 |
hess | +1.111 |
igan | +1.097 |
Neg logit contributions | |
� | -1.784 |
� | -1.641 |
verning | -1.612 |
�� | -1.598 |
Crim | -1.588 |
Token | / |
Token ID | 14 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
� | +5.856 |
� | +4.920 |
� | +4.831 |
Crim | +4.734 |
�� | +4.691 |
Neg logit contributions | |
arine | -9.080 |
hess | -8.952 |
igan | -8.698 |
illin | -8.666 |
RFC | -8.577 |
Token | kg |
Token ID | 10025 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
arine | +0.427 |
illin | +0.399 |
hess | +0.399 |
PF | +0.398 |
igan | +0.392 |
Neg logit contributions | |
� | -0.595 |
� | -0.543 |
verning | -0.529 |
�� | -0.527 |
Crim | -0.525 |
Token | ) |
Token ID | 8 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
� | +2.822 |
� | +2.438 |
verning | +2.342 |
Crim | +2.339 |
� | +2.334 |
Neg logit contributions | |
arine | -4.253 |
hess | -4.120 |
illin | -4.053 |
PF | -4.027 |
igan | -4.020 |
Token | also |
Token ID | 635 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
arine | +2.608 |
illin | +2.466 |
PF | +2.461 |
hess | +2.433 |
igan | +2.414 |
Neg logit contributions | |
� | -3.021 |
� | -2.747 |
�� | -2.685 |
verning | -2.658 |
Crim | -2.630 |
Token | showed |
Token ID | 3751 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
arine | +1.160 |
hess | +1.092 |
illin | +1.091 |
PF | +1.090 |
igan | +1.073 |
Neg logit contributions | |
� | -1.378 |
� | -1.251 |
�� | -1.222 |
verning | -1.213 |
Crim | -1.203 |
Token |
|
Token ID | 198 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
� | +0.369 |
� | +0.333 |
verning | +0.324 |
Crim | +0.321 |
�� | +0.320 |
Neg logit contributions | |
arine | -0.338 |
hess | -0.319 |
illin | -0.318 |
PF | -0.316 |
igan | -0.312 |
Token | It |
Token ID | 1026 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
� | +0.263 |
� | +0.237 |
verning | +0.229 |
�� | +0.228 |
Crim | +0.227 |
Neg logit contributions | |
arine | -0.258 |
illin | -0.244 |
hess | -0.244 |
PF | -0.241 |
igan | -0.240 |
Token | 's |
Token ID | 338 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
arine | +1.561 |
hess | +1.465 |
illin | +1.454 |
PF | +1.452 |
igan | +1.441 |
Neg logit contributions | |
� | -1.957 |
� | -1.775 |
�� | -1.738 |
verning | -1.734 |
� | -1.712 |
Token | really |
Token ID | 1107 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
arine | +0.615 |
hess | +0.578 |
illin | +0.577 |
PF | +0.574 |
igan | +0.566 |
Neg logit contributions | |
� | -0.759 |
� | -0.689 |
verning | -0.671 |
�� | -0.669 |
� | -0.663 |
Token | that |
Token ID | 326 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
� | +0.956 |
� | +0.866 |
verning | +0.840 |
Crim | +0.838 |
� | +0.830 |
Neg logit contributions | |
arine | -0.828 |
hess | -0.781 |
illin | -0.781 |
PF | -0.778 |
igan | -0.762 |
Token | simple |
Token ID | 2829 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
arine | +1.098 |
hess | +1.033 |
illin | +1.031 |
PF | +1.026 |
igan | +1.012 |
Neg logit contributions | |
� | -1.386 |
� | -1.260 |
verning | -1.225 |
�� | -1.223 |
� | -1.213 |
Token | :) |
Token ID | 14373 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
arine | +4.628 |
hess | +4.400 |
igan | +4.355 |
PF | +4.328 |
payoff | +4.271 |
Neg logit contributions | |
� | -6.234 |
� | -5.718 |
�� | -5.636 |
verning | -5.600 |
� | -5.572 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
arine | +2.365 |
hess | +2.242 |
PF | +2.234 |
illin | +2.227 |
igan | +2.201 |
Neg logit contributions | |
� | -2.784 |
� | -2.526 |
verning | -2.479 |
�� | -2.477 |
� | -2.434 |
Token |
|
Token ID | 198 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
arine | +0.952 |
hess | +0.899 |
PF | +0.896 |
illin | +0.895 |
igan | +0.885 |
Neg logit contributions | |
� | -1.146 |
� | -1.041 |
�� | -1.022 |
verning | -1.011 |
� | -1.001 |
Token | If |
Token ID | 1532 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
arine | +0.602 |
hess | +0.569 |
illin | +0.568 |
PF | +0.565 |
igan | +0.558 |
Neg logit contributions | |
� | -0.626 |
� | -0.564 |
verning | -0.547 |
�� | -0.544 |
Crim | -0.541 |
Token | you |
Token ID | 345 |
Feature activation | +6.12e-03 |
Pos logit contributions | |
� | +1.725 |
� | +1.556 |
verning | +1.508 |
Crim | +1.506 |
�� | +1.500 |
Neg logit contributions | |
arine | -1.571 |
hess | -1.488 |
illin | -1.484 |
PF | -1.472 |
igan | -1.456 |
Token | } |
Token ID | 92 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
� | +0.521 |
� | +0.476 |
verning | +0.464 |
�� | +0.463 |
Crim | +0.459 |
Neg logit contributions | |
arine | -0.390 |
hess | -0.365 |
PF | -0.364 |
illin | -0.363 |
igan | -0.357 |
Token | -> |
Token ID | 4613 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
� | +2.111 |
� | +1.889 |
verning | +1.831 |
�� | +1.820 |
Crim | +1.808 |
Neg logit contributions | |
arine | -2.100 |
hess | -1.995 |
illin | -1.991 |
PF | -1.974 |
igan | -1.946 |
Token | " |
Token ID | 366 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
arine | +0.170 |
hess | +0.162 |
illin | +0.161 |
PF | +0.161 |
igan | +0.159 |
Neg logit contributions | |
� | -0.145 |
� | -0.129 |
verning | -0.125 |
�� | -0.124 |
Crim | -0.123 |
Token | S |
Token ID | 50 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
� | +2.082 |
� | +1.896 |
verning | +1.837 |
�� | +1.826 |
� | +1.824 |
Neg logit contributions | |
arine | -1.576 |
illin | -1.483 |
hess | -1.476 |
PF | -1.452 |
igan | -1.446 |
Token | ", |
Token ID | 1600 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
� | +2.891 |
� | +2.629 |
verning | +2.547 |
�� | +2.532 |
� | +2.525 |
Neg logit contributions | |
arine | -2.185 |
illin | -2.056 |
hess | -2.054 |
PF | -2.039 |
igan | -2.002 |
Token | { |
Token ID | 1391 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
� | +1.901 |
� | +1.708 |
�� | +1.654 |
verning | +1.654 |
Crim | +1.638 |
Neg logit contributions | |
arine | -1.832 |
hess | -1.740 |
illin | -1.739 |
PF | -1.725 |
igan | -1.705 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
arine | +5.135 |
PF | +4.946 |
hess | +4.934 |
igan | +4.815 |
RFC | +4.804 |
Neg logit contributions | |
� | -6.424 |
verning | -5.819 |
�� | -5.793 |
� | -5.784 |
Crim | -5.644 |
Token | , |
Token ID | 11 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
arine | +1.563 |
PF | +1.481 |
hess | +1.478 |
igan | +1.459 |
illin | +1.454 |
Neg logit contributions | |
� | -1.877 |
� | -1.703 |
�� | -1.695 |
verning | -1.653 |
� | -1.638 |
Token | 14 |
Token ID | 1478 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
� | +0.492 |
� | +0.447 |
verning | +0.436 |
�� | +0.433 |
Crim | +0.432 |
Neg logit contributions | |
arine | -0.374 |
hess | -0.351 |
illin | -0.351 |
PF | -0.348 |
igan | -0.344 |
Token | } |
Token ID | 92 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
� | +0.327 |
� | +0.297 |
verning | +0.289 |
�� | +0.287 |
Crim | +0.286 |
Neg logit contributions | |
arine | -0.256 |
hess | -0.240 |
illin | -0.240 |
PF | -0.238 |
igan | -0.235 |
Token | -> |
Token ID | 4613 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
� | +1.501 |
� | +1.339 |
verning | +1.306 |
Crim | +1.292 |
� | +1.279 |
Neg logit contributions | |
arine | -1.529 |
illin | -1.449 |
hess | -1.448 |
PF | -1.432 |
igan | -1.410 |
Token | guess |
Token ID | 4724 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
arine | +1.492 |
hess | +1.418 |
illin | +1.404 |
PF | +1.404 |
igan | +1.394 |
Neg logit contributions | |
� | -1.614 |
� | -1.454 |
verning | -1.420 |
�� | -1.412 |
� | -1.392 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
� | +0.286 |
� | +0.257 |
verning | +0.249 |
�� | +0.248 |
Crim | +0.247 |
Neg logit contributions | |
arine | -0.284 |
illin | -0.269 |
hess | -0.269 |
PF | -0.267 |
igan | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
� | +0.701 |
� | +0.627 |
verning | +0.607 |
Crim | +0.606 |
� | +0.600 |
Neg logit contributions | |
arine | -0.739 |
hess | -0.699 |
illin | -0.697 |
PF | -0.691 |
igan | -0.684 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
� | +0.164 |
� | +0.148 |
verning | +0.144 |
Crim | +0.143 |
�� | +0.143 |
Neg logit contributions | |
arine | -0.149 |
hess | -0.141 |
illin | -0.141 |
PF | -0.140 |
igan | -0.138 |
Token | I |
Token ID | 40 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
arine | +0.084 |
hess | +0.080 |
illin | +0.080 |
PF | +0.079 |
igan | +0.078 |
Neg logit contributions | |
� | -0.089 |
� | -0.080 |
verning | -0.077 |
�� | -0.077 |
Crim | -0.077 |
Token | asked |
Token ID | 1965 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
� | +2.259 |
� | +2.037 |
verning | +1.968 |
Crim | +1.953 |
wat | +1.941 |
Neg logit contributions | |
arine | -2.358 |
hess | -2.235 |
PF | -2.232 |
illin | -2.225 |
igan | -2.157 |
Token | J |
Token ID | 449 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
arine | +4.519 |
PF | +4.374 |
igan | +4.280 |
hess | +4.279 |
illin | +4.243 |
Neg logit contributions | |
� | -5.834 |
�� | -5.335 |
� | -5.313 |
verning | -5.200 |
� | -5.095 |
Token | atin |
Token ID | 10680 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
arine | +1.078 |
hess | +1.018 |
illin | +1.018 |
PF | +1.014 |
igan | +1.001 |
Neg logit contributions | |
� | -1.110 |
� | -0.999 |
�� | -0.971 |
verning | -0.970 |
Crim | -0.958 |
Token | Th |
Token ID | 536 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
arine | +0.695 |
hess | +0.655 |
illin | +0.653 |
PF | +0.651 |
igan | +0.643 |
Neg logit contributions | |
� | -0.854 |
� | -0.774 |
verning | -0.755 |
�� | -0.752 |
Crim | -0.745 |
Token | ak |
Token ID | 461 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
arine | +1.320 |
illin | +1.252 |
hess | +1.246 |
igan | +1.241 |
PF | +1.237 |
Neg logit contributions | |
� | -1.132 |
� | -1.008 |
�� | -0.978 |
verning | -0.970 |
� | -0.960 |
Token | kar |
Token ID | 21070 |
Feature activation | -9.59e-03 |
Pos logit contributions | |
� | +1.839 |
� | +1.651 |
wat | +1.604 |
verning | +1.596 |
� | +1.591 |
Neg logit contributions | |
arine | -1.797 |
hess | -1.718 |
PF | -1.708 |
illin | -1.694 |
igan | -1.676 |
Token | necessary |
Token ID | 3306 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
arine | +0.782 |
hess | +0.734 |
illin | +0.732 |
PF | +0.729 |
igan | +0.718 |
Neg logit contributions | |
� | -1.063 |
� | -0.969 |
verning | -0.944 |
�� | -0.940 |
Crim | -0.933 |
Token | packages |
Token ID | 10392 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
arine | +1.422 |
hess | +1.341 |
PF | +1.336 |
illin | +1.335 |
igan | +1.313 |
Neg logit contributions | |
� | -1.709 |
� | -1.553 |
verning | -1.512 |
�� | -1.503 |
� | -1.489 |
Token | from |
Token ID | 422 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
arine | +2.186 |
hess | +2.075 |
PF | +2.060 |
illin | +2.049 |
igan | +2.040 |
Neg logit contributions | |
� | -2.767 |
� | -2.520 |
verning | -2.468 |
�� | -2.433 |
� | -2.426 |
Token | im |
Token ID | 545 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
arine | +1.620 |
hess | +1.535 |
PF | +1.528 |
illin | +1.527 |
igan | +1.504 |
Neg logit contributions | |
� | -1.950 |
� | -1.766 |
verning | -1.726 |
�� | -1.714 |
� | -1.697 |
Token | utils |
Token ID | 26791 |
Feature activation | +9.98e-02 |
Pos logit contributions | |
� | +0.716 |
� | +0.632 |
verning | +0.611 |
�� | +0.603 |
Crim | +0.603 |
Neg logit contributions | |
arine | -0.911 |
hess | -0.867 |
PF | -0.866 |
illin | -0.866 |
igan | -0.853 |
Token | import |
Token ID | 1330 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
arine | +0.543 |
hess | +0.510 |
illin | +0.508 |
PF | +0.506 |
igan | +0.499 |
Neg logit contributions | |
� | -0.710 |
� | -0.646 |
verning | -0.630 |
�� | -0.626 |
Crim | -0.622 |
Token | paths |
Token ID | 13532 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
arine | +4.869 |
PF | +4.693 |
illin | +4.656 |
hess | +4.620 |
igan | +4.619 |
Neg logit contributions | |
� | -5.652 |
� | -5.167 |
verning | -5.074 |
�� | -5.002 |
� | -4.947 |
Token | import |
Token ID | 1330 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
arine | +1.184 |
hess | +1.113 |
illin | +1.106 |
PF | +1.106 |
igan | +1.095 |
Neg logit contributions | |
� | -1.480 |
� | -1.346 |
verning | -1.312 |
�� | -1.305 |
Crim | -1.294 |
Token | n |
Token ID | 299 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
arine | +5.246 |
illin | +5.087 |
PF | +5.078 |
hess | +5.025 |
igan | +5.009 |
Neg logit contributions | |
� | -5.614 |
� | -5.113 |
verning | -5.044 |
�� | -4.901 |
� | -4.863 |
Token | umpy |
Token ID | 32152 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
arine | +1.445 |
hess | +1.349 |
illin | +1.344 |
PF | +1.335 |
igan | +1.320 |
Neg logit contributions | |
� | -2.141 |
� | -1.961 |
verning | -1.919 |
�� | -1.910 |
� | -1.894 |
Token | as |
Token ID | 355 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
arine | +1.164 |
hess | +1.084 |
illin | +1.080 |
PF | +1.073 |
igan | +1.065 |
Neg logit contributions | |
� | -1.780 |
� | -1.636 |
verning | -1.596 |
�� | -1.591 |
Crim | -1.574 |
Token | future |
Token ID | 2003 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
arine | +0.213 |
hess | +0.201 |
illin | +0.200 |
PF | +0.199 |
igan | +0.197 |
Neg logit contributions | |
� | -0.255 |
� | -0.231 |
verning | -0.225 |
�� | -0.223 |
Crim | -0.222 |
Token | blog |
Token ID | 4130 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
arine | +2.697 |
PF | +2.524 |
illin | +2.519 |
hess | +2.507 |
igan | +2.455 |
Neg logit contributions | |
� | -4.502 |
� | -4.113 |
verning | -4.048 |
�� | -4.038 |
� | -3.982 |
Token | post |
Token ID | 1281 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
arine | +0.760 |
hess | +0.706 |
illin | +0.706 |
PF | +0.704 |
igan | +0.692 |
Neg logit contributions | |
� | -1.178 |
� | -1.077 |
verning | -1.056 |
�� | -1.052 |
Crim | -1.042 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
arine | +2.294 |
PF | +2.168 |
hess | +2.150 |
illin | +2.145 |
igan | +2.135 |
Neg logit contributions | |
� | -2.650 |
� | -2.386 |
verning | -2.343 |
�� | -2.341 |
Crim | -2.302 |
Token | Stay |
Token ID | 16160 |
Feature activation | -6.26e-03 |
Pos logit contributions | |
arine | +1.016 |
hess | +0.961 |
illin | +0.960 |
PF | +0.957 |
igan | +0.946 |
Neg logit contributions | |
� | -1.093 |
� | -0.986 |
verning | -0.960 |
�� | -0.958 |
� | -0.944 |
Token | tuned |
Token ID | 16524 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
� | +0.045 |
� | +0.041 |
verning | +0.039 |
Crim | +0.039 |
�� | +0.039 |
Neg logit contributions | |
arine | -0.034 |
hess | -0.032 |
illin | -0.032 |
PF | -0.032 |
igan | -0.031 |
Token | ! |
Token ID | 0 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
arine | +4.189 |
hess | +3.930 |
PF | +3.922 |
igan | +3.915 |
illin | +3.847 |
Neg logit contributions | |
� | -5.834 |
� | -5.271 |
�� | -5.250 |
verning | -5.205 |
� | -5.118 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
arine | +3.736 |
PF | +3.532 |
illin | +3.519 |
hess | +3.507 |
igan | +3.495 |
Neg logit contributions | |
� | -4.722 |
� | -4.277 |
verning | -4.265 |
�� | -4.233 |
� | -4.137 |
Token | Mer |
Token ID | 13102 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
� | +0.326 |
� | +0.294 |
verning | +0.285 |
�� | +0.284 |
� | +0.282 |
Neg logit contributions | |
arine | -0.295 |
hess | -0.279 |
illin | -0.278 |
PF | -0.276 |
igan | -0.273 |
Token | kel |
Token ID | 7750 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
� | +0.100 |
� | +0.089 |
verning | +0.086 |
�� | +0.086 |
Crim | +0.085 |
Neg logit contributions | |
arine | -0.113 |
hess | -0.107 |
illin | -0.107 |
PF | -0.106 |
igan | -0.105 |
Token | told |
Token ID | 1297 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
� | +1.166 |
� | +1.056 |
verning | +1.029 |
Crim | +1.019 |
�� | +1.017 |
Neg logit contributions | |
arine | -1.005 |
illin | -0.945 |
hess | -0.942 |
PF | -0.938 |
igan | -0.919 |
Token | and |
Token ID | 290 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
arine | +2.780 |
PF | +2.614 |
igan | +2.583 |
illin | +2.580 |
hess | +2.576 |
Neg logit contributions | |
� | -3.312 |
� | -3.007 |
�� | -2.927 |
verning | -2.895 |
� | -2.884 |
Token | a |
Token ID | 257 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
arine | +0.455 |
hess | +0.428 |
illin | +0.426 |
PF | +0.426 |
igan | +0.421 |
Neg logit contributions | |
� | -0.525 |
� | -0.476 |
�� | -0.463 |
verning | -0.463 |
� | -0.457 |
Token | cable |
Token ID | 7862 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
arine | +0.264 |
hess | +0.248 |
illin | +0.248 |
PF | +0.247 |
igan | +0.243 |
Neg logit contributions | |
� | -0.324 |
� | -0.294 |
verning | -0.286 |
�� | -0.286 |
� | -0.283 |
Token | bundle |
Token ID | 18537 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
� | +0.084 |
� | +0.076 |
verning | +0.074 |
�� | +0.074 |
� | +0.073 |
Neg logit contributions | |
arine | -0.077 |
hess | -0.073 |
illin | -0.072 |
PF | -0.072 |
igan | -0.071 |
Token | ! |
Token ID | 0 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
arine | +0.230 |
hess | +0.216 |
illin | +0.216 |
PF | +0.215 |
igan | +0.212 |
Neg logit contributions | |
� | -0.265 |
� | -0.240 |
verning | -0.234 |
�� | -0.232 |
Crim | -0.231 |
Token | You |
Token ID | 921 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
� | +0.153 |
� | +0.138 |
verning | +0.134 |
Crim | +0.133 |
�� | +0.132 |
Neg logit contributions | |
arine | -0.149 |
hess | -0.141 |
illin | -0.141 |
PF | -0.140 |
igan | -0.138 |
Token | must |
Token ID | 1276 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
arine | +0.266 |
hess | +0.252 |
illin | +0.252 |
PF | +0.250 |
igan | +0.247 |
Neg logit contributions | |
� | -0.268 |
� | -0.241 |
verning | -0.234 |
�� | -0.233 |
Crim | -0.231 |
Token | specify |
Token ID | 11986 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
� | +2.241 |
� | +2.016 |
Crim | +1.957 |
verning | +1.956 |
� | +1.931 |
Neg logit contributions | |
arine | -2.142 |
illin | -2.047 |
hess | -2.029 |
PF | -2.004 |
igan | -1.962 |
Token | that |
Token ID | 326 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
� | +1.454 |
� | +1.307 |
Crim | +1.273 |
verning | +1.272 |
�� | +1.252 |
Neg logit contributions | |
arine | -1.456 |
hess | -1.388 |
illin | -1.387 |
PF | -1.364 |
igan | -1.352 |
Token | you |
Token ID | 345 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
� | +2.391 |
� | +2.150 |
Crim | +2.108 |
verning | +2.084 |
� | +2.079 |
Neg logit contributions | |
arine | -2.369 |
hess | -2.268 |
illin | -2.251 |
PF | -2.227 |
igan | -2.199 |
Token | want |
Token ID | 765 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
arine | +0.699 |
hess | +0.656 |
illin | +0.655 |
PF | +0.652 |
igan | +0.644 |
Neg logit contributions | |
� | -0.889 |
� | -0.808 |
verning | -0.788 |
�� | -0.785 |
Crim | -0.778 |
Token | from |
Token ID | 422 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
arine | +1.348 |
illin | +1.262 |
hess | +1.258 |
PF | +1.250 |
igan | +1.244 |
Neg logit contributions | |
� | -2.073 |
� | -1.894 |
verning | -1.854 |
�� | -1.841 |
Crim | -1.826 |
Token | home |
Token ID | 1363 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
� | +0.171 |
� | +0.144 |
verning | +0.137 |
�� | +0.136 |
Crim | +0.134 |
Neg logit contributions | |
arine | -0.349 |
hess | -0.335 |
illin | -0.334 |
PF | -0.334 |
igan | -0.330 |
Token | hours |
Token ID | 2250 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
arine | +1.463 |
hess | +1.376 |
illin | +1.376 |
PF | +1.369 |
igan | +1.360 |
Neg logit contributions | |
� | -1.755 |
� | -1.585 |
verning | -1.553 |
�� | -1.537 |
Crim | -1.523 |
Token | and |
Token ID | 290 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
arine | +0.835 |
hess | +0.783 |
illin | +0.781 |
PF | +0.781 |
igan | +0.777 |
Neg logit contributions | |
� | -0.947 |
� | -0.852 |
�� | -0.835 |
verning | -0.835 |
Crim | -0.821 |
Token | almost |
Token ID | 2048 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
arine | +1.179 |
hess | +1.106 |
illin | +1.100 |
PF | +1.100 |
igan | +1.084 |
Neg logit contributions | |
� | -1.532 |
� | -1.393 |
�� | -1.360 |
verning | -1.359 |
� | -1.343 |
Token | a |
Token ID | 257 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
arine | +1.130 |
hess | +1.068 |
illin | +1.066 |
PF | +1.061 |
igan | +1.047 |
Neg logit contributions | |
� | -1.235 |
� | -1.115 |
verning | -1.084 |
�� | -1.076 |
Crim | -1.073 |
Token | third |
Token ID | 2368 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
arine | +1.999 |
illin | +1.871 |
hess | +1.871 |
PF | +1.866 |
igan | +1.834 |
Neg logit contributions | |
� | -2.773 |
� | -2.523 |
�� | -2.473 |
verning | -2.465 |
� | -2.432 |
Token | of |
Token ID | 286 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
arine | +3.179 |
illin | +3.002 |
hess | +3.002 |
PF | +2.995 |
igan | +2.980 |
Neg logit contributions | |
� | -3.334 |
� | -2.971 |
�� | -2.960 |
verning | -2.924 |
� | -2.898 |
Token | people |
Token ID | 661 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
arine | +1.828 |
PF | +1.726 |
illin | +1.713 |
hess | +1.709 |
igan | +1.700 |
Neg logit contributions | |
� | -2.134 |
� | -1.926 |
verning | -1.893 |
�� | -1.890 |
� | -1.856 |
Token | said |
Token ID | 531 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
arine | +1.010 |
hess | +0.957 |
illin | +0.956 |
PF | +0.952 |
igan | +0.943 |
Neg logit contributions | |
� | -0.973 |
� | -0.869 |
verning | -0.846 |
�� | -0.845 |
� | -0.834 |
Token | they |
Token ID | 484 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
� | +0.480 |
� | +0.434 |
verning | +0.420 |
Crim | +0.417 |
�� | +0.417 |
Neg logit contributions | |
arine | -0.431 |
hess | -0.408 |
illin | -0.407 |
PF | -0.405 |
igan | -0.399 |
Token | Prov |
Token ID | 15946 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
� | +1.680 |
� | +1.512 |
Crim | +1.457 |
wat | +1.449 |
verning | +1.446 |
Neg logit contributions | |
arine | -1.620 |
illin | -1.524 |
hess | -1.519 |
igan | -1.493 |
PF | -1.482 |
Token | idence |
Token ID | 1704 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
� | +3.095 |
� | +2.775 |
Crim | +2.690 |
verning | +2.687 |
� | +2.678 |
Neg logit contributions | |
arine | -2.871 |
hess | -2.709 |
PF | -2.706 |
illin | -2.695 |
�� | -2.651 |
Token | is |
Token ID | 318 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
� | +0.835 |
� | +0.760 |
Crim | +0.737 |
verning | +0.736 |
�� | +0.732 |
Neg logit contributions | |
arine | -0.685 |
illin | -0.645 |
hess | -0.643 |
PF | -0.640 |
igan | -0.628 |
Token | restrained |
Token ID | 31531 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
� | +0.624 |
� | +0.565 |
verning | +0.546 |
Crim | +0.545 |
�� | +0.544 |
Neg logit contributions | |
arine | -0.530 |
hess | -0.500 |
illin | -0.499 |
PF | -0.493 |
igan | -0.487 |
Token | in |
Token ID | 287 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
� | +0.752 |
� | +0.683 |
verning | +0.662 |
Crim | +0.657 |
�� | +0.656 |
Neg logit contributions | |
arine | -0.653 |
illin | -0.613 |
PF | -0.613 |
hess | -0.613 |
igan | -0.599 |
Token | its |
Token ID | 663 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
arine | +1.288 |
hess | +1.218 |
illin | +1.215 |
PF | +1.208 |
igan | +1.200 |
Neg logit contributions | |
� | -1.365 |
� | -1.229 |
verning | -1.201 |
�� | -1.193 |
� | -1.177 |
Token | gore |
Token ID | 46835 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
arine | +0.938 |
hess | +0.876 |
illin | +0.875 |
PF | +0.870 |
igan | +0.858 |
Neg logit contributions | |
� | -1.354 |
� | -1.237 |
verning | -1.209 |
�� | -1.202 |
� | -1.193 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
arine | +0.385 |
hess | +0.362 |
illin | +0.362 |
PF | +0.360 |
igan | +0.354 |
Neg logit contributions | |
� | -0.448 |
� | -0.406 |
verning | -0.395 |
�� | -0.393 |
Crim | -0.391 |
Token | but |
Token ID | 475 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
arine | +0.690 |
hess | +0.650 |
illin | +0.649 |
PF | +0.646 |
igan | +0.637 |
Neg logit contributions | |
� | -0.801 |
� | -0.725 |
verning | -0.706 |
�� | -0.702 |
Crim | -0.697 |
Token | it |
Token ID | 340 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
� | +1.037 |
� | +0.937 |
verning | +0.909 |
Crim | +0.906 |
�� | +0.902 |
Neg logit contributions | |
arine | -0.940 |
illin | -0.887 |
hess | -0.886 |
PF | -0.883 |
igan | -0.868 |
Token | certainly |
Token ID | 3729 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
arine | +1.773 |
hess | +1.672 |
illin | +1.665 |
PF | +1.658 |
igan | +1.650 |
Neg logit contributions | |
� | -2.241 |
� | -2.028 |
�� | -1.989 |
verning | -1.987 |
Crim | -1.957 |
Token | gh |
Token ID | 456 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
arine | +0.538 |
hess | +0.512 |
illin | +0.510 |
PF | +0.506 |
igan | +0.503 |
Neg logit contributions | |
� | -0.480 |
� | -0.426 |
�� | -0.418 |
verning | -0.414 |
Crim | -0.409 |
Token | ts |
Token ID | 912 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
arine | +2.462 |
hess | +2.362 |
illin | +2.342 |
PF | +2.319 |
igan | +2.312 |
Neg logit contributions | |
� | -1.979 |
�� | -1.745 |
� | -1.734 |
verning | -1.687 |
Crim | -1.674 |
Token | . |
Token ID | 13 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
arine | +1.965 |
PF | +1.862 |
hess | +1.860 |
illin | +1.845 |
igan | +1.833 |
Neg logit contributions | |
� | -2.350 |
� | -2.129 |
�� | -2.097 |
verning | -2.070 |
Crim | -2.056 |
Token | It |
Token ID | 1026 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
arine | +2.998 |
PF | +2.873 |
illin | +2.865 |
hess | +2.841 |
igan | +2.803 |
Neg logit contributions | |
� | -3.102 |
� | -2.795 |
�� | -2.778 |
verning | -2.715 |
� | -2.669 |
Token | unleashed |
Token ID | 28136 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
arine | +1.813 |
illin | +1.712 |
hess | +1.708 |
PF | +1.695 |
igan | +1.685 |
Neg logit contributions | |
� | -1.809 |
� | -1.615 |
�� | -1.588 |
verning | -1.575 |
Crim | -1.562 |
Token | into |
Token ID | 656 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
arine | +2.040 |
illin | +1.923 |
PF | +1.914 |
hess | +1.909 |
igan | +1.884 |
Neg logit contributions | |
� | -2.441 |
� | -2.209 |
�� | -2.180 |
verning | -2.162 |
Crim | -2.130 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
arine | +2.319 |
illin | +2.194 |
hess | +2.190 |
PF | +2.187 |
igan | +2.146 |
Neg logit contributions | |
� | -2.620 |
� | -2.355 |
�� | -2.329 |
verning | -2.307 |
Crim | -2.271 |
Token | clouds |
Token ID | 15114 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
arine | +0.759 |
illin | +0.717 |
hess | +0.716 |
PF | +0.714 |
igan | +0.702 |
Neg logit contributions | |
� | -0.836 |
� | -0.753 |
�� | -0.734 |
verning | -0.732 |
� | -0.723 |
Token | of |
Token ID | 286 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
� | +0.866 |
� | +0.782 |
verning | +0.760 |
�� | +0.754 |
Crim | +0.751 |
Neg logit contributions | |
arine | -0.773 |
hess | -0.731 |
illin | -0.729 |
PF | -0.724 |
igan | -0.715 |
Token | pure |
Token ID | 5899 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
� | +1.118 |
� | +1.014 |
verning | +0.984 |
Crim | +0.975 |
�� | +0.975 |
Neg logit contributions | |
arine | -0.958 |
hess | -0.910 |
illin | -0.902 |
PF | -0.896 |
igan | -0.886 |
Token | thought |
Token ID | 1807 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
arine | +1.609 |
illin | +1.500 |
PF | +1.496 |
hess | +1.490 |
igan | +1.468 |
Neg logit contributions | |
� | -2.034 |
� | -1.845 |
verning | -1.809 |
�� | -1.803 |
� | -1.780 |
Token | vote |
Token ID | 3015 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
arine | +2.017 |
PF | +1.880 |
illin | +1.866 |
hess | +1.865 |
igan | +1.859 |
Neg logit contributions | |
� | -3.052 |
� | -2.786 |
�� | -2.757 |
verning | -2.722 |
� | -2.695 |
Token | . |
Token ID | 13 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
arine | +1.539 |
hess | +1.444 |
PF | +1.443 |
illin | +1.440 |
igan | +1.435 |
Neg logit contributions | |
� | -2.029 |
� | -1.840 |
verning | -1.802 |
�� | -1.802 |
� | -1.774 |
Token | � |
Token ID | 447 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
arine | +2.256 |
illin | +2.135 |
PF | +2.126 |
hess | +2.126 |
igan | +2.109 |
Neg logit contributions | |
� | -3.053 |
� | -2.780 |
�� | -2.748 |
verning | -2.743 |
� | -2.685 |
Token | � |
Token ID | 251 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
� | +0.803 |
� | +0.622 |
verning | +0.577 |
�� | +0.568 |
Crim | +0.558 |
Neg logit contributions | |
arine | -2.746 |
hess | -2.652 |
illin | -2.649 |
PF | -2.642 |
igan | -2.621 |
Token |
|
Token ID | 198 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
� | +0.918 |
� | +0.833 |
verning | +0.807 |
�� | +0.803 |
Crim | +0.802 |
Neg logit contributions | |
arine | -0.769 |
hess | -0.723 |
illin | -0.722 |
PF | -0.718 |
igan | -0.708 |
Token |
|
Token ID | 198 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
arine | +0.300 |
hess | +0.283 |
illin | +0.282 |
PF | +0.282 |
igan | +0.278 |
Neg logit contributions | |
� | -0.346 |
� | -0.313 |
�� | -0.305 |
verning | -0.304 |
� | -0.301 |
Token | Both |
Token ID | 10265 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
arine | +0.146 |
hess | +0.138 |
illin | +0.138 |
PF | +0.137 |
igan | +0.135 |
Neg logit contributions | |
� | -0.163 |
� | -0.147 |
verning | -0.143 |
�� | -0.143 |
Crim | -0.142 |
Token | users |
Token ID | 2985 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
� | +1.930 |
� | +1.761 |
Crim | +1.711 |
verning | +1.704 |
� | +1.699 |
Neg logit contributions | |
arine | -1.410 |
hess | -1.317 |
illin | -1.315 |
PF | -1.312 |
igan | -1.286 |
Token | say |
Token ID | 910 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
arine | +2.099 |
hess | +1.986 |
illin | +1.980 |
igan | +1.967 |
PF | +1.961 |
Neg logit contributions | |
� | -2.313 |
� | -2.067 |
�� | -2.039 |
verning | -2.025 |
� | -1.999 |
Token | they |
Token ID | 484 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
� | +2.355 |
� | +2.129 |
Crim | +2.056 |
verning | +2.036 |
� | +2.036 |
Neg logit contributions | |
arine | -2.325 |
illin | -2.193 |
PF | -2.183 |
hess | -2.179 |
igan | -2.140 |
Token | received |
Token ID | 2722 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
arine | +0.648 |
hess | +0.612 |
illin | +0.612 |
PF | +0.608 |
igan | +0.604 |
Neg logit contributions | |
� | -0.700 |
� | -0.630 |
verning | -0.614 |
�� | -0.613 |
� | -0.605 |
Token | file |
Token ID | 2393 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
� | +2.591 |
� | +2.357 |
verning | +2.318 |
� | +2.289 |
Crim | +2.288 |
Neg logit contributions | |
arine | -1.994 |
illin | -1.895 |
hess | -1.890 |
PF | -1.850 |
igan | -1.821 |
Token | is |
Token ID | 318 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
� | +2.490 |
� | +2.242 |
verning | +2.147 |
Crim | +2.143 |
� | +2.143 |
Neg logit contributions | |
arine | -2.735 |
illin | -2.592 |
hess | -2.571 |
PF | -2.570 |
igan | -2.518 |
Token | opened |
Token ID | 4721 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
� | +1.245 |
� | +1.135 |
verning | +1.099 |
� | +1.087 |
Crim | +1.087 |
Neg logit contributions | |
arine | -1.046 |
illin | -0.993 |
hess | -0.989 |
PF | -0.985 |
igan | -0.963 |
Token | in |
Token ID | 287 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
� | +1.240 |
� | +1.120 |
verning | +1.085 |
Crim | +1.076 |
�� | +1.074 |
Neg logit contributions | |
arine | -1.209 |
illin | -1.150 |
hess | -1.147 |
PF | -1.141 |
igan | -1.118 |
Token | the |
Token ID | 262 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
� | +0.731 |
� | +0.661 |
verning | +0.641 |
�� | +0.641 |
� | +0.633 |
Neg logit contributions | |
arine | -0.663 |
hess | -0.625 |
illin | -0.624 |
PF | -0.624 |
igan | -0.615 |
Token | terminal |
Token ID | 12094 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
� | +0.925 |
� | +0.839 |
verning | +0.817 |
�� | +0.812 |
Crim | +0.809 |
Neg logit contributions | |
arine | -0.760 |
hess | -0.716 |
illin | -0.714 |
PF | -0.710 |
igan | -0.700 |
Token | , |
Token ID | 11 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
� | +2.007 |
� | +1.811 |
verning | +1.752 |
Crim | +1.735 |
� | +1.735 |
Neg logit contributions | |
arine | -1.952 |
illin | -1.853 |
hess | -1.847 |
PF | -1.835 |
igan | -1.804 |
Token | you |
Token ID | 345 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
� | +3.375 |
� | +3.038 |
Crim | +2.983 |
verning | +2.952 |
� | +2.905 |
Neg logit contributions | |
arine | -3.072 |
hess | -2.953 |
illin | -2.936 |
PF | -2.891 |
�� | -2.821 |
Token | will |
Token ID | 481 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
� | +2.433 |
� | +2.189 |
verning | +2.086 |
wat | +2.072 |
Crim | +2.072 |
Neg logit contributions | |
arine | -2.742 |
hess | -2.633 |
illin | -2.606 |
PF | -2.599 |
igan | -2.545 |
Token | paste |
Token ID | 17008 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
� | +2.873 |
� | +2.597 |
verning | +2.472 |
Crim | +2.467 |
� | +2.455 |
Neg logit contributions | |
arine | -3.062 |
hess | -2.952 |
illin | -2.921 |
PF | -2.902 |
igan | -2.813 |
Token | or |
Token ID | 393 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
� | +0.625 |
� | +0.564 |
verning | +0.548 |
�� | +0.545 |
Crim | +0.542 |
Neg logit contributions | |
arine | -0.569 |
hess | -0.537 |
illin | -0.536 |
PF | -0.534 |
igan | -0.527 |
Token | and |
Token ID | 290 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
arine | +1.210 |
hess | +1.138 |
illin | +1.138 |
PF | +1.133 |
igan | +1.118 |
Neg logit contributions | |
� | -1.475 |
� | -1.338 |
verning | -1.303 |
�� | -1.300 |
� | -1.286 |
Token | helped |
Token ID | 4193 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
arine | +1.106 |
hess | +1.046 |
illin | +1.043 |
PF | +1.037 |
igan | +1.025 |
Neg logit contributions | |
� | -1.235 |
� | -1.114 |
verning | -1.088 |
�� | -1.082 |
� | -1.070 |
Token | its |
Token ID | 663 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
arine | +0.155 |
hess | +0.146 |
illin | +0.145 |
PF | +0.145 |
igan | +0.143 |
Neg logit contributions | |
� | -0.183 |
� | -0.166 |
verning | -0.161 |
�� | -0.161 |
Crim | -0.160 |
Token | supervisors |
Token ID | 36520 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
arine | +0.590 |
hess | +0.558 |
illin | +0.557 |
PF | +0.555 |
igan | +0.548 |
Neg logit contributions | |
� | -0.592 |
� | -0.532 |
verning | -0.517 |
�� | -0.514 |
Crim | -0.510 |
Token | identify |
Token ID | 5911 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
� | +1.300 |
� | +1.177 |
verning | +1.158 |
Crim | +1.146 |
�� | +1.133 |
Neg logit contributions | |
arine | -1.079 |
hess | -1.020 |
PF | -1.013 |
illin | -1.012 |
igan | -0.985 |
Token | signals |
Token ID | 10425 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
� | +0.431 |
� | +0.391 |
Crim | +0.381 |
verning | +0.380 |
�� | +0.376 |
Neg logit contributions | |
arine | -0.353 |
hess | -0.335 |
illin | -0.334 |
PF | -0.330 |
igan | -0.324 |
Token | that |
Token ID | 326 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
� | +1.175 |
� | +1.058 |
verning | +1.021 |
Crim | +1.018 |
� | +1.010 |
Neg logit contributions | |
arine | -1.077 |
hess | -1.019 |
illin | -1.018 |
PF | -1.008 |
igan | -0.990 |
Token | the |
Token ID | 262 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
� | +0.679 |
� | +0.610 |
verning | +0.591 |
Crim | +0.588 |
�� | +0.586 |
Neg logit contributions | |
arine | -0.661 |
hess | -0.628 |
illin | -0.626 |
PF | -0.621 |
igan | -0.612 |
Token | work |
Token ID | 670 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
arine | +0.604 |
hess | +0.571 |
illin | +0.569 |
PF | +0.567 |
igan | +0.559 |
Neg logit contributions | |
� | -0.654 |
� | -0.590 |
verning | -0.573 |
�� | -0.570 |
Crim | -0.567 |
Token | was |
Token ID | 373 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
� | +0.527 |
� | +0.473 |
verning | +0.461 |
�� | +0.455 |
� | +0.455 |
Neg logit contributions | |
arine | -0.512 |
hess | -0.485 |
illin | -0.482 |
PF | -0.481 |
igan | -0.474 |
Token | taking |
Token ID | 2263 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
arine | +0.628 |
hess | +0.590 |
illin | +0.589 |
PF | +0.585 |
igan | +0.575 |
Neg logit contributions | |
� | -0.850 |
� | -0.775 |
verning | -0.754 |
�� | -0.748 |
Crim | -0.748 |
Token | in |
Token ID | 287 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
� | +0.646 |
� | +0.588 |
verning | +0.572 |
�� | +0.569 |
Crim | +0.566 |
Neg logit contributions | |
arine | -0.501 |
hess | -0.471 |
illin | -0.469 |
PF | -0.467 |
igan | -0.460 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
� | +1.438 |
� | +1.304 |
verning | +1.266 |
�� | +1.261 |
Crim | +1.251 |
Neg logit contributions | |
arine | -1.245 |
illin | -1.172 |
hess | -1.172 |
PF | -1.168 |
igan | -1.147 |
Token | very |
Token ID | 845 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
� | +0.705 |
� | +0.640 |
verning | +0.622 |
�� | +0.619 |
Crim | +0.618 |
Neg logit contributions | |
arine | -0.592 |
hess | -0.556 |
illin | -0.554 |
PF | -0.552 |
igan | -0.545 |
Token | last |
Token ID | 938 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
� | +1.128 |
� | +1.027 |
verning | +0.998 |
�� | +0.991 |
Crim | +0.990 |
Neg logit contributions | |
arine | -0.918 |
illin | -0.859 |
hess | -0.858 |
PF | -0.855 |
igan | -0.844 |
Token | stage |
Token ID | 3800 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
arine | +0.534 |
hess | +0.501 |
illin | +0.500 |
PF | +0.497 |
igan | +0.489 |
Neg logit contributions | |
� | -0.729 |
� | -0.665 |
verning | -0.648 |
�� | -0.645 |
Crim | -0.641 |
Token | and |
Token ID | 290 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
� | +2.720 |
� | +2.446 |
verning | +2.366 |
�� | +2.353 |
Crim | +2.349 |
Neg logit contributions | |
arine | -2.746 |
hess | -2.595 |
illin | -2.588 |
PF | -2.573 |
igan | -2.529 |
Token | I |
Token ID | 314 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
� | +0.916 |
� | +0.829 |
verning | +0.804 |
�� | +0.799 |
Crim | +0.798 |
Neg logit contributions | |
arine | -0.799 |
illin | -0.756 |
hess | -0.756 |
PF | -0.750 |
igan | -0.740 |
Token | do |
Token ID | 466 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
� | +1.757 |
� | +1.589 |
verning | +1.527 |
Crim | +1.513 |
� | +1.509 |
Neg logit contributions | |
arine | -1.809 |
hess | -1.723 |
PF | -1.717 |
illin | -1.708 |
igan | -1.657 |
Token | agree |
Token ID | 4236 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
� | +1.091 |
� | +0.977 |
verning | +0.947 |
�� | +0.938 |
Crim | +0.932 |
Neg logit contributions | |
arine | -1.129 |
hess | -1.077 |
illin | -1.072 |
PF | -1.065 |
igan | -1.045 |
Token | some |
Token ID | 617 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
� | +2.814 |
� | +2.540 |
verning | +2.455 |
Crim | +2.454 |
wat | +2.439 |
Neg logit contributions | |
arine | -2.658 |
illin | -2.548 |
hess | -2.527 |
PF | -2.516 |
igan | -2.457 |
Token | are |
Token ID | 389 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
� | +2.241 |
� | +2.023 |
verning | +1.952 |
Crim | +1.939 |
�� | +1.939 |
Neg logit contributions | |
arine | -2.082 |
hess | -1.972 |
illin | -1.968 |
PF | -1.961 |
igan | -1.939 |
Token | always |
Token ID | 1464 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
� | +1.462 |
� | +1.330 |
verning | +1.297 |
Crim | +1.281 |
� | +1.281 |
Neg logit contributions | |
arine | -1.152 |
hess | -1.081 |
illin | -1.080 |
PF | -1.066 |
igan | -1.056 |
Token | considered |
Token ID | 3177 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
� | +2.788 |
� | +2.547 |
verning | +2.495 |
Crim | +2.479 |
� | +2.463 |
Neg logit contributions | |
arine | -1.889 |
hess | -1.765 |
illin | -1.760 |
PF | -1.717 |
igan | -1.698 |
Token | a |
Token ID | 257 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
� | +1.606 |
� | +1.454 |
verning | +1.418 |
Crim | +1.402 |
�� | +1.399 |
Neg logit contributions | |
arine | -1.398 |
illin | -1.317 |
hess | -1.316 |
PF | -1.303 |
igan | -1.284 |
Token | good |
Token ID | 922 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
� | +1.427 |
� | +1.295 |
verning | +1.265 |
Crim | +1.252 |
�� | +1.248 |
Neg logit contributions | |
arine | -1.176 |
hess | -1.108 |
illin | -1.108 |
PF | -1.091 |
igan | -1.083 |
Token | place |
Token ID | 1295 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
� | +3.097 |
� | +2.818 |
verning | +2.744 |
Crim | +2.727 |
� | +2.716 |
Neg logit contributions | |
arine | -2.415 |
hess | -2.261 |
illin | -2.255 |
PF | -2.221 |
�� | -2.167 |
Token | to |
Token ID | 284 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
� | +1.646 |
� | +1.483 |
verning | +1.435 |
�� | +1.426 |
Crim | +1.422 |
Neg logit contributions | |
arine | -1.565 |
hess | -1.477 |
illin | -1.471 |
PF | -1.470 |
igan | -1.439 |
Token | invest |
Token ID | 1325 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
� | +1.522 |
� | +1.387 |
verning | +1.354 |
Crim | +1.352 |
�� | +1.337 |
Neg logit contributions | |
arine | -1.193 |
hess | -1.122 |
illin | -1.121 |
PF | -1.104 |
igan | -1.077 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
arine | +0.840 |
hess | +0.792 |
illin | +0.792 |
PF | +0.788 |
igan | +0.783 |
Neg logit contributions | |
� | -0.958 |
� | -0.866 |
�� | -0.842 |
verning | -0.841 |
� | -0.832 |
Token | the |
Token ID | 262 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
� | +0.999 |
� | +0.904 |
verning | +0.881 |
�� | +0.873 |
Crim | +0.872 |
Neg logit contributions | |
arine | -0.879 |
illin | -0.830 |
hess | -0.830 |
PF | -0.823 |
igan | -0.812 |
Token | government |
Token ID | 1230 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
arine | +1.539 |
PF | +1.449 |
hess | +1.445 |
illin | +1.443 |
igan | +1.424 |
Neg logit contributions | |
� | -1.924 |
� | -1.746 |
�� | -1.704 |
verning | -1.703 |
� | -1.681 |
Token | bonds |
Token ID | 13100 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
arine | +0.626 |
hess | +0.592 |
illin | +0.590 |
PF | +0.588 |
igan | +0.581 |
Neg logit contributions | |
� | -0.686 |
� | -0.619 |
verning | -0.602 |
�� | -0.600 |
Crim | -0.594 |
Token |
|
Token ID | 198 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
arine | +0.165 |
hess | +0.156 |
illin | +0.156 |
PF | +0.155 |
igan | +0.153 |
Neg logit contributions | |
� | -0.188 |
� | -0.170 |
verning | -0.165 |
�� | -0.165 |
� | -0.163 |
Token | Read |
Token ID | 5569 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
arine | +1.654 |
PF | +1.576 |
hess | +1.570 |
illin | +1.565 |
igan | +1.546 |
Neg logit contributions | |
� | -1.612 |
� | -1.442 |
verning | -1.419 |
�� | -1.409 |
Crim | -1.393 |
Token | Next |
Token ID | 7406 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
arine | +1.542 |
PF | +1.469 |
illin | +1.462 |
hess | +1.459 |
igan | +1.446 |
Neg logit contributions | |
� | -1.248 |
� | -1.108 |
verning | -1.078 |
�� | -1.070 |
Crim | -1.060 |
Token |
|
Token ID | 198 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
arine | +4.046 |
illin | +3.998 |
PF | +3.917 |
igan | +3.858 |
hess | +3.810 |
Neg logit contributions | |
� | -5.732 |
�� | -5.252 |
� | -5.228 |
� | -5.138 |
verning | -5.133 |
Token |
|
Token ID | 198 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
arine | +1.986 |
PF | +1.888 |
hess | +1.877 |
igan | +1.863 |
illin | +1.859 |
Neg logit contributions | |
� | -2.721 |
�� | -2.503 |
� | -2.490 |
verning | -2.411 |
� | -2.409 |
Token | L |
Token ID | 43 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
arine | +2.359 |
PF | +2.280 |
illin | +2.240 |
hess | +2.233 |
igan | +2.226 |
Neg logit contributions | |
� | -2.575 |
� | -2.304 |
verning | -2.298 |
�� | -2.288 |
Crim | -2.238 |
Token | AT |
Token ID | 1404 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
� | +3.203 |
� | +2.912 |
wat | +2.821 |
verning | +2.806 |
� | +2.778 |
Neg logit contributions | |
arine | -2.910 |
hess | -2.795 |
illin | -2.773 |
PF | -2.752 |
�� | -2.715 |
Token | EST |
Token ID | 6465 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
arine | +1.746 |
PF | +1.563 |
illin | +1.558 |
igan | +1.557 |
hess | +1.543 |
Neg logit contributions | |
� | -4.875 |
� | -4.539 |
verning | -4.480 |
�� | -4.455 |
Crim | -4.414 |
Token | STOR |
Token ID | 46366 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
arine | +2.435 |
PF | +2.313 |
illin | +2.298 |
hess | +2.286 |
igan | +2.272 |
Neg logit contributions | |
� | -2.933 |
� | -2.638 |
verning | -2.597 |
�� | -2.587 |
� | -2.536 |
Token | IES |
Token ID | 11015 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
PF | +2.348 |
arine | +2.239 |
BG | +2.235 |
RFC | +2.218 |
igan | +2.212 |
Neg logit contributions | |
� | -3.008 |
�� | -2.711 |
� | -2.702 |
verning | -2.683 |
� | -2.601 |
Token |
|
Token ID | 198 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
arine | +2.233 |
PF | +2.108 |
hess | +2.099 |
illin | +2.091 |
igan | +2.088 |
Neg logit contributions | |
� | -2.928 |
� | -2.647 |
verning | -2.608 |
�� | -2.604 |
� | -2.564 |
Token | By |
Token ID | 2750 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
� | +0.894 |
� | +0.804 |
verning | +0.782 |
�� | +0.777 |
Crim | +0.772 |
Neg logit contributions | |
arine | -0.865 |
hess | -0.818 |
illin | -0.817 |
PF | -0.814 |
igan | -0.804 |
Token | Bill |
Token ID | 3941 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
arine | +0.642 |
hess | +0.602 |
illin | +0.602 |
PF | +0.600 |
igan | +0.591 |
Neg logit contributions | |
� | -0.822 |
� | -0.748 |
verning | -0.729 |
�� | -0.726 |
Crim | -0.720 |
Token | Clark |
Token ID | 11264 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
� | +3.201 |
Crim | +2.939 |
� | +2.883 |
� | +2.832 |
� | +2.795 |
Neg logit contributions | |
arine | -2.782 |
illin | -2.657 |
hess | -2.627 |
PF | -2.533 |
�� | -2.486 |
Token | / |
Token ID | 14 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
arine | +1.709 |
illin | +1.635 |
hess | +1.627 |
PF | +1.620 |
igan | +1.614 |
Neg logit contributions | |
� | -1.481 |
� | -1.327 |
�� | -1.285 |
verning | -1.275 |
� | -1.258 |
Token | C |
Token ID | 34 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
� | +1.670 |
� | +1.515 |
verning | +1.488 |
Crim | +1.465 |
� | +1.463 |
Neg logit contributions | |
arine | -1.317 |
hess | -1.234 |
illin | -1.211 |
igan | -1.177 |
PF | -1.176 |
Token | Q |
Token ID | 48 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
� | +1.697 |
� | +1.523 |
verning | +1.495 |
� | +1.470 |
wat | +1.464 |
Neg logit contributions | |
arine | -1.515 |
�� | -1.435 |
hess | -1.426 |
illin | -1.406 |
PF | -1.404 |
Token | Roll |
Token ID | 8299 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
� | +7.543 |
� | +6.881 |
Crim | +6.832 |
verning | +6.827 |
� | +6.713 |
Neg logit contributions | |
arine | -4.049 |
�� | -3.923 |
hess | -3.856 |
igan | -3.717 |
illin | -3.716 |
Token | Call |
Token ID | 4889 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
arine | +2.475 |
igan | +2.360 |
PF | +2.332 |
illin | +2.320 |
hess | +2.237 |
Neg logit contributions | |
� | -3.154 |
�� | -2.876 |
� | -2.875 |
verning | -2.808 |
Crim | -2.771 |
Token | ) |
Token ID | 8 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
� | +4.164 |
� | +3.668 |
Crim | +3.574 |
verning | +3.563 |
� | +3.517 |
Neg logit contributions | |
arine | -4.900 |
hess | -4.770 |
illin | -4.711 |
PF | -4.597 |
igan | -4.541 |
Token | Scott |
Token ID | 4746 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
arine | +2.442 |
PF | +2.315 |
illin | +2.299 |
igan | +2.294 |
hess | +2.289 |
Neg logit contributions | |
� | -2.867 |
� | -2.605 |
�� | -2.567 |
verning | -2.546 |
� | -2.495 |
Token | Brown |
Token ID | 4373 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
� | +1.007 |
� | +0.915 |
verning | +0.894 |
�� | +0.884 |
Crim | +0.884 |
Neg logit contributions | |
arine | -0.808 |
hess | -0.764 |
PF | -0.758 |
illin | -0.758 |
igan | -0.744 |
Token | anatomy |
Token ID | 33449 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
� | +1.632 |
� | +1.475 |
Crim | +1.438 |
verning | +1.433 |
�� | +1.428 |
Neg logit contributions | |
arine | -1.297 |
hess | -1.233 |
illin | -1.228 |
PF | -1.218 |
igan | -1.194 |
Token | and |
Token ID | 290 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
arine | +1.069 |
hess | +1.006 |
illin | +1.002 |
PF | +0.998 |
igan | +0.986 |
Neg logit contributions | |
� | -1.240 |
� | -1.123 |
verning | -1.094 |
�� | -1.090 |
� | -1.080 |
Token | be |
Token ID | 307 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
arine | +0.489 |
hess | +0.459 |
illin | +0.457 |
PF | +0.456 |
igan | +0.450 |
Neg logit contributions | |
� | -0.616 |
� | -0.561 |
verning | -0.548 |
�� | -0.545 |
Crim | -0.540 |
Token | called |
Token ID | 1444 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
arine | +2.410 |
PF | +2.261 |
hess | +2.258 |
illin | +2.249 |
igan | +2.246 |
Neg logit contributions | |
� | -2.816 |
� | -2.550 |
�� | -2.506 |
verning | -2.491 |
Crim | -2.465 |
Token | by |
Token ID | 416 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
arine | +4.421 |
igan | +4.115 |
PF | +4.107 |
hess | +4.094 |
illin | +4.067 |
Neg logit contributions | |
� | -5.209 |
� | -4.737 |
�� | -4.720 |
verning | -4.689 |
Crim | -4.553 |
Token | female |
Token ID | 4048 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
� | +2.236 |
� | +2.016 |
Crim | +1.932 |
� | +1.931 |
verning | +1.931 |
Neg logit contributions | |
arine | -2.165 |
hess | -2.061 |
illin | -2.060 |
PF | -2.041 |
igan | -2.011 |
Token | pronouns |
Token ID | 43947 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
� | +7.300 |
Crim | +6.636 |
� | +6.634 |
wat | +6.510 |
verning | +6.435 |
Neg logit contributions | |
arine | -4.824 |
illin | -4.598 |
PF | -4.465 |
hess | -4.456 |
igan | -4.342 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
� | +3.505 |
� | +3.166 |
verning | +3.039 |
Crim | +3.038 |
� | +3.038 |
Neg logit contributions | |
arine | -3.238 |
illin | -3.063 |
hess | -3.035 |
PF | -3.019 |
igan | -2.959 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
arine | +1.787 |
hess | +1.691 |
PF | +1.688 |
illin | +1.686 |
igan | +1.663 |
Neg logit contributions | |
� | -1.921 |
� | -1.733 |
verning | -1.690 |
�� | -1.689 |
� | -1.659 |
Token |
|
Token ID | 198 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
arine | +0.796 |
hess | +0.751 |
illin | +0.749 |
PF | +0.749 |
igan | +0.739 |
Neg logit contributions | |
� | -0.939 |
� | -0.852 |
�� | -0.833 |
verning | -0.827 |
� | -0.818 |
Token | Gender |
Token ID | 41394 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
arine | +1.955 |
PF | +1.880 |
hess | +1.858 |
illin | +1.842 |
igan | +1.819 |
Neg logit contributions | |
� | -2.028 |
� | -1.832 |
verning | -1.792 |
�� | -1.781 |
Crim | -1.761 |
Token | b |
Token ID | 65 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
� | +3.841 |
� | +3.441 |
wat | +3.366 |
� | +3.314 |
� | +3.308 |
Neg logit contributions | |
arine | -3.793 |
illin | -3.581 |
hess | -3.554 |
PF | -3.509 |
igan | -3.485 |
Token | ] |
Token ID | 60 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
arine | +0.843 |
hess | +0.788 |
illin | +0.783 |
PF | +0.781 |
igan | +0.775 |
Neg logit contributions | |
� | -1.278 |
� | -1.170 |
�� | -1.147 |
verning | -1.146 |
� | -1.134 |
Token | Est |
Token ID | 22362 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
� | +1.613 |
� | +1.460 |
verning | +1.413 |
Crim | +1.410 |
�� | +1.409 |
Neg logit contributions | |
arine | -1.423 |
hess | -1.335 |
illin | -1.332 |
PF | -1.314 |
igan | -1.308 |
Token | imate |
Token ID | 1920 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
� | +0.653 |
� | +0.588 |
verning | +0.571 |
�� | +0.567 |
Crim | +0.565 |
Neg logit contributions | |
arine | -0.632 |
hess | -0.598 |
illin | -0.598 |
PF | -0.597 |
igan | -0.587 |
Token | : |
Token ID | 25 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
� | +1.921 |
� | +1.757 |
Crim | +1.711 |
verning | +1.711 |
�� | +1.701 |
Neg logit contributions | |
arine | -1.258 |
hess | -1.179 |
illin | -1.176 |
PF | -1.162 |
igan | -1.141 |
Token | [/ |
Token ID | 13412 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
� | +0.501 |
� | +0.459 |
verning | +0.447 |
Crim | +0.445 |
�� | +0.445 |
Neg logit contributions | |
arine | -0.329 |
hess | -0.308 |
illin | -0.307 |
PF | -0.304 |
igan | -0.299 |
Token | b |
Token ID | 65 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
� | +4.717 |
wat | +4.195 |
� | +3.940 |
verning | +3.914 |
Crim | +3.763 |
Neg logit contributions | |
arine | -8.397 |
�� | -8.124 |
illin | -7.936 |
PF | -7.935 |
hess | -7.898 |
Token | ] |
Token ID | 60 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
arine | +0.387 |
hess | +0.360 |
PF | +0.356 |
illin | +0.356 |
igan | +0.351 |
Neg logit contributions | |
� | -0.629 |
� | -0.578 |
verning | -0.566 |
�� | -0.564 |
� | -0.559 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
arine | +0.400 |
hess | +0.377 |
illin | +0.376 |
PF | +0.376 |
igan | +0.370 |
Neg logit contributions | |
� | -0.476 |
� | -0.432 |
verning | -0.421 |
�� | -0.419 |
� | -0.415 |
Token | : |
Token ID | 25 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
arine | +2.025 |
PF | +1.916 |
hess | +1.910 |
illin | +1.910 |
igan | +1.886 |
Neg logit contributions | |
� | -2.354 |
� | -2.124 |
verning | -2.083 |
�� | -2.064 |
Crim | -2.044 |
Token | 20 |
Token ID | 1238 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
arine | +0.288 |
hess | +0.272 |
illin | +0.272 |
PF | +0.270 |
igan | +0.267 |
Neg logit contributions | |
� | -0.323 |
� | -0.291 |
verning | -0.283 |
�� | -0.282 |
Crim | -0.280 |
Token | com |
Token ID | 785 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
� | +0.150 |
� | +0.135 |
verning | +0.131 |
�� | +0.130 |
Crim | +0.129 |
Neg logit contributions | |
arine | -0.155 |
hess | -0.146 |
illin | -0.146 |
PF | -0.146 |
igan | -0.144 |
Token | and |
Token ID | 290 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
� | +2.701 |
� | +2.475 |
Crim | +2.391 |
verning | +2.367 |
�� | +2.362 |
Neg logit contributions | |
arine | -2.422 |
illin | -2.322 |
hess | -2.308 |
PF | -2.284 |
igan | -2.226 |
Token | V |
Token ID | 569 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
� | +3.860 |
� | +3.494 |
Crim | +3.439 |
verning | +3.374 |
� | +3.327 |
Neg logit contributions | |
arine | -3.628 |
illin | -3.490 |
hess | -3.477 |
PF | -3.414 |
igan | -3.364 |
Token | odka |
Token ID | 28601 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
� | +2.723 |
� | +2.470 |
verning | +2.404 |
Crim | +2.394 |
�� | +2.384 |
Neg logit contributions | |
arine | -2.347 |
hess | -2.224 |
illin | -2.187 |
PF | -2.176 |
RFC | -2.137 |
Token | O |
Token ID | 440 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
� | +1.895 |
� | +1.711 |
verning | +1.667 |
Crim | +1.659 |
�� | +1.653 |
Neg logit contributions | |
arine | -1.731 |
illin | -1.634 |
hess | -1.632 |
PF | -1.614 |
igan | -1.596 |
Token | ' |
Token ID | 6 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
� | +1.086 |
� | +0.965 |
verning | +0.936 |
�� | +0.926 |
Crim | +0.924 |
Neg logit contributions | |
arine | -1.250 |
hess | -1.190 |
illin | -1.187 |
PF | -1.181 |
igan | -1.166 |
Token | Clock |
Token ID | 44758 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
� | +6.358 |
� | +5.692 |
Crim | +5.571 |
wat | +5.520 |
verning | +5.514 |
Neg logit contributions | |
arine | -5.452 |
hess | -5.194 |
illin | -5.083 |
PF | -4.963 |
�� | -4.951 |
Token | Podcast |
Token ID | 16036 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
� | +1.608 |
� | +1.449 |
verning | +1.408 |
Crim | +1.407 |
�� | +1.396 |
Neg logit contributions | |
arine | -1.504 |
illin | -1.429 |
hess | -1.427 |
PF | -1.414 |
igan | -1.382 |
Token | . |
Token ID | 13 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
� | +3.818 |
� | +3.509 |
verning | +3.349 |
Crim | +3.342 |
�� | +3.326 |
Neg logit contributions | |
arine | -3.653 |
illin | -3.507 |
hess | -3.489 |
PF | -3.463 |
RFC | -3.352 |
Token | Author |
Token ID | 6434 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
� | +1.710 |
� | +1.543 |
Crim | +1.489 |
verning | +1.484 |
� | +1.472 |
Neg logit contributions | |
arine | -1.717 |
hess | -1.632 |
illin | -1.629 |
PF | -1.619 |
igan | -1.593 |
Token | of |
Token ID | 286 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
� | +1.388 |
� | +1.254 |
verning | +1.217 |
�� | +1.210 |
Crim | +1.203 |
Neg logit contributions | |
arine | -1.289 |
hess | -1.223 |
illin | -1.218 |
PF | -1.211 |
igan | -1.194 |
Token | bound |
Token ID | 5421 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
� | +1.373 |
� | +1.250 |
verning | +1.215 |
Crim | +1.203 |
�� | +1.202 |
Neg logit contributions | |
arine | -1.109 |
illin | -1.043 |
hess | -1.043 |
PF | -1.036 |
igan | -1.020 |
Token | only |
Token ID | 691 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
� | +1.323 |
� | +1.193 |
verning | +1.160 |
�� | +1.154 |
Crim | +1.147 |
Neg logit contributions | |
arine | -1.224 |
hess | -1.156 |
illin | -1.154 |
PF | -1.149 |
igan | -1.134 |
Token | to |
Token ID | 284 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
� | +3.316 |
� | +3.021 |
verning | +2.864 |
Crim | +2.862 |
� | +2.859 |
Neg logit contributions | |
arine | -3.729 |
illin | -3.596 |
hess | -3.595 |
PF | -3.573 |
RFC | -3.508 |
Token | make |
Token ID | 787 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
� | +1.651 |
� | +1.507 |
Crim | +1.470 |
verning | +1.468 |
� | +1.452 |
Neg logit contributions | |
arine | -1.264 |
illin | -1.199 |
hess | -1.199 |
PF | -1.179 |
igan | -1.151 |
Token | the |
Token ID | 262 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
� | +2.984 |
� | +2.692 |
Crim | +2.657 |
verning | +2.615 |
� | +2.587 |
Neg logit contributions | |
arine | -2.975 |
illin | -2.834 |
hess | -2.822 |
PF | -2.804 |
RFC | -2.738 |
Token | problem |
Token ID | 1917 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
� | +3.359 |
� | +3.079 |
Crim | +3.050 |
verning | +2.981 |
� | +2.952 |
Neg logit contributions | |
arine | -2.652 |
hess | -2.492 |
illin | -2.467 |
PF | -2.449 |
RFC | -2.392 |
Token | worse |
Token ID | 4785 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
� | +5.764 |
� | +5.100 |
Crim | +4.951 |
�� | +4.775 |
verning | +4.761 |
Neg logit contributions | |
arine | -6.634 |
hess | -6.477 |
�� | -6.347 |
illin | -6.327 |
PF | -6.286 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
� | +0.951 |
� | +0.856 |
verning | +0.831 |
�� | +0.826 |
Crim | +0.821 |
Neg logit contributions | |
arine | -0.919 |
hess | -0.869 |
illin | -0.867 |
PF | -0.864 |
igan | -0.851 |
Token |
|
Token ID | 198 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
� | +1.721 |
� | +1.540 |
Crim | +1.514 |
verning | +1.505 |
� | +1.478 |
Neg logit contributions | |
arine | -1.807 |
hess | -1.710 |
illin | -1.707 |
PF | -1.686 |
igan | -1.659 |
Token |
|
Token ID | 198 |
Feature activation | -2.78e-03 |
Pos logit contributions | |
� | +0.617 |
� | +0.556 |
verning | +0.542 |
Crim | +0.538 |
� | +0.533 |
Neg logit contributions | |
arine | -0.580 |
hess | -0.547 |
illin | -0.547 |
PF | -0.542 |
igan | -0.534 |
Token | With |
Token ID | 3152 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
� | +0.018 |
� | +0.016 |
verning | +0.016 |
�� | +0.016 |
Crim | +0.016 |
Neg logit contributions | |
arine | -0.017 |
hess | -0.016 |
illin | -0.016 |
PF | -0.016 |
igan | -0.016 |