Token | transmission |
Token ID | 11478 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
irtual | +2.582 |
� | +2.525 |
Reply | +2.509 |
roll | +2.383 |
Stra | +2.313 |
Neg logit contributions | |
merce | -2.677 |
bour | -2.549 |
onial | -2.538 |
agher | -2.316 |
otor | -2.276 |
Token | of |
Token ID | 286 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
merce | +1.419 |
bour | +1.395 |
onial | +1.387 |
otor | +1.270 |
agher | +1.262 |
Neg logit contributions | |
irtual | -1.057 |
� | -1.015 |
Reply | -1.011 |
roll | -0.938 |
Stra | -0.925 |
Token | criminal |
Token ID | 4301 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
merce | +0.928 |
bour | +0.908 |
onial | +0.903 |
otor | +0.821 |
agher | +0.817 |
Neg logit contributions | |
irtual | -0.821 |
� | -0.793 |
Reply | -0.791 |
roll | -0.739 |
Stra | -0.726 |
Token | convictions |
Token ID | 19131 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
merce | +1.959 |
bour | +1.901 |
onial | +1.891 |
otor | +1.705 |
agher | +1.689 |
Neg logit contributions | |
irtual | -2.087 |
� | -2.023 |
Reply | -2.016 |
roll | -1.900 |
Stra | -1.871 |
Token | . |
Token ID | 764 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
merce | +0.511 |
bour | +0.497 |
onial | +0.494 |
otor | +0.452 |
agher | +0.451 |
Neg logit contributions | |
irtual | -0.402 |
� | -0.389 |
Reply | -0.387 |
roll | -0.361 |
Stra | -0.355 |
Token | Crim |
Token ID | 9822 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
irtual | +0.591 |
� | +0.572 |
Reply | +0.569 |
roll | +0.535 |
Stra | +0.525 |
Neg logit contributions | |
merce | -0.653 |
bour | -0.635 |
onial | -0.631 |
otor | -0.573 |
agher | -0.572 |
Token | in |
Token ID | 259 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
onial | +5.218 |
merce | +5.193 |
bour | +5.161 |
otor | +4.681 |
agher | +4.583 |
Neg logit contributions | |
irtual | -5.513 |
� | -5.413 |
Reply | -5.335 |
roll | -4.958 |
� | -4.905 |
Token | ology |
Token ID | 1435 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
irtual | +0.564 |
� | +0.549 |
Reply | +0.545 |
roll | +0.522 |
Stra | +0.512 |
Neg logit contributions | |
merce | -0.511 |
bour | -0.494 |
onial | -0.484 |
agher | -0.437 |
otor | -0.437 |
Token | , |
Token ID | 11 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
merce | +1.429 |
bour | +1.393 |
onial | +1.389 |
otor | +1.259 |
agher | +1.258 |
Neg logit contributions | |
irtual | -1.383 |
� | -1.340 |
Reply | -1.330 |
roll | -1.251 |
Stra | -1.229 |
Token | 35 |
Token ID | 3439 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
merce | +0.114 |
bour | +0.112 |
onial | +0.111 |
otor | +0.101 |
agher | +0.100 |
Neg logit contributions | |
irtual | -0.109 |
� | -0.105 |
Reply | -0.104 |
roll | -0.098 |
Stra | -0.096 |
Token | , |
Token ID | 11 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
merce | +0.573 |
bour | +0.554 |
onial | +0.550 |
otor | +0.499 |
agher | +0.498 |
Neg logit contributions | |
irtual | -0.537 |
� | -0.522 |
Reply | -0.519 |
roll | -0.490 |
Stra | -0.482 |
Token | face |
Token ID | 1986 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
merce | +0.271 |
bour | +0.262 |
onial | +0.261 |
otor | +0.236 |
agher | +0.235 |
Neg logit contributions | |
irtual | -0.269 |
� | -0.261 |
Reply | -0.260 |
roll | -0.246 |
Stra | -0.241 |
Token | jail |
Token ID | 7356 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
merce | +1.623 |
bour | +1.561 |
onial | +1.549 |
agher | +1.394 |
otor | +1.389 |
Neg logit contributions | |
irtual | -1.836 |
� | -1.793 |
Reply | -1.779 |
roll | -1.670 |
Stra | -1.649 |
Token | sentences |
Token ID | 13439 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
merce | +3.509 |
bour | +3.418 |
onial | +3.395 |
agher | +3.076 |
otor | +3.052 |
Neg logit contributions | |
irtual | -3.295 |
� | -3.242 |
Reply | -3.194 |
roll | -2.938 |
Stra | -2.906 |
Token | if |
Token ID | 611 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
merce | +2.790 |
bour | +2.720 |
onial | +2.695 |
agher | +2.433 |
otor | +2.425 |
Neg logit contributions | |
irtual | -2.850 |
� | -2.759 |
Reply | -2.746 |
roll | -2.554 |
Stra | -2.530 |
Token | found |
Token ID | 1043 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
irtual | +0.816 |
� | +0.793 |
Reply | +0.792 |
roll | +0.759 |
rules | +0.743 |
Neg logit contributions | |
merce | -0.881 |
bour | -0.848 |
onial | -0.844 |
otor | -0.770 |
agher | -0.766 |
Token | guilty |
Token ID | 6717 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
merce | +1.296 |
bour | +1.252 |
onial | +1.249 |
agher | +1.100 |
otor | +1.088 |
Neg logit contributions | |
irtual | -1.857 |
� | -1.799 |
Reply | -1.787 |
roll | -1.690 |
Stra | -1.673 |
Token | of |
Token ID | 286 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
merce | +4.985 |
bour | +4.824 |
onial | +4.814 |
agher | +4.290 |
otor | +4.256 |
Neg logit contributions | |
irtual | -5.723 |
� | -5.545 |
Reply | -5.434 |
roll | -5.067 |
Stra | -5.012 |
Token | any |
Token ID | 597 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
merce | +0.558 |
bour | +0.537 |
onial | +0.534 |
otor | +0.475 |
agher | +0.474 |
Neg logit contributions | |
irtual | -0.716 |
� | -0.699 |
Reply | -0.696 |
roll | -0.665 |
Stra | -0.653 |
Token | wrongdoing |
Token ID | 25013 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
irtual | +0.210 |
Reply | +0.205 |
� | +0.205 |
roll | +0.198 |
Stra | +0.194 |
Neg logit contributions | |
merce | -0.122 |
bour | -0.116 |
onial | -0.116 |
agher | -0.101 |
otor | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
merce | +2.803 |
bour | +2.714 |
onial | +2.713 |
otor | +2.430 |
agher | +2.422 |
Neg logit contributions | |
irtual | -3.095 |
� | -3.004 |
Reply | -2.981 |
roll | -2.808 |
Stra | -2.773 |
Token |
|
Token ID | 198 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
merce | +0.831 |
bour | +0.806 |
onial | +0.803 |
otor | +0.733 |
agher | +0.731 |
Neg logit contributions | |
irtual | -0.660 |
� | -0.638 |
Reply | -0.635 |
roll | -0.596 |
Stra | -0.584 |
Token | damn |
Token ID | 12270 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
irtual | +0.938 |
� | +0.909 |
Reply | +0.905 |
roll | +0.851 |
Stra | +0.836 |
Neg logit contributions | |
merce | -1.026 |
bour | -0.995 |
onial | -0.989 |
otor | -0.898 |
agher | -0.897 |
Token | cle |
Token ID | 1190 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
irtual | +0.535 |
� | +0.518 |
Reply | +0.516 |
roll | +0.485 |
Stra | +0.477 |
Neg logit contributions | |
merce | -0.585 |
bour | -0.568 |
onial | -0.565 |
otor | -0.513 |
agher | -0.512 |
Token | ats |
Token ID | 1381 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
irtual | +1.233 |
Reply | +1.185 |
� | +1.184 |
roll | +1.144 |
Stra | +1.118 |
Neg logit contributions | |
merce | -0.940 |
bour | -0.894 |
onial | -0.889 |
otor | -0.791 |
agher | -0.783 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
merce | +1.291 |
bour | +1.253 |
onial | +1.247 |
otor | +1.131 |
agher | +1.131 |
Neg logit contributions | |
irtual | -1.181 |
� | -1.143 |
Reply | -1.137 |
roll | -1.068 |
Stra | -1.051 |
Token | Conf |
Token ID | 7326 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
irtual | +0.260 |
� | +0.249 |
Reply | +0.247 |
roll | +0.231 |
Stra | +0.226 |
Neg logit contributions | |
merce | -0.350 |
bour | -0.342 |
onial | -0.339 |
otor | -0.312 |
agher | -0.311 |
Token | ession |
Token ID | 2521 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
irtual | +0.218 |
� | +0.211 |
Reply | +0.210 |
roll | +0.196 |
Stra | +0.194 |
Neg logit contributions | |
merce | -0.248 |
bour | -0.241 |
onial | -0.240 |
otor | -0.219 |
agher | -0.218 |
Token | time |
Token ID | 640 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
merce | +4.943 |
onial | +4.881 |
bour | +4.866 |
agher | +4.403 |
otor | +4.337 |
Neg logit contributions | |
irtual | -5.635 |
Reply | -5.362 |
� | -5.169 |
roll | -4.924 |
Stra | -4.807 |
Token | : |
Token ID | 25 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
merce | +1.043 |
bour | +1.014 |
onial | +1.008 |
agher | +0.914 |
otor | +0.913 |
Neg logit contributions | |
irtual | -0.974 |
� | -0.939 |
Reply | -0.935 |
roll | -0.877 |
Stra | -0.864 |
Token | We |
Token ID | 775 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
merce | +0.177 |
bour | +0.173 |
onial | +0.172 |
agher | +0.158 |
otor | +0.158 |
Neg logit contributions | |
irtual | -0.136 |
� | -0.131 |
Reply | -0.130 |
roll | -0.121 |
Stra | -0.118 |
Token | don |
Token ID | 836 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
merce | +0.273 |
bour | +0.266 |
onial | +0.264 |
otor | +0.242 |
agher | +0.241 |
Neg logit contributions | |
irtual | -0.213 |
� | -0.206 |
Reply | -0.205 |
roll | -0.191 |
Stra | -0.187 |
Token | 't |
Token ID | 470 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
irtual | +0.529 |
� | +0.504 |
Reply | +0.500 |
roll | +0.469 |
Stra | +0.461 |
Neg logit contributions | |
merce | -0.569 |
bour | -0.563 |
onial | -0.555 |
otor | -0.507 |
agher | -0.505 |
Token | , |
Token ID | 11 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
merce | +3.499 |
bour | +3.434 |
onial | +3.403 |
otor | +3.135 |
agher | +3.121 |
Neg logit contributions | |
irtual | -3.184 |
� | -3.125 |
Reply | -3.119 |
Stra | -2.827 |
roll | -2.826 |
Token | 57 |
Token ID | 7632 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
merce | +0.813 |
bour | +0.802 |
onial | +0.794 |
otor | +0.723 |
agher | +0.721 |
Neg logit contributions | |
irtual | -0.790 |
� | -0.760 |
Reply | -0.755 |
roll | -0.708 |
Stra | -0.691 |
Token | , |
Token ID | 11 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
merce | +1.188 |
bour | +1.159 |
onial | +1.150 |
otor | +1.040 |
agher | +1.033 |
Neg logit contributions | |
irtual | -1.283 |
� | -1.244 |
Reply | -1.233 |
roll | -1.162 |
Stra | -1.147 |
Token | was |
Token ID | 373 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
merce | +0.176 |
bour | +0.172 |
onial | +0.171 |
otor | +0.157 |
agher | +0.156 |
Neg logit contributions | |
irtual | -0.132 |
� | -0.127 |
Reply | -0.127 |
roll | -0.118 |
Stra | -0.116 |
Token | found |
Token ID | 1043 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
irtual | +0.561 |
� | +0.546 |
Reply | +0.544 |
roll | +0.518 |
Stra | +0.510 |
Neg logit contributions | |
merce | -0.417 |
bour | -0.401 |
onial | -0.398 |
agher | -0.352 |
otor | -0.352 |
Token | guilty |
Token ID | 6717 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
merce | +1.413 |
bour | +1.369 |
onial | +1.365 |
otor | +1.223 |
agher | +1.215 |
Neg logit contributions | |
irtual | -1.758 |
� | -1.703 |
Reply | -1.696 |
roll | -1.600 |
Stra | -1.576 |
Token | of |
Token ID | 286 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
merce | +5.381 |
onial | +5.267 |
bour | +5.235 |
agher | +4.733 |
otor | +4.722 |
Neg logit contributions | |
irtual | -5.011 |
� | -4.739 |
Reply | -4.729 |
roll | -4.311 |
Stra | -4.263 |
Token | driving |
Token ID | 5059 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
merce | +0.993 |
bour | +0.966 |
onial | +0.961 |
otor | +0.874 |
agher | +0.869 |
Neg logit contributions | |
irtual | -0.951 |
� | -0.922 |
Reply | -0.919 |
roll | -0.860 |
Stra | -0.847 |
Token | drunk |
Token ID | 10785 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
merce | +0.952 |
bour | +0.926 |
onial | +0.921 |
otor | +0.842 |
agher | +0.840 |
Neg logit contributions | |
irtual | -0.784 |
� | -0.758 |
Reply | -0.755 |
roll | -0.704 |
Stra | -0.693 |
Token | and |
Token ID | 290 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
merce | +1.620 |
bour | +1.577 |
onial | +1.569 |
otor | +1.436 |
agher | +1.431 |
Neg logit contributions | |
irtual | -1.300 |
� | -1.255 |
Reply | -1.250 |
roll | -1.164 |
Stra | -1.147 |
Token | crashing |
Token ID | 21899 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
merce | +0.434 |
bour | +0.421 |
onial | +0.419 |
otor | +0.380 |
agher | +0.378 |
Neg logit contributions | |
irtual | -0.430 |
� | -0.416 |
Reply | -0.415 |
roll | -0.389 |
Stra | -0.383 |
Token |
|
Token ID | 198 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
merce | +0.007 |
bour | +0.007 |
onial | +0.006 |
otor | +0.006 |
agher | +0.006 |
Neg logit contributions | |
irtual | -0.005 |
� | -0.005 |
Reply | -0.005 |
roll | -0.004 |
Stra | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
irtual | +0.333 |
� | +0.318 |
Reply | +0.315 |
roll | +0.293 |
Stra | +0.285 |
Neg logit contributions | |
merce | -0.544 |
bour | -0.532 |
onial | -0.528 |
otor | -0.488 |
agher | -0.487 |
Token | excerpt |
Token ID | 20911 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
irtual | +0.587 |
� | +0.566 |
Reply | +0.562 |
roll | +0.524 |
Stra | +0.513 |
Neg logit contributions | |
merce | -0.824 |
bour | -0.802 |
onial | -0.798 |
otor | -0.733 |
agher | -0.731 |
Token | from |
Token ID | 422 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
irtual | +1.682 |
� | +1.644 |
Reply | +1.631 |
roll | +1.526 |
Stra | +1.499 |
Neg logit contributions | |
merce | -2.190 |
bour | -2.106 |
onial | -2.093 |
otor | -1.922 |
agher | -1.915 |
Token | Conf |
Token ID | 7326 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
irtual | +0.533 |
� | +0.516 |
Reply | +0.513 |
roll | +0.480 |
Stra | +0.471 |
Neg logit contributions | |
merce | -0.697 |
bour | -0.677 |
onial | -0.674 |
otor | -0.617 |
agher | -0.616 |
Token | ession |
Token ID | 2521 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
irtual | +0.220 |
� | +0.215 |
Reply | +0.212 |
roll | +0.195 |
Stra | +0.193 |
Neg logit contributions | |
merce | -0.323 |
bour | -0.315 |
onial | -0.314 |
otor | -0.289 |
agher | -0.288 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
bour | +5.261 |
merce | +5.256 |
onial | +5.202 |
agher | +4.789 |
otor | +4.742 |
Neg logit contributions | |
irtual | -4.625 |
� | -4.375 |
Reply | -4.360 |
roll | -4.124 |
Stra | -4.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
bour | +0.658 |
merce | +0.646 |
onial | +0.641 |
otor | +0.588 |
agher | +0.586 |
Neg logit contributions | |
irtual | -0.614 |
� | -0.571 |
Reply | -0.561 |
roll | -0.522 |
rules | -0.515 |
Token | - |
Token ID | 12 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
merce | +0.489 |
bour | +0.480 |
onial | +0.476 |
otor | +0.440 |
agher | +0.438 |
Neg logit contributions | |
irtual | -0.306 |
� | -0.291 |
Reply | -0.287 |
roll | -0.268 |
Stra | -0.260 |
Token | and |
Token ID | 290 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
merce | +0.377 |
bour | +0.367 |
onial | +0.365 |
agher | +0.332 |
otor | +0.332 |
Neg logit contributions | |
irtual | -0.324 |
� | -0.312 |
Reply | -0.310 |
roll | -0.292 |
Stra | -0.286 |
Token | Herman |
Token ID | 25028 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
irtual | +0.440 |
� | +0.425 |
Reply | +0.423 |
roll | +0.396 |
Stra | +0.389 |
Neg logit contributions | |
merce | -0.546 |
bour | -0.531 |
onial | -0.528 |
otor | -0.482 |
agher | -0.481 |
Token | McCarthy |
Token ID | 18751 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
irtual | +0.007 |
� | +0.007 |
Reply | +0.007 |
roll | +0.007 |
Stra | +0.007 |
Neg logit contributions | |
merce | -0.008 |
bour | -0.008 |
onial | -0.008 |
otor | -0.007 |
agher | -0.007 |
Token | will |
Token ID | 481 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
irtual | +0.613 |
� | +0.594 |
Reply | +0.589 |
roll | +0.550 |
Stra | +0.534 |
Neg logit contributions | |
merce | -0.946 |
bour | -0.920 |
onial | -0.914 |
otor | -0.840 |
agher | -0.839 |
Token | be |
Token ID | 307 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
merce | +0.751 |
bour | +0.730 |
onial | +0.726 |
otor | +0.662 |
agher | +0.660 |
Neg logit contributions | |
irtual | -0.630 |
� | -0.610 |
Reply | -0.606 |
roll | -0.568 |
Stra | -0.558 |
Token | found |
Token ID | 1043 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
irtual | +0.560 |
� | +0.542 |
Reply | +0.540 |
roll | +0.506 |
Stra | +0.497 |
Neg logit contributions | |
merce | -0.678 |
bour | -0.658 |
onial | -0.654 |
otor | -0.597 |
agher | -0.595 |
Token | not |
Token ID | 407 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
merce | +0.459 |
bour | +0.445 |
onial | +0.444 |
agher | +0.402 |
otor | +0.400 |
Neg logit contributions | |
irtual | -0.454 |
� | -0.440 |
Reply | -0.437 |
roll | -0.411 |
Stra | -0.404 |
Token | guilty |
Token ID | 6717 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
irtual | +0.402 |
� | +0.392 |
Reply | +0.390 |
roll | +0.371 |
Stra | +0.366 |
Neg logit contributions | |
merce | -0.296 |
bour | -0.285 |
onial | -0.283 |
otor | -0.251 |
agher | -0.250 |
Token | in |
Token ID | 287 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
merce | +5.215 |
bour | +5.075 |
onial | +5.059 |
agher | +4.572 |
otor | +4.539 |
Neg logit contributions | |
irtual | -4.826 |
� | -4.669 |
Reply | -4.571 |
roll | -4.271 |
rules | -4.226 |
Token | the |
Token ID | 262 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
merce | +0.524 |
bour | +0.507 |
onial | +0.504 |
otor | +0.459 |
agher | +0.456 |
Neg logit contributions | |
irtual | -0.469 |
� | -0.454 |
Reply | -0.452 |
roll | -0.427 |
Stra | -0.418 |
Token | upcoming |
Token ID | 7865 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
merce | +0.673 |
bour | +0.652 |
onial | +0.648 |
otor | +0.586 |
agher | +0.585 |
Neg logit contributions | |
irtual | -0.656 |
� | -0.637 |
Reply | -0.634 |
roll | -0.598 |
Stra | -0.588 |
Token | trial |
Token ID | 4473 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
irtual | +1.569 |
� | +1.537 |
Reply | +1.533 |
roll | +1.470 |
Stra | +1.451 |
Neg logit contributions | |
merce | -0.929 |
bour | -0.891 |
onial | -0.875 |
otor | -0.764 |
agher | -0.761 |
Token | scheduled |
Token ID | 7530 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
merce | +3.187 |
onial | +3.113 |
bour | +3.105 |
agher | +2.811 |
otor | +2.799 |
Neg logit contributions | |
irtual | -3.180 |
� | -3.074 |
Reply | -3.038 |
roll | -2.833 |
Stra | -2.825 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-04 |
Pos logit contributions | |
irtual | +0.525 |
� | +0.511 |
Reply | +0.509 |
roll | +0.480 |
Stra | +0.471 |
Neg logit contributions | |
merce | -0.549 |
bour | -0.530 |
onial | -0.527 |
otor | -0.477 |
agher | -0.476 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
irtual | +0.000 |
� | +0.000 |
Reply | +0.000 |
roll | +0.000 |
Stra | +0.000 |
Neg logit contributions | |
merce | -0.001 |
bour | -0.001 |
onial | -0.001 |
agher | -0.001 |
otor | -0.001 |
Token | Abstract |
Token ID | 23839 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
irtual | +0.695 |
� | +0.672 |
Reply | +0.670 |
roll | +0.619 |
Stra | +0.607 |
Neg logit contributions | |
merce | -1.133 |
bour | -1.100 |
onial | -1.097 |
otor | -1.012 |
agher | -1.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
merce | +2.112 |
bour | +2.069 |
onial | +2.053 |
otor | +1.886 |
agher | +1.877 |
Neg logit contributions | |
irtual | -1.699 |
� | -1.629 |
Reply | -1.626 |
roll | -1.519 |
Stra | -1.483 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
bour | +0.264 |
merce | +0.261 |
onial | +0.259 |
otor | +0.237 |
agher | +0.236 |
Neg logit contributions | |
irtual | -0.240 |
� | -0.224 |
Reply | -0.221 |
roll | -0.207 |
rules | -0.202 |
Token | Background |
Token ID | 21756 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
merce | +0.315 |
bour | +0.308 |
onial | +0.306 |
otor | +0.281 |
agher | +0.280 |
Neg logit contributions | |
irtual | -0.216 |
� | -0.207 |
Reply | -0.206 |
roll | -0.192 |
Stra | -0.187 |
Token | Depression |
Token ID | 22483 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
bour | +5.226 |
merce | +5.216 |
onial | +5.157 |
otor | +4.807 |
agher | +4.695 |
Neg logit contributions | |
irtual | -4.702 |
Reply | -4.430 |
� | -4.382 |
roll | -4.093 |
rules | -4.022 |
Token | presents |
Token ID | 10969 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
merce | +1.023 |
bour | +1.001 |
onial | +1.001 |
otor | +0.919 |
agher | +0.909 |
Neg logit contributions | |
irtual | -0.742 |
� | -0.711 |
Reply | -0.709 |
roll | -0.657 |
Stra | -0.644 |
Token | a |
Token ID | 257 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
irtual | +1.064 |
� | +1.036 |
Reply | +1.029 |
roll | +0.965 |
Stra | +0.947 |
Neg logit contributions | |
merce | -1.291 |
bour | -1.253 |
onial | -1.244 |
agher | -1.137 |
otor | -1.135 |
Token | significant |
Token ID | 2383 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
merce | +0.126 |
bour | +0.122 |
onial | +0.122 |
otor | +0.110 |
agher | +0.110 |
Neg logit contributions | |
irtual | -0.123 |
� | -0.119 |
Reply | -0.119 |
roll | -0.112 |
Stra | -0.110 |
Token | burden |
Token ID | 10538 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
merce | +0.725 |
bour | +0.704 |
onial | +0.701 |
otor | +0.640 |
agher | +0.638 |
Neg logit contributions | |
irtual | -0.606 |
� | -0.586 |
Reply | -0.583 |
roll | -0.546 |
Stra | -0.537 |
Token | her |
Token ID | 607 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
merce | +0.024 |
bour | +0.023 |
onial | +0.023 |
agher | +0.021 |
otor | +0.020 |
Neg logit contributions | |
irtual | -0.021 |
� | -0.020 |
Reply | -0.020 |
roll | -0.019 |
Stra | -0.019 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
merce | +0.836 |
bour | +0.811 |
onial | +0.806 |
otor | +0.714 |
agher | +0.711 |
Neg logit contributions | |
irtual | -1.131 |
� | -1.100 |
Reply | -1.098 |
roll | -1.042 |
Stra | -1.028 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
merce | +0.375 |
bour | +0.361 |
onial | +0.360 |
agher | +0.325 |
otor | +0.325 |
Neg logit contributions | |
irtual | -0.354 |
� | -0.344 |
Reply | -0.341 |
roll | -0.323 |
Stra | -0.316 |
Token |
|
Token ID | 198 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
merce | +0.670 |
bour | +0.647 |
onial | +0.646 |
otor | +0.590 |
agher | +0.588 |
Neg logit contributions | |
irtual | -0.482 |
� | -0.468 |
Reply | -0.465 |
roll | -0.435 |
Stra | -0.426 |
Token |
|
Token ID | 198 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
bour | +1.187 |
onial | +1.145 |
merce | +1.142 |
otor | +1.054 |
agher | +1.049 |
Neg logit contributions | |
irtual | -1.162 |
� | -1.065 |
Reply | -1.046 |
roll | -0.972 |
rules | -0.958 |
Token | Det |
Token ID | 11242 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
merce | +1.028 |
bour | +1.011 |
onial | +1.001 |
otor | +0.922 |
agher | +0.919 |
Neg logit contributions | |
irtual | -0.728 |
� | -0.695 |
Reply | -0.687 |
roll | -0.642 |
Stra | -0.626 |
Token | Sgt |
Token ID | 22925 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
merce | +5.754 |
onial | +5.753 |
bour | +5.748 |
otor | +5.302 |
agher | +5.216 |
Neg logit contributions | |
irtual | -4.087 |
� | -4.002 |
Reply | -3.970 |
Stra | -3.583 |
roll | -3.554 |
Token | Ronnie |
Token ID | 40892 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
merce | +2.891 |
bour | +2.859 |
onial | +2.851 |
otor | +2.612 |
agher | +2.608 |
Neg logit contributions | |
irtual | -2.144 |
Reply | -2.074 |
� | -2.074 |
roll | -1.887 |
Stra | -1.868 |
Token | Payne |
Token ID | 32788 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
merce | +3.488 |
bour | +3.478 |
onial | +3.419 |
agher | +3.143 |
otor | +3.124 |
Neg logit contributions | |
irtual | -3.255 |
� | -3.117 |
Reply | -3.110 |
roll | -2.858 |
rules | -2.826 |
Token | asked |
Token ID | 1965 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
merce | +1.024 |
bour | +1.000 |
onial | +0.993 |
otor | +0.909 |
agher | +0.908 |
Neg logit contributions | |
irtual | -0.817 |
� | -0.789 |
Reply | -0.784 |
roll | -0.731 |
Stra | -0.720 |
Token | anyone |
Token ID | 2687 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
merce | +1.016 |
bour | +0.993 |
onial | +0.985 |
otor | +0.900 |
agher | +0.899 |
Neg logit contributions | |
irtual | -0.850 |
� | -0.819 |
Reply | -0.818 |
roll | -0.761 |
Stra | -0.751 |
Token | to |
Token ID | 284 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
irtual | +0.472 |
� | +0.455 |
Reply | +0.452 |
roll | +0.420 |
Stra | +0.412 |
Neg logit contributions | |
merce | -0.677 |
bour | -0.658 |
onial | -0.655 |
otor | -0.602 |
agher | -0.601 |
Token | call |
Token ID | 869 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
merce | +0.161 |
bour | +0.156 |
onial | +0.155 |
otor | +0.141 |
agher | +0.141 |
Neg logit contributions | |
irtual | -0.147 |
� | -0.142 |
Reply | -0.141 |
roll | -0.133 |
Stra | -0.130 |
Token | NYPD |
Token ID | 27615 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
merce | +0.309 |
bour | +0.300 |
onial | +0.298 |
otor | +0.270 |
agher | +0.269 |
Neg logit contributions | |
irtual | -0.297 |
� | -0.288 |
Reply | -0.286 |
roll | -0.270 |
Stra | -0.265 |
Token | Crime |
Token ID | 10003 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
merce | +2.544 |
bour | +2.515 |
onial | +2.489 |
otor | +2.257 |
agher | +2.245 |
Neg logit contributions | |
irtual | -2.521 |
� | -2.431 |
Reply | -2.420 |
roll | -2.260 |
rules | -2.234 |
Token | St |
Token ID | 520 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
merce | +1.650 |
bour | +1.631 |
onial | +1.603 |
otor | +1.465 |
agher | +1.449 |
Neg logit contributions | |
irtual | -1.663 |
� | -1.617 |
Reply | -1.599 |
roll | -1.517 |
rules | -1.485 |
Token | oppers |
Token ID | 37186 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
irtual | +0.369 |
� | +0.360 |
Reply | +0.359 |
roll | +0.341 |
Stra | +0.337 |
Neg logit contributions | |
merce | -0.245 |
bour | -0.236 |
onial | -0.234 |
otor | -0.206 |
agher | -0.205 |
Token | at |
Token ID | 379 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
merce | +4.782 |
bour | +4.742 |
onial | +4.673 |
agher | +4.250 |
otor | +4.235 |
Neg logit contributions | |
irtual | -4.722 |
� | -4.542 |
Reply | -4.521 |
roll | -4.208 |
rules | -4.139 |
Token | ( |
Token ID | 357 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
merce | +0.483 |
bour | +0.469 |
onial | +0.466 |
otor | +0.424 |
agher | +0.423 |
Neg logit contributions | |
irtual | -0.424 |
� | -0.410 |
Reply | -0.408 |
roll | -0.383 |
Stra | -0.376 |
Token | 800 |
Token ID | 7410 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
merce | +0.521 |
bour | +0.512 |
onial | +0.509 |
otor | +0.469 |
agher | +0.467 |
Neg logit contributions | |
irtual | -0.336 |
� | -0.322 |
Reply | -0.320 |
roll | -0.294 |
Stra | -0.286 |
Token | ) |
Token ID | 8 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
merce | +1.007 |
bour | +0.990 |
onial | +0.981 |
otor | +0.895 |
agher | +0.889 |
Neg logit contributions | |
irtual | -0.898 |
� | -0.855 |
Reply | -0.852 |
roll | -0.797 |
Stra | -0.783 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
merce | +0.529 |
bour | +0.514 |
onial | +0.511 |
otor | +0.465 |
agher | +0.464 |
Neg logit contributions | |
irtual | -0.462 |
� | -0.446 |
Reply | -0.444 |
roll | -0.417 |
Stra | -0.409 |
Token | she |
Token ID | 673 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
merce | +0.325 |
bour | +0.317 |
onial | +0.315 |
agher | +0.287 |
otor | +0.287 |
Neg logit contributions | |
irtual | -0.275 |
� | -0.265 |
Reply | -0.263 |
roll | -0.246 |
Stra | -0.242 |
Token | is |
Token ID | 318 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
merce | +0.937 |
bour | +0.911 |
onial | +0.904 |
agher | +0.830 |
otor | +0.828 |
Neg logit contributions | |
irtual | -0.736 |
� | -0.707 |
Reply | -0.704 |
roll | -0.652 |
Stra | -0.648 |
Token | � |
Token ID | 564 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
irtual | +0.122 |
� | +0.118 |
Reply | +0.117 |
roll | +0.110 |
Stra | +0.108 |
Neg logit contributions | |
merce | -0.154 |
bour | -0.149 |
onial | -0.149 |
otor | -0.136 |
agher | -0.136 |
Token | � |
Token ID | 250 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
irtual | +0.437 |
� | +0.416 |
Reply | +0.414 |
roll | +0.382 |
Stra | +0.375 |
Neg logit contributions | |
merce | -0.724 |
bour | -0.708 |
onial | -0.705 |
otor | -0.651 |
agher | -0.649 |
Token | p |
Token ID | 79 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
merce | +0.310 |
bour | +0.300 |
onial | +0.299 |
otor | +0.271 |
agher | +0.271 |
Neg logit contributions | |
irtual | -0.277 |
� | -0.269 |
Reply | -0.267 |
roll | -0.251 |
Stra | -0.247 |
Token | roud |
Token ID | 5493 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
merce | +0.877 |
onial | +0.862 |
bour | +0.861 |
otor | +0.787 |
agher | +0.784 |
Neg logit contributions | |
irtual | -0.662 |
� | -0.642 |
Reply | -0.634 |
roll | -0.587 |
Stra | -0.581 |
Token | of |
Token ID | 286 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
merce | +5.429 |
bour | +5.405 |
onial | +5.385 |
otor | +4.913 |
agher | +4.877 |
Neg logit contributions | |
irtual | -4.002 |
Reply | -3.778 |
� | -3.703 |
rules | -3.470 |
roll | -3.469 |
Token | our |
Token ID | 674 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
irtual | +0.080 |
� | +0.077 |
Reply | +0.077 |
roll | +0.072 |
Stra | +0.070 |
Neg logit contributions | |
merce | -0.094 |
bour | -0.091 |
onial | -0.091 |
otor | -0.083 |
agher | -0.083 |
Token | work |
Token ID | 670 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
irtual | +0.220 |
� | +0.213 |
Reply | +0.211 |
roll | +0.199 |
Stra | +0.195 |
Neg logit contributions | |
merce | -0.235 |
bour | -0.229 |
onial | -0.228 |
otor | -0.207 |
agher | -0.205 |
Token | to |
Token ID | 284 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
irtual | +1.395 |
� | +1.348 |
Reply | +1.340 |
roll | +1.253 |
Stra | +1.224 |
Neg logit contributions | |
merce | -1.927 |
bour | -1.872 |
onial | -1.860 |
otor | -1.706 |
agher | -1.703 |
Token | preserve |
Token ID | 12201 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
irtual | +0.642 |
� | +0.622 |
Reply | +0.618 |
roll | +0.578 |
Stra | +0.569 |
Neg logit contributions | |
merce | -0.755 |
bour | -0.734 |
onial | -0.731 |
otor | -0.667 |
agher | -0.664 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
bour | +0.223 |
merce | +0.222 |
onial | +0.219 |
otor | +0.201 |
agher | +0.200 |
Neg logit contributions | |
irtual | -0.198 |
� | -0.186 |
Reply | -0.183 |
roll | -0.171 |
Stra | -0.168 |
Token | F |
Token ID | 37 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
irtual | +0.037 |
� | +0.035 |
Reply | +0.035 |
roll | +0.032 |
Stra | +0.031 |
Neg logit contributions | |
merce | -0.057 |
bour | -0.056 |
onial | -0.056 |
otor | -0.051 |
agher | -0.051 |
Token | inance |
Token ID | 14149 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
irtual | +0.331 |
� | +0.321 |
Reply | +0.321 |
roll | +0.304 |
Stra | +0.299 |
Neg logit contributions | |
merce | -0.305 |
bour | -0.294 |
onial | -0.292 |
otor | -0.262 |
agher | -0.262 |
Token | Minister |
Token ID | 4139 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
merce | +1.364 |
bour | +1.320 |
onial | +1.307 |
agher | +1.178 |
otor | +1.172 |
Neg logit contributions | |
irtual | -1.482 |
� | -1.434 |
Reply | -1.430 |
roll | -1.338 |
Stra | -1.325 |
Token | Michael |
Token ID | 3899 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
irtual | +0.327 |
� | +0.315 |
Reply | +0.314 |
roll | +0.293 |
Stra | +0.287 |
Neg logit contributions | |
merce | -0.417 |
bour | -0.406 |
onial | -0.404 |
otor | -0.369 |
agher | -0.369 |
Token | Noon |
Token ID | 41035 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
merce | +0.867 |
bour | +0.843 |
onial | +0.835 |
agher | +0.743 |
otor | +0.741 |
Neg logit contributions | |
irtual | -1.135 |
� | -1.107 |
Reply | -1.104 |
roll | -1.042 |
Stra | -1.029 |
Token | an |
Token ID | 272 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
bour | +3.248 |
onial | +3.178 |
merce | +3.126 |
agher | +2.826 |
otor | +2.711 |
Neg logit contributions | |
irtual | -6.002 |
� | -5.921 |
Reply | -5.913 |
Stra | -5.652 |
roll | -5.619 |
Token | said |
Token ID | 531 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
irtual | +0.255 |
� | +0.246 |
Reply | +0.244 |
roll | +0.226 |
Stra | +0.224 |
Neg logit contributions | |
merce | -0.355 |
bour | -0.346 |
onial | -0.344 |
agher | -0.317 |
otor | -0.316 |
Token | on |
Token ID | 319 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
irtual | +0.122 |
� | +0.118 |
Reply | +0.117 |
roll | +0.110 |
Stra | +0.108 |
Neg logit contributions | |
merce | -0.144 |
bour | -0.140 |
onial | -0.139 |
otor | -0.127 |
agher | -0.127 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
irtual | +0.824 |
� | +0.795 |
Reply | +0.791 |
roll | +0.738 |
Stra | +0.723 |
Neg logit contributions | |
merce | -1.122 |
bour | -1.091 |
onial | -1.086 |
otor | -0.995 |
agher | -0.993 |
Token | that |
Token ID | 326 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
merce | +0.489 |
bour | +0.475 |
onial | +0.472 |
otor | +0.431 |
agher | +0.430 |
Neg logit contributions | |
irtual | -0.418 |
� | -0.405 |
Reply | -0.402 |
roll | -0.377 |
Stra | -0.371 |
Token | conventional |
Token ID | 10224 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
merce | +0.240 |
bour | +0.232 |
onial | +0.231 |
otor | +0.208 |
agher | +0.208 |
Neg logit contributions | |
irtual | -0.244 |
� | -0.236 |
Reply | -0.235 |
roll | -0.222 |
Stra | -0.218 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
irtual | +0.336 |
� | +0.325 |
Reply | +0.324 |
roll | +0.304 |
Stra | +0.299 |
Neg logit contributions | |
merce | -0.356 |
bour | -0.345 |
onial | -0.343 |
otor | -0.311 |
agher | -0.311 |
Token | It |
Token ID | 632 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
merce | +0.279 |
bour | +0.276 |
onial | +0.272 |
otor | +0.250 |
agher | +0.250 |
Neg logit contributions | |
irtual | -0.230 |
� | -0.217 |
Reply | -0.216 |
roll | -0.203 |
rules | -0.197 |
Token | is |
Token ID | 318 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
irtual | +0.469 |
� | +0.450 |
Reply | +0.447 |
roll | +0.413 |
Stra | +0.405 |
Neg logit contributions | |
merce | -0.765 |
bour | -0.745 |
onial | -0.742 |
otor | -0.684 |
agher | -0.684 |
Token | no |
Token ID | 645 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
merce | +0.352 |
bour | +0.343 |
onial | +0.341 |
otor | +0.311 |
agher | +0.310 |
Neg logit contributions | |
irtual | -0.289 |
� | -0.279 |
Reply | -0.278 |
roll | -0.260 |
Stra | -0.255 |
Token | different |
Token ID | 1180 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
irtual | +0.148 |
� | +0.144 |
Reply | +0.143 |
roll | +0.134 |
Stra | +0.133 |
Neg logit contributions | |
merce | -0.166 |
bour | -0.160 |
onial | -0.160 |
otor | -0.145 |
agher | -0.144 |
Token | than |
Token ID | 621 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
merce | +4.986 |
onial | +4.868 |
bour | +4.777 |
agher | +4.379 |
otor | +4.355 |
Neg logit contributions | |
irtual | -4.226 |
Reply | -4.072 |
� | -4.046 |
roll | -3.801 |
Stra | -3.761 |
Token | when |
Token ID | 618 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
merce | +1.889 |
bour | +1.844 |
onial | +1.829 |
agher | +1.668 |
otor | +1.650 |
Neg logit contributions | |
irtual | -1.807 |
� | -1.740 |
Reply | -1.723 |
roll | -1.621 |
Stra | -1.591 |
Token | I |
Token ID | 314 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
merce | +0.146 |
bour | +0.142 |
onial | +0.141 |
otor | +0.128 |
agher | +0.128 |
Neg logit contributions | |
irtual | -0.129 |
� | -0.125 |
Reply | -0.124 |
roll | -0.116 |
Stra | -0.114 |
Token | do |
Token ID | 466 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
merce | +0.927 |
bour | +0.902 |
onial | +0.897 |
otor | +0.820 |
agher | +0.819 |
Neg logit contributions | |
irtual | -0.738 |
� | -0.719 |
Reply | -0.709 |
roll | -0.660 |
Stra | -0.653 |
Token | a |
Token ID | 257 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
merce | +1.278 |
bour | +1.237 |
onial | +1.231 |
otor | +1.121 |
agher | +1.120 |
Neg logit contributions | |
irtual | -1.130 |
� | -1.097 |
Reply | -1.086 |
roll | -1.021 |
Stra | -1.004 |
Token | Commission |
Token ID | 4513 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
irtual | +0.143 |
� | +0.139 |
Reply | +0.139 |
roll | +0.131 |
Stra | +0.129 |
Neg logit contributions | |
merce | -0.142 |
bour | -0.137 |
onial | -0.136 |
otor | -0.123 |
agher | -0.123 |
Token | can |
Token ID | 460 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
merce | +1.206 |
bour | +1.173 |
onial | +1.164 |
agher | +1.075 |
otor | +1.072 |
Neg logit contributions | |
irtual | -0.800 |
� | -0.771 |
Reply | -0.763 |
roll | -0.697 |
Stra | -0.692 |
Token | fine |
Token ID | 3734 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
merce | +0.571 |
bour | +0.554 |
onial | +0.551 |
otor | +0.502 |
agher | +0.501 |
Neg logit contributions | |
irtual | -0.488 |
� | -0.472 |
Reply | -0.470 |
roll | -0.442 |
Stra | -0.433 |
Token | companies |
Token ID | 2706 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
merce | +1.190 |
bour | +1.156 |
onial | +1.145 |
otor | +1.033 |
agher | +1.029 |
Neg logit contributions | |
irtual | -1.277 |
� | -1.240 |
Reply | -1.230 |
roll | -1.159 |
Stra | -1.143 |
Token | found |
Token ID | 1043 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
merce | +0.432 |
bour | +0.420 |
onial | +0.418 |
otor | +0.382 |
agher | +0.381 |
Neg logit contributions | |
irtual | -0.342 |
� | -0.332 |
Reply | -0.330 |
roll | -0.309 |
Stra | -0.303 |
Token | guilty |
Token ID | 6717 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
merce | +1.471 |
bour | +1.428 |
onial | +1.420 |
agher | +1.293 |
otor | +1.290 |
Neg logit contributions | |
irtual | -1.261 |
� | -1.213 |
Reply | -1.209 |
roll | -1.127 |
Stra | -1.114 |
Token | of |
Token ID | 286 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
merce | +4.924 |
bour | +4.781 |
onial | +4.747 |
agher | +4.326 |
otor | +4.281 |
Neg logit contributions | |
irtual | -4.398 |
� | -4.231 |
Reply | -4.158 |
Stra | -3.818 |
roll | -3.817 |
Token | price |
Token ID | 2756 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
merce | +0.798 |
bour | +0.771 |
onial | +0.767 |
otor | +0.688 |
agher | +0.686 |
Neg logit contributions | |
irtual | -0.897 |
� | -0.872 |
Reply | -0.868 |
roll | -0.823 |
Stra | -0.810 |
Token | - |
Token ID | 12 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
merce | +0.891 |
bour | +0.866 |
onial | +0.861 |
otor | +0.782 |
agher | +0.780 |
Neg logit contributions | |
irtual | -0.800 |
� | -0.774 |
Reply | -0.770 |
roll | -0.723 |
Stra | -0.711 |
Token | fix |
Token ID | 13049 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
merce | +0.702 |
bour | +0.684 |
onial | +0.680 |
otor | +0.621 |
agher | +0.620 |
Neg logit contributions | |
irtual | -0.543 |
� | -0.524 |
Reply | -0.520 |
roll | -0.485 |
Stra | -0.477 |
Token | ing |
Token ID | 278 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
merce | +0.729 |
bour | +0.711 |
onial | +0.707 |
otor | +0.644 |
agher | +0.641 |
Neg logit contributions | |
irtual | -0.588 |
� | -0.567 |
Reply | -0.563 |
roll | -0.520 |
Stra | -0.518 |
Token | statement |
Token ID | 2643 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
irtual | +0.486 |
� | +0.470 |
Reply | +0.468 |
roll | +0.440 |
Stra | +0.433 |
Neg logit contributions | |
merce | -0.515 |
bour | -0.499 |
onial | -0.497 |
otor | -0.450 |
agher | -0.449 |
Token | . |
Token ID | 13 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
irtual | +0.143 |
� | +0.139 |
Reply | +0.138 |
roll | +0.131 |
Stra | +0.128 |
Neg logit contributions | |
merce | -0.142 |
bour | -0.138 |
onial | -0.137 |
otor | -0.123 |
agher | -0.123 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
irtual | +0.123 |
� | +0.119 |
Reply | +0.118 |
roll | +0.110 |
Stra | +0.108 |
Neg logit contributions | |
merce | -0.162 |
bour | -0.158 |
onial | -0.157 |
otor | -0.144 |
agher | -0.143 |
Token |
|
Token ID | 198 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
bour | +0.307 |
merce | +0.304 |
onial | +0.300 |
otor | +0.275 |
agher | +0.274 |
Neg logit contributions | |
irtual | -0.279 |
� | -0.261 |
Reply | -0.256 |
roll | -0.239 |
Stra | -0.235 |
Token | " |
Token ID | 1 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
irtual | +0.041 |
� | +0.039 |
Reply | +0.039 |
roll | +0.036 |
Stra | +0.035 |
Neg logit contributions | |
merce | -0.066 |
bour | -0.065 |
onial | -0.064 |
otor | -0.059 |
agher | -0.059 |
Token | En |
Token ID | 4834 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
irtual | +0.747 |
� | +0.717 |
Reply | +0.712 |
roll | +0.658 |
Stra | +0.643 |
Neg logit contributions | |
merce | -1.236 |
bour | -1.205 |
onial | -1.199 |
otor | -1.107 |
agher | -1.105 |
Token | vision |
Token ID | 10178 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
merce | +4.532 |
bour | +4.512 |
onial | +4.392 |
agher | +4.036 |
otor | +3.970 |
Neg logit contributions | |
irtual | -4.572 |
Reply | -4.431 |
� | -4.430 |
Stra | -4.079 |
ELL | -4.051 |
Token | ing |
Token ID | 278 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
merce | +0.894 |
bour | +0.871 |
onial | +0.866 |
otor | +0.791 |
agher | +0.789 |
Neg logit contributions | |
irtual | -0.716 |
Reply | -0.691 |
� | -0.690 |
roll | -0.638 |
Stra | -0.629 |
Token | a |
Token ID | 257 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
merce | +0.304 |
bour | +0.296 |
onial | +0.294 |
otor | +0.266 |
agher | +0.265 |
Neg logit contributions | |
irtual | -0.313 |
� | -0.303 |
Reply | -0.302 |
roll | -0.283 |
Stra | -0.279 |
Token | world |
Token ID | 995 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
irtual | +0.031 |
� | +0.030 |
Reply | +0.030 |
roll | +0.028 |
Stra | +0.027 |
Neg logit contributions | |
merce | -0.029 |
bour | -0.028 |
onial | -0.028 |
otor | -0.025 |
agher | -0.025 |
Token | where |
Token ID | 810 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
merce | +1.657 |
bour | +1.620 |
onial | +1.617 |
otor | +1.467 |
agher | +1.453 |
Neg logit contributions | |
irtual | -1.516 |
Reply | -1.464 |
� | -1.463 |
roll | -1.356 |
Stra | -1.333 |
Token | who |
Token ID | 508 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
merce | +0.577 |
bour | +0.568 |
onial | +0.562 |
agher | +0.513 |
otor | +0.513 |
Neg logit contributions | |
irtual | -0.491 |
� | -0.474 |
Reply | -0.471 |
roll | -0.441 |
Stra | -0.435 |
Token | owns |
Token ID | 12216 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
irtual | +1.307 |
� | +1.262 |
Reply | +1.255 |
roll | +1.173 |
Stra | +1.150 |
Neg logit contributions | |
merce | -1.710 |
bour | -1.663 |
onial | -1.654 |
otor | -1.514 |
agher | -1.512 |
Token | several |
Token ID | 1811 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
irtual | +0.399 |
� | +0.386 |
Reply | +0.385 |
roll | +0.363 |
Stra | +0.355 |
Neg logit contributions | |
merce | -0.448 |
bour | -0.432 |
onial | -0.431 |
otor | -0.391 |
agher | -0.391 |
Token | restaurant |
Token ID | 7072 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
irtual | +1.040 |
� | +1.007 |
Reply | +1.004 |
roll | +0.949 |
Stra | +0.930 |
Neg logit contributions | |
merce | -1.061 |
bour | -1.023 |
onial | -1.019 |
otor | -0.921 |
agher | -0.920 |
Token | / |
Token ID | 14 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
merce | +2.076 |
bour | +2.040 |
onial | +2.027 |
otor | +1.817 |
agher | +1.806 |
Neg logit contributions | |
irtual | -2.004 |
� | -1.938 |
Reply | -1.930 |
roll | -1.793 |
Stra | -1.788 |
Token | bars |
Token ID | 34046 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
merce | +0.563 |
bour | +0.545 |
onial | +0.542 |
otor | +0.490 |
agher | +0.489 |
Neg logit contributions | |
irtual | -0.559 |
� | -0.542 |
Reply | -0.540 |
roll | -0.509 |
Stra | -0.501 |
Token | in |
Token ID | 287 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
bour | +4.927 |
merce | +4.913 |
onial | +4.887 |
otor | +4.364 |
agher | +4.342 |
Neg logit contributions | |
irtual | -4.131 |
� | -3.966 |
Reply | -3.953 |
roll | -3.631 |
Stra | -3.612 |
Token | Forest |
Token ID | 9115 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
irtual | +0.350 |
� | +0.338 |
Reply | +0.336 |
roll | +0.313 |
Stra | +0.305 |
Neg logit contributions | |
merce | -0.512 |
bour | -0.496 |
onial | -0.494 |
agher | -0.454 |
otor | -0.454 |
Token | Park |
Token ID | 3250 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
irtual | +0.846 |
� | +0.810 |
Reply | +0.804 |
roll | +0.738 |
Stra | +0.721 |
Neg logit contributions | |
merce | -1.548 |
bour | -1.512 |
onial | -1.504 |
otor | -1.394 |
agher | -1.391 |
Token | and |
Token ID | 290 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
irtual | +0.718 |
� | +0.695 |
Reply | +0.691 |
roll | +0.651 |
Stra | +0.639 |
Neg logit contributions | |
merce | -0.787 |
bour | -0.763 |
onial | -0.759 |
otor | -0.689 |
agher | -0.688 |
Token | who |
Token ID | 508 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
merce | +0.897 |
bour | +0.882 |
onial | +0.873 |
otor | +0.800 |
agher | +0.798 |
Neg logit contributions | |
irtual | -0.695 |
� | -0.670 |
Reply | -0.666 |
roll | -0.620 |
Stra | -0.611 |
Token | ock |
Token ID | 735 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
merce | +0.889 |
bour | +0.865 |
onial | +0.859 |
agher | +0.779 |
otor | +0.779 |
Neg logit contributions | |
irtual | -0.837 |
� | -0.812 |
Reply | -0.808 |
roll | -0.758 |
Stra | -0.746 |
Token | noted |
Token ID | 4367 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
irtual | +0.061 |
� | +0.059 |
Reply | +0.059 |
roll | +0.055 |
Stra | +0.054 |
Neg logit contributions | |
merce | -0.078 |
bour | -0.076 |
onial | -0.076 |
agher | -0.069 |
otor | -0.069 |
Token | that |
Token ID | 326 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
irtual | +0.516 |
� | +0.500 |
Reply | +0.497 |
roll | +0.468 |
Stra | +0.459 |
Neg logit contributions | |
merce | -0.630 |
bour | -0.612 |
onial | -0.608 |
otor | -0.556 |
agher | -0.554 |
Token | " |
Token ID | 366 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
merce | +0.804 |
bour | +0.781 |
onial | +0.776 |
otor | +0.707 |
agher | +0.706 |
Neg logit contributions | |
irtual | -0.700 |
� | -0.677 |
Reply | -0.674 |
roll | -0.631 |
Stra | -0.621 |
Token | wh |
Token ID | 1929 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
merce | +0.045 |
bour | +0.043 |
onial | +0.043 |
otor | +0.039 |
agher | +0.039 |
Neg logit contributions | |
irtual | -0.036 |
� | -0.035 |
Reply | -0.035 |
roll | -0.033 |
Stra | -0.032 |
Token | ilst |
Token ID | 11750 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
merce | +0.491 |
bour | +0.473 |
onial | +0.470 |
otor | +0.416 |
agher | +0.414 |
Neg logit contributions | |
irtual | -0.673 |
� | -0.656 |
Reply | -0.654 |
roll | -0.621 |
Stra | -0.613 |
Token | people |
Token ID | 661 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
merce | +4.621 |
bour | +4.537 |
onial | +4.509 |
agher | +4.096 |
otor | +4.075 |
Neg logit contributions | |
irtual | -4.505 |
� | -4.254 |
Reply | -4.215 |
roll | -3.935 |
Stra | -3.914 |
Token | expect |
Token ID | 1607 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
irtual | +0.792 |
� | +0.765 |
Reply | +0.762 |
roll | +0.712 |
Stra | +0.695 |
Neg logit contributions | |
merce | -1.077 |
bour | -1.047 |
onial | -1.042 |
otor | -0.955 |
agher | -0.952 |
Token | a |
Token ID | 257 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
irtual | +0.254 |
� | +0.247 |
Reply | +0.246 |
roll | +0.232 |
Stra | +0.227 |
Neg logit contributions | |
merce | -0.288 |
bour | -0.279 |
onial | -0.278 |
otor | -0.253 |
agher | -0.251 |
Token | full |
Token ID | 1336 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
irtual | +0.523 |
� | +0.510 |
Reply | +0.509 |
roll | +0.484 |
Stra | +0.475 |
Neg logit contributions | |
merce | -0.482 |
bour | -0.467 |
onial | -0.464 |
otor | -0.416 |
agher | -0.415 |
Token | value |
Token ID | 1988 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
irtual | +0.299 |
� | +0.292 |
Reply | +0.291 |
roll | +0.277 |
Stra | +0.270 |
Neg logit contributions | |
merce | -0.289 |
bour | -0.280 |
onial | -0.277 |
otor | -0.251 |
agher | -0.248 |
Token | and |
Token ID | 290 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
irtual | +2.160 |
� | +2.088 |
Reply | +2.056 |
roll | +1.973 |
Stra | +1.906 |
Neg logit contributions | |
merce | -2.440 |
bour | -2.381 |
onial | -2.367 |
agher | -2.142 |
otor | -2.138 |
Token | utilize |
Token ID | 17624 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
irtual | +0.842 |
� | +0.813 |
Reply | +0.809 |
roll | +0.759 |
Stra | +0.744 |
Neg logit contributions | |
merce | -1.054 |
bour | -1.024 |
onial | -1.019 |
agher | -0.930 |
otor | -0.930 |
Token | easily |
Token ID | 3538 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
irtual | +0.632 |
� | +0.612 |
Reply | +0.606 |
roll | +0.572 |
Stra | +0.561 |
Neg logit contributions | |
merce | -0.768 |
bour | -0.745 |
onial | -0.742 |
agher | -0.677 |
otor | -0.674 |
Token | with |
Token ID | 351 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
irtual | +2.560 |
� | +2.465 |
Reply | +2.437 |
roll | +2.344 |
Stra | +2.264 |
Neg logit contributions | |
merce | -3.098 |
bour | -3.039 |
onial | -3.008 |
agher | -2.748 |
otor | -2.731 |
Token | excellent |
Token ID | 6275 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
merce | +0.498 |
bour | +0.483 |
onial | +0.480 |
otor | +0.435 |
agher | +0.434 |
Neg logit contributions | |
irtual | -0.475 |
� | -0.461 |
Reply | -0.458 |
roll | -0.432 |
Stra | -0.425 |
Token | Arduino |
Token ID | 27634 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
irtual | +0.449 |
� | +0.434 |
Reply | +0.432 |
roll | +0.406 |
Stra | +0.399 |
Neg logit contributions | |
merce | -0.515 |
bour | -0.499 |
onial | -0.496 |
otor | -0.452 |
agher | -0.451 |
Token | compatibility |
Token ID | 17764 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
merce | +4.929 |
bour | +4.775 |
onial | +4.672 |
otor | +4.399 |
agher | +4.245 |
Neg logit contributions | |
irtual | -4.050 |
Reply | -3.974 |
� | -3.925 |
roll | -3.694 |
Stra | -3.585 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
merce | +0.311 |
bour | +0.301 |
onial | +0.299 |
otor | +0.271 |
agher | +0.270 |
Neg logit contributions | |
irtual | -0.307 |
� | -0.298 |
Reply | -0.297 |
roll | -0.279 |
Stra | -0.275 |
Token | I |
Token ID | 314 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
merce | +0.416 |
bour | +0.407 |
onial | +0.404 |
otor | +0.370 |
agher | +0.369 |
Neg logit contributions | |
irtual | -0.322 |
� | -0.309 |
Reply | -0.307 |
roll | -0.287 |
Stra | -0.281 |
Token | � |
Token ID | 447 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
merce | +0.242 |
bour | +0.236 |
onial | +0.235 |
otor | +0.216 |
agher | +0.215 |
Neg logit contributions | |
irtual | -0.164 |
� | -0.158 |
Reply | -0.157 |
roll | -0.146 |
Stra | -0.143 |
Token | � |
Token ID | 247 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
merce | +0.031 |
bour | +0.031 |
onial | +0.030 |
otor | +0.028 |
agher | +0.028 |
Neg logit contributions | |
irtual | -0.024 |
� | -0.023 |
Reply | -0.023 |
roll | -0.022 |
Stra | -0.021 |
Token | take |
Token ID | 1011 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
irtual | +0.402 |
� | +0.389 |
Reply | +0.387 |
roll | +0.365 |
Stra | +0.358 |
Neg logit contributions | |
merce | -0.432 |
bour | -0.419 |
onial | -0.417 |
otor | -0.378 |
agher | -0.377 |
Token | on |
Token ID | 319 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
irtual | +1.560 |
� | +1.509 |
Reply | +1.495 |
roll | +1.404 |
Stra | +1.372 |
Neg logit contributions | |
merce | -2.169 |
bour | -2.091 |
onial | -2.082 |
agher | -1.913 |
otor | -1.911 |
Token | the |
Token ID | 262 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
merce | +0.397 |
bour | +0.387 |
onial | +0.384 |
otor | +0.350 |
agher | +0.349 |
Neg logit contributions | |
irtual | -0.349 |
� | -0.337 |
Reply | -0.336 |
roll | -0.316 |
Stra | -0.309 |
Token | history |
Token ID | 2106 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
merce | +0.103 |
bour | +0.100 |
onial | +0.100 |
otor | +0.090 |
agher | +0.090 |
Neg logit contributions | |
irtual | -0.092 |
� | -0.089 |
Reply | -0.089 |
roll | -0.084 |
Stra | -0.082 |
Token | of |
Token ID | 286 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
merce | +1.024 |
bour | +0.997 |
onial | +0.992 |
otor | +0.910 |
agher | +0.908 |
Neg logit contributions | |
irtual | -0.746 |
� | -0.720 |
Reply | -0.716 |
roll | -0.667 |
Stra | -0.654 |
Token | Arduino |
Token ID | 27634 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
irtual | +0.036 |
� | +0.034 |
Reply | +0.034 |
roll | +0.032 |
Stra | +0.032 |
Neg logit contributions | |
merce | -0.040 |
bour | -0.039 |
onial | -0.039 |
otor | -0.035 |
agher | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
merce | +4.737 |
bour | +4.602 |
onial | +4.520 |
otor | +4.222 |
agher | +4.115 |
Neg logit contributions | |
irtual | -4.219 |
Reply | -4.100 |
� | -4.092 |
roll | -3.840 |
Stra | -3.766 |
Token | and |
Token ID | 290 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
merce | +0.437 |
bour | +0.425 |
onial | +0.422 |
otor | +0.384 |
agher | +0.383 |
Neg logit contributions | |
irtual | -0.383 |
� | -0.371 |
Reply | -0.369 |
roll | -0.347 |
Stra | -0.341 |
Token | the |
Token ID | 262 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
irtual | +0.080 |
� | +0.077 |
Reply | +0.077 |
roll | +0.072 |
Stra | +0.071 |
Neg logit contributions | |
merce | -0.105 |
bour | -0.102 |
onial | -0.101 |
otor | -0.093 |
agher | -0.093 |
Token | evolution |
Token ID | 6954 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
merce | +0.320 |
bour | +0.311 |
onial | +0.309 |
otor | +0.280 |
agher | +0.279 |
Neg logit contributions | |
irtual | -0.301 |
� | -0.291 |
Reply | -0.290 |
roll | -0.273 |
Stra | -0.268 |
Token | of |
Token ID | 286 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
merce | +0.539 |
bour | +0.523 |
onial | +0.521 |
otor | +0.478 |
agher | +0.478 |
Neg logit contributions | |
irtual | -0.373 |
� | -0.360 |
Reply | -0.358 |
roll | -0.333 |
Stra | -0.327 |
Token | , |
Token ID | 11 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
merce | +0.986 |
bour | +0.955 |
onial | +0.948 |
otor | +0.858 |
agher | +0.857 |
Neg logit contributions | |
irtual | -0.967 |
� | -0.936 |
Reply | -0.933 |
roll | -0.875 |
Stra | -0.866 |
Token | such |
Token ID | 884 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
merce | +0.226 |
bour | +0.220 |
onial | +0.218 |
otor | +0.199 |
agher | +0.199 |
Neg logit contributions | |
irtual | -0.184 |
� | -0.178 |
Reply | -0.177 |
roll | -0.165 |
Stra | -0.162 |
Token | as |
Token ID | 355 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
merce | +0.777 |
bour | +0.766 |
onial | +0.755 |
agher | +0.695 |
otor | +0.692 |
Neg logit contributions | |
irtual | -0.617 |
� | -0.586 |
Reply | -0.584 |
roll | -0.541 |
Stra | -0.535 |
Token | Alpha |
Token ID | 12995 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
merce | +0.764 |
bour | +0.742 |
onial | +0.738 |
otor | +0.671 |
agher | +0.670 |
Neg logit contributions | |
irtual | -0.678 |
� | -0.656 |
Reply | -0.654 |
roll | -0.614 |
Stra | -0.603 |
Token | Delta |
Token ID | 16978 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
merce | +2.133 |
bour | +2.107 |
onial | +2.083 |
agher | +1.895 |
otor | +1.879 |
Neg logit contributions | |
irtual | -2.134 |
Reply | -2.042 |
� | -2.040 |
roll | -1.910 |
Stra | -1.869 |
Token | Phi |
Token ID | 47256 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
merce | +1.652 |
bour | +1.630 |
onial | +1.610 |
agher | +1.465 |
otor | +1.460 |
Neg logit contributions | |
irtual | -1.629 |
Reply | -1.567 |
� | -1.558 |
roll | -1.462 |
Stra | -1.439 |
Token | ($ |
Token ID | 7198 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
merce | +4.478 |
bour | +4.459 |
onial | +4.377 |
otor | +3.954 |
agher | +3.939 |
Neg logit contributions | |
irtual | -4.459 |
Reply | -4.263 |
� | -4.224 |
roll | -3.928 |
Stra | -3.893 |
Token | 400 |
Token ID | 7029 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
merce | +1.195 |
bour | +1.173 |
onial | +1.163 |
otor | +1.075 |
agher | +1.071 |
Neg logit contributions | |
irtual | -0.798 |
� | -0.758 |
Reply | -0.753 |
roll | -0.697 |
Stra | -0.682 |
Token | per |
Token ID | 583 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
irtual | +0.097 |
� | +0.093 |
Reply | +0.093 |
roll | +0.087 |
Stra | +0.085 |
Neg logit contributions | |
merce | -0.121 |
bour | -0.118 |
onial | -0.117 |
otor | -0.107 |
agher | -0.107 |
Token | semester |
Token ID | 24878 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
irtual | +1.236 |
� | +1.207 |
Reply | +1.200 |
roll | +1.149 |
Stra | +1.117 |
Neg logit contributions | |
merce | -1.440 |
bour | -1.389 |
onial | -1.378 |
otor | -1.255 |
agher | -1.250 |
Token | ), |
Token ID | 828 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
irtual | +0.026 |
� | +0.025 |
Reply | +0.025 |
roll | +0.024 |
Stra | +0.023 |
Neg logit contributions | |
merce | -0.033 |
bour | -0.032 |
onial | -0.032 |
otor | -0.029 |
agher | -0.029 |
Token | LCD |
Token ID | 23598 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
irtual | +0.825 |
� | +0.797 |
Reply | +0.796 |
roll | +0.750 |
Stra | +0.736 |
Neg logit contributions | |
merce | -0.838 |
bour | -0.811 |
onial | -0.807 |
agher | -0.730 |
otor | -0.726 |
Token | library |
Token ID | 5888 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
merce | +2.738 |
bour | +2.655 |
onial | +2.650 |
otor | +2.432 |
agher | +2.375 |
Neg logit contributions | |
irtual | -2.610 |
� | -2.546 |
Reply | -2.535 |
roll | -2.353 |
rules | -2.345 |
Token | . |
Token ID | 13 |
Feature activation | -9.15e-03 |
Pos logit contributions | |
merce | +2.079 |
bour | +2.022 |
onial | +2.017 |
otor | +1.842 |
agher | +1.820 |
Neg logit contributions | |
irtual | -1.826 |
� | -1.766 |
Reply | -1.766 |
roll | -1.645 |
Stra | -1.622 |
Token | Features |
Token ID | 17571 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
irtual | +0.017 |
� | +0.016 |
Reply | +0.016 |
roll | +0.015 |
Stra | +0.015 |
Neg logit contributions | |
merce | -0.023 |
bour | -0.022 |
onial | -0.022 |
otor | -0.020 |
agher | -0.020 |
Token | no |
Token ID | 645 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
merce | +1.568 |
bour | +1.529 |
onial | +1.519 |
otor | +1.388 |
agher | +1.378 |
Neg logit contributions | |
irtual | -1.285 |
Reply | -1.237 |
� | -1.237 |
roll | -1.154 |
Stra | -1.133 |
Token | Arduino |
Token ID | 27634 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
irtual | +1.285 |
� | +1.257 |
Reply | +1.244 |
roll | +1.181 |
Stra | +1.167 |
Neg logit contributions | |
merce | -1.073 |
onial | -1.029 |
bour | -1.024 |
agher | -0.921 |
otor | -0.901 |
Token | boards |
Token ID | 11490 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
merce | +4.917 |
bour | +4.870 |
onial | +4.733 |
otor | +4.410 |
agher | +4.313 |
Neg logit contributions | |
irtual | -3.990 |
Reply | -3.830 |
� | -3.805 |
roll | -3.539 |
Stra | -3.524 |
Token | have |
Token ID | 423 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
merce | +2.866 |
bour | +2.800 |
onial | +2.768 |
otor | +2.551 |
agher | +2.531 |
Neg logit contributions | |
irtual | -2.276 |
� | -2.225 |
Reply | -2.218 |
Stra | -2.040 |
roll | -2.025 |
Token | , |
Token ID | 11 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
merce | +0.813 |
bour | +0.793 |
onial | +0.787 |
otor | +0.711 |
agher | +0.709 |
Neg logit contributions | |
irtual | -0.797 |
� | -0.774 |
Reply | -0.772 |
roll | -0.726 |
Stra | -0.715 |
Token | like |
Token ID | 588 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
irtual | +0.042 |
� | +0.041 |
Reply | +0.041 |
roll | +0.038 |
Stra | +0.037 |
Neg logit contributions | |
merce | -0.053 |
bour | -0.052 |
onial | -0.051 |
otor | -0.047 |
agher | -0.047 |
Token | Te |
Token ID | 1665 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
merce | +1.156 |
bour | +1.121 |
onial | +1.113 |
otor | +1.015 |
agher | +1.010 |
Neg logit contributions | |
irtual | -1.042 |
� | -1.012 |
Reply | -1.004 |
roll | -0.943 |
Stra | -0.927 |
Token | 2014 |
Token ID | 1946 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
irtual | +0.200 |
� | +0.193 |
Reply | +0.192 |
roll | +0.180 |
Stra | +0.176 |
Neg logit contributions | |
merce | -0.235 |
bour | -0.230 |
onial | -0.229 |
otor | -0.209 |
agher | -0.208 |
Token | award |
Token ID | 5764 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
irtual | +1.034 |
� | +0.999 |
Reply | +0.993 |
roll | +0.930 |
Stra | +0.912 |
Neg logit contributions | |
merce | -1.344 |
bour | -1.304 |
onial | -1.298 |
otor | -1.187 |
agher | -1.186 |
Token | winners |
Token ID | 14591 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
irtual | +2.691 |
� | +2.641 |
Reply | +2.620 |
roll | +2.498 |
Stra | +2.432 |
Neg logit contributions | |
merce | -3.057 |
onial | -2.931 |
bour | -2.930 |
agher | -2.665 |
otor | -2.663 |
Token | ( |
Token ID | 357 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
irtual | +1.108 |
� | +1.073 |
Reply | +1.058 |
roll | +0.994 |
Stra | +0.965 |
Neg logit contributions | |
merce | -1.750 |
bour | -1.696 |
onial | -1.690 |
otor | -1.561 |
agher | -1.554 |
Token | as |
Token ID | 292 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
irtual | +0.055 |
� | +0.053 |
Reply | +0.053 |
roll | +0.050 |
Stra | +0.049 |
Neg logit contributions | |
merce | -0.057 |
bour | -0.055 |
onial | -0.055 |
otor | -0.050 |
agher | -0.050 |
Token | well |
Token ID | 880 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
merce | +0.758 |
bour | +0.738 |
onial | +0.731 |
agher | +0.666 |
otor | +0.663 |
Neg logit contributions | |
irtual | -0.711 |
Reply | -0.688 |
� | -0.686 |
roll | -0.640 |
Stra | -0.631 |
Token | as |
Token ID | 355 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Reply | +4.222 |
� | +4.141 |
irtual | +4.134 |
roll | +3.955 |
Stra | +3.739 |
Neg logit contributions | |
merce | -8.443 |
onial | -8.067 |
bour | -7.999 |
otor | -7.511 |
agher | -7.429 |
Token | the |
Token ID | 262 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
irtual | +1.219 |
� | +1.181 |
Reply | +1.177 |
roll | +1.109 |
Stra | +1.090 |
Neg logit contributions | |
merce | -1.331 |
bour | -1.286 |
onial | -1.281 |
otor | -1.164 |
agher | -1.159 |
Token | previously |
Token ID | 4271 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
irtual | +0.632 |
� | +0.612 |
Reply | +0.609 |
roll | +0.572 |
Stra | +0.562 |
Neg logit contributions | |
merce | -0.693 |
bour | -0.674 |
onial | -0.670 |
otor | -0.608 |
agher | -0.607 |
Token | announced |
Token ID | 3414 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
irtual | +0.896 |
� | +0.869 |
Reply | +0.858 |
roll | +0.801 |
Stra | +0.784 |
Neg logit contributions | |
merce | -1.444 |
bour | -1.400 |
onial | -1.399 |
otor | -1.291 |
agher | -1.288 |
Token | nominees |
Token ID | 26456 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
irtual | +1.335 |
� | +1.294 |
Reply | +1.290 |
roll | +1.210 |
Stra | +1.189 |
Neg logit contributions | |
merce | -1.656 |
bour | -1.600 |
onial | -1.595 |
otor | -1.455 |
agher | -1.453 |
Token | official |
Token ID | 1743 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
irtual | +0.129 |
� | +0.124 |
Reply | +0.124 |
roll | +0.117 |
Stra | +0.116 |
Neg logit contributions | |
merce | -0.101 |
onial | -0.098 |
bour | -0.098 |
otor | -0.087 |
agher | -0.087 |
Token | statement |
Token ID | 2643 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
merce | +1.131 |
bour | +1.102 |
onial | +1.101 |
otor | +0.988 |
agher | +0.986 |
Neg logit contributions | |
irtual | -1.169 |
� | -1.122 |
Reply | -1.110 |
roll | -1.051 |
Stra | -1.034 |
Token | soon |
Token ID | 2582 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
irtual | +0.198 |
� | +0.183 |
Reply | +0.182 |
roll | +0.166 |
rules | +0.162 |
Neg logit contributions | |
merce | -0.312 |
bour | -0.309 |
onial | -0.304 |
otor | -0.282 |
agher | -0.279 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
irtual | +1.748 |
� | +1.693 |
Reply | +1.684 |
roll | +1.592 |
Stra | +1.566 |
Neg logit contributions | |
merce | -1.642 |
bour | -1.593 |
onial | -1.582 |
otor | -1.427 |
agher | -1.423 |
Token | As |
Token ID | 1081 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
irtual | +0.280 |
� | +0.271 |
Reply | +0.271 |
roll | +0.251 |
Stra | +0.246 |
Neg logit contributions | |
merce | -0.403 |
bour | -0.392 |
onial | -0.391 |
otor | -0.358 |
agher | -0.357 |
Token | well |
Token ID | 880 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
merce | +0.332 |
bour | +0.327 |
onial | +0.321 |
agher | +0.293 |
otor | +0.287 |
Neg logit contributions | |
irtual | -0.426 |
� | -0.407 |
Reply | -0.405 |
roll | -0.380 |
Stra | -0.379 |
Token | as |
Token ID | 355 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
Reply | +3.876 |
� | +3.845 |
irtual | +3.789 |
roll | +3.637 |
Stra | +3.454 |
Neg logit contributions | |
merce | -7.827 |
onial | -7.495 |
bour | -7.396 |
otor | -6.899 |
agher | -6.799 |
Token | updates |
Token ID | 5992 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
irtual | +0.355 |
� | +0.295 |
Reply | +0.290 |
roll | +0.198 |
Stra | +0.189 |
Neg logit contributions | |
merce | -2.552 |
bour | -2.510 |
onial | -2.498 |
otor | -2.363 |
agher | -2.362 |
Token | regarding |
Token ID | 5115 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
irtual | +1.091 |
� | +1.048 |
Reply | +1.042 |
roll | +0.964 |
Stra | +0.943 |
Neg logit contributions | |
merce | -1.747 |
bour | -1.703 |
onial | -1.695 |
otor | -1.563 |
agher | -1.560 |
Token | the |
Token ID | 262 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
irtual | +1.966 |
� | +1.932 |
Reply | +1.923 |
roll | +1.815 |
Stra | +1.779 |
Neg logit contributions | |
merce | -2.246 |
onial | -2.152 |
bour | -2.152 |
agher | -1.952 |
otor | -1.951 |
Token | future |
Token ID | 2003 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
irtual | +0.445 |
� | +0.427 |
Reply | +0.424 |
roll | +0.398 |
Stra | +0.394 |
Neg logit contributions | |
merce | -0.426 |
bour | -0.416 |
onial | -0.412 |
otor | -0.373 |
agher | -0.369 |
Token | the |
Token ID | 262 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
merce | +0.305 |
bour | +0.293 |
onial | +0.291 |
otor | +0.265 |
agher | +0.264 |
Neg logit contributions | |
irtual | -0.273 |
� | -0.264 |
Reply | -0.262 |
roll | -0.250 |
Stra | -0.245 |
Token | busy |
Token ID | 8179 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
irtual | +0.503 |
� | +0.489 |
Reply | +0.488 |
roll | +0.464 |
Stra | +0.458 |
Neg logit contributions | |
merce | -0.450 |
bour | -0.429 |
onial | -0.427 |
otor | -0.384 |
agher | -0.384 |
Token | corner |
Token ID | 5228 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
irtual | +0.426 |
� | +0.415 |
Reply | +0.412 |
roll | +0.396 |
Stra | +0.390 |
Neg logit contributions | |
merce | -0.353 |
onial | -0.334 |
bour | -0.334 |
otor | -0.298 |
agher | -0.296 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
irtual | +1.354 |
� | +1.316 |
Reply | +1.288 |
roll | +1.240 |
Stra | +1.213 |
Neg logit contributions | |
merce | -1.732 |
onial | -1.654 |
bour | -1.647 |
otor | -1.520 |
agher | -1.504 |
Token | As |
Token ID | 1081 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
merce | +0.512 |
bour | +0.499 |
onial | +0.496 |
otor | +0.454 |
agher | +0.454 |
Neg logit contributions | |
irtual | -0.395 |
� | -0.380 |
Reply | -0.378 |
roll | -0.353 |
Stra | -0.346 |
Token | well |
Token ID | 880 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
merce | +1.411 |
bour | +1.375 |
onial | +1.365 |
otor | +1.241 |
agher | +1.238 |
Neg logit contributions | |
irtual | -1.289 |
Reply | -1.251 |
� | -1.250 |
roll | -1.168 |
Stra | -1.148 |
Token | , |
Token ID | 11 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
irtual | +4.172 |
� | +4.040 |
Reply | +3.844 |
roll | +3.789 |
Stra | +3.596 |
Neg logit contributions | |
merce | -7.138 |
bour | -6.932 |
onial | -6.905 |
agher | -6.397 |
otor | -6.385 |
Token | Cow |
Token ID | 10417 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
irtual | +1.143 |
� | +1.104 |
Reply | +1.090 |
roll | +1.045 |
Stra | +1.019 |
Neg logit contributions | |
merce | -1.343 |
bour | -1.286 |
onial | -1.285 |
otor | -1.170 |
agher | -1.162 |
Token | bell |
Token ID | 7923 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
irtual | +1.336 |
� | +1.288 |
Reply | +1.277 |
roll | +1.220 |
rules | +1.188 |
Neg logit contributions | |
merce | -1.567 |
onial | -1.502 |
bour | -1.484 |
otor | -1.358 |
agher | -1.351 |
Token | Lane |
Token ID | 15016 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
merce | +1.407 |
bour | +1.375 |
onial | +1.366 |
otor | +1.248 |
agher | +1.247 |
Neg logit contributions | |
irtual | -1.117 |
� | -1.081 |
Reply | -1.079 |
roll | -1.002 |
Stra | -0.988 |
Token | will |
Token ID | 481 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
irtual | +1.117 |
� | +1.078 |
Reply | +1.071 |
roll | +1.014 |
Stra | +0.992 |
Neg logit contributions | |
merce | -1.452 |
onial | -1.394 |
bour | -1.389 |
otor | -1.270 |
agher | -1.268 |
Token | .) |
Token ID | 2014 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
merce | +0.647 |
bour | +0.630 |
onial | +0.628 |
otor | +0.574 |
agher | +0.573 |
Neg logit contributions | |
irtual | -0.497 |
� | -0.480 |
Reply | -0.478 |
roll | -0.446 |
Stra | -0.438 |
Token | So |
Token ID | 1406 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
merce | +1.104 |
bour | +1.090 |
onial | +1.075 |
otor | +0.996 |
agher | +0.990 |
Neg logit contributions | |
irtual | -0.873 |
� | -0.819 |
Reply | -0.809 |
roll | -0.756 |
rules | -0.740 |
Token | I |
Token ID | 314 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
merce | +0.052 |
bour | +0.050 |
onial | +0.050 |
otor | +0.046 |
agher | +0.046 |
Neg logit contributions | |
irtual | -0.037 |
� | -0.036 |
Reply | -0.035 |
roll | -0.033 |
Stra | -0.032 |
Token | might |
Token ID | 1244 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
irtual | +0.789 |
� | +0.761 |
Reply | +0.756 |
roll | +0.705 |
Stra | +0.690 |
Neg logit contributions | |
merce | -1.129 |
bour | -1.099 |
onial | -1.093 |
otor | -1.004 |
agher | -1.002 |
Token | as |
Token ID | 355 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
irtual | +0.781 |
� | +0.754 |
Reply | +0.749 |
roll | +0.700 |
Stra | +0.685 |
Neg logit contributions | |
merce | -1.081 |
bour | -1.051 |
onial | -1.046 |
otor | -0.959 |
agher | -0.958 |
Token | well |
Token ID | 880 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
irtual | +0.907 |
Reply | +0.871 |
� | +0.870 |
roll | +0.819 |
Stra | +0.810 |
Neg logit contributions | |
merce | -0.787 |
bour | -0.768 |
onial | -0.757 |
otor | -0.682 |
agher | -0.681 |
Token | make |
Token ID | 787 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
irtual | +4.693 |
Reply | +4.515 |
� | +4.512 |
roll | +4.388 |
Stra | +4.196 |
Neg logit contributions | |
merce | -6.669 |
bour | -6.383 |
onial | -6.379 |
agher | -5.864 |
otor | -5.827 |
Token | them |
Token ID | 606 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
irtual | +1.509 |
� | +1.464 |
Reply | +1.456 |
roll | +1.378 |
Stra | +1.347 |
Neg logit contributions | |
merce | -1.761 |
bour | -1.709 |
onial | -1.700 |
agher | -1.543 |
otor | -1.540 |
Token | useful |
Token ID | 4465 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
merce | +0.056 |
bour | +0.054 |
onial | +0.054 |
otor | +0.049 |
agher | +0.049 |
Neg logit contributions | |
irtual | -0.049 |
� | -0.047 |
Reply | -0.047 |
roll | -0.044 |
Stra | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
merce | +2.076 |
bour | +2.032 |
onial | +2.022 |
otor | +1.845 |
agher | +1.833 |
Neg logit contributions | |
irtual | -1.806 |
Reply | -1.734 |
� | -1.730 |
roll | -1.612 |
Stra | -1.591 |
Token | A |
Token ID | 317 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
irtual | +0.173 |
� | +0.164 |
Reply | +0.163 |
roll | +0.151 |
Stra | +0.148 |
Neg logit contributions | |
merce | -0.228 |
bour | -0.225 |
onial | -0.222 |
otor | -0.205 |
agher | -0.204 |
Token | Sony |
Token ID | 10184 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
irtual | +0.166 |
� | +0.160 |
Reply | +0.159 |
roll | +0.148 |
Stra | +0.145 |
Neg logit contributions | |
merce | -0.216 |
bour | -0.211 |
onial | -0.210 |
otor | -0.192 |
agher | -0.191 |
Token | PlayStation |
Token ID | 14047 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
irtual | +1.026 |
� | +0.992 |
Reply | +0.988 |
roll | +0.920 |
Stra | +0.904 |
Neg logit contributions | |
merce | -1.284 |
bour | -1.249 |
onial | -1.239 |
otor | -1.137 |
agher | -1.129 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
irtual | +1.567 |
� | +1.516 |
Reply | +1.508 |
roll | +1.414 |
Stra | +1.388 |
Neg logit contributions | |
merce | -1.858 |
bour | -1.804 |
onial | -1.794 |
otor | -1.636 |
agher | -1.632 |
Token | ," |
Token ID | 553 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
merce | +0.298 |
bour | +0.291 |
onial | +0.288 |
otor | +0.266 |
agher | +0.263 |
Neg logit contributions | |
irtual | -0.232 |
� | -0.224 |
Reply | -0.223 |
roll | -0.205 |
Stra | -0.202 |
Token | as |
Token ID | 355 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
merce | +0.258 |
bour | +0.251 |
onial | +0.250 |
agher | +0.227 |
otor | +0.227 |
Neg logit contributions | |
irtual | -0.218 |
� | -0.211 |
Reply | -0.210 |
roll | -0.195 |
Stra | -0.192 |
Token | well |
Token ID | 880 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
irtual | +0.175 |
� | +0.170 |
Reply | +0.170 |
roll | +0.159 |
Stra | +0.156 |
Neg logit contributions | |
merce | -0.185 |
bour | -0.180 |
onial | -0.179 |
otor | -0.162 |
agher | -0.162 |
Token | as |
Token ID | 355 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
irtual | +3.915 |
� | +3.782 |
Reply | +3.764 |
roll | +3.624 |
Stra | +3.419 |
Neg logit contributions | |
merce | -7.208 |
bour | -7.127 |
onial | -7.040 |
otor | -6.507 |
agher | -6.503 |
Token | Windows |
Token ID | 3964 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
irtual | +1.281 |
� | +1.241 |
Reply | +1.233 |
roll | +1.159 |
Stra | +1.136 |
Neg logit contributions | |
merce | -1.555 |
bour | -1.509 |
onial | -1.502 |
otor | -1.370 |
agher | -1.367 |
Token | PCs |
Token ID | 21869 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
irtual | +0.827 |
� | +0.795 |
Reply | +0.792 |
roll | +0.732 |
Stra | +0.721 |
Neg logit contributions | |
merce | -1.175 |
bour | -1.143 |
onial | -1.135 |
otor | -1.044 |
agher | -1.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
irtual | +1.173 |
� | +1.139 |
Reply | +1.128 |
roll | +1.071 |
Stra | +1.048 |
Neg logit contributions | |
merce | -1.329 |
bour | -1.290 |
onial | -1.283 |
agher | -1.168 |
otor | -1.164 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
irtual | +0.306 |
� | +0.294 |
Reply | +0.292 |
roll | +0.271 |
Stra | +0.265 |
Neg logit contributions | |
merce | -0.391 |
bour | -0.384 |
onial | -0.381 |
otor | -0.349 |
agher | -0.348 |
Token | official |
Token ID | 1743 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
irtual | +0.284 |
� | +0.275 |
Reply | +0.273 |
roll | +0.259 |
Stra | +0.255 |
Neg logit contributions | |
merce | -0.229 |
bour | -0.223 |
onial | -0.222 |
otor | -0.198 |
agher | -0.197 |
Token | statement |
Token ID | 2643 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
merce | +0.909 |
bour | +0.886 |
onial | +0.883 |
agher | +0.793 |
otor | +0.793 |
Neg logit contributions | |
irtual | -0.915 |
� | -0.882 |
Reply | -0.875 |
roll | -0.827 |
Stra | -0.812 |
Token | soon |
Token ID | 2582 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
irtual | +0.433 |
� | +0.401 |
Reply | +0.400 |
roll | +0.365 |
rules | +0.354 |
Neg logit contributions | |
merce | -0.746 |
bour | -0.738 |
onial | -0.729 |
otor | -0.671 |
agher | -0.670 |
Token | . |
Token ID | 13 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
irtual | +1.850 |
� | +1.801 |
Reply | +1.794 |
roll | +1.696 |
Stra | +1.668 |
Neg logit contributions | |
merce | -1.794 |
bour | -1.731 |
onial | -1.722 |
otor | -1.552 |
agher | -1.549 |
Token | As |
Token ID | 1081 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
irtual | +0.627 |
� | +0.601 |
Reply | +0.595 |
roll | +0.558 |
Stra | +0.545 |
Neg logit contributions | |
merce | -0.808 |
bour | -0.793 |
onial | -0.785 |
otor | -0.721 |
agher | -0.720 |
Token | well |
Token ID | 880 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
irtual | +0.063 |
� | +0.060 |
Reply | +0.060 |
roll | +0.056 |
Stra | +0.056 |
Neg logit contributions | |
merce | -0.051 |
bour | -0.050 |
onial | -0.049 |
agher | -0.044 |
otor | -0.044 |
Token | as |
Token ID | 355 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
� | +3.662 |
Reply | +3.647 |
irtual | +3.594 |
roll | +3.463 |
Stra | +3.295 |
Neg logit contributions | |
merce | -7.643 |
onial | -7.326 |
bour | -7.212 |
otor | -6.763 |
agher | -6.635 |
Token | updates |
Token ID | 5992 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
irtual | +0.354 |
� | +0.294 |
Reply | +0.291 |
roll | +0.196 |
Stra | +0.186 |
Neg logit contributions | |
merce | -2.567 |
bour | -2.525 |
onial | -2.511 |
agher | -2.376 |
otor | -2.376 |
Token | regarding |
Token ID | 5115 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
irtual | +1.052 |
� | +1.014 |
Reply | +1.005 |
roll | +0.931 |
Stra | +0.909 |
Neg logit contributions | |
merce | -1.725 |
bour | -1.680 |
onial | -1.672 |
otor | -1.544 |
agher | -1.542 |
Token | the |
Token ID | 262 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
irtual | +1.959 |
� | +1.929 |
Reply | +1.916 |
roll | +1.812 |
Stra | +1.776 |
Neg logit contributions | |
merce | -2.261 |
onial | -2.165 |
bour | -2.164 |
agher | -1.968 |
otor | -1.966 |
Token | future |
Token ID | 2003 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
irtual | +0.589 |
� | +0.567 |
Reply | +0.565 |
roll | +0.531 |
Stra | +0.523 |
Neg logit contributions | |
merce | -0.590 |
bour | -0.575 |
onial | -0.570 |
otor | -0.516 |
agher | -0.513 |
Token | body |
Token ID | 1767 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
irtual | +0.083 |
� | +0.080 |
Reply | +0.080 |
roll | +0.075 |
Stra | +0.074 |
Neg logit contributions | |
merce | -0.090 |
bour | -0.088 |
onial | -0.087 |
otor | -0.079 |
agher | -0.079 |
Token | modification |
Token ID | 17613 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
irtual | +0.240 |
� | +0.230 |
Reply | +0.230 |
roll | +0.213 |
Stra | +0.210 |
Neg logit contributions | |
merce | -0.309 |
bour | -0.300 |
onial | -0.299 |
otor | -0.275 |
agher | -0.274 |
Token | community |
Token ID | 2055 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
merce | +0.896 |
bour | +0.860 |
onial | +0.856 |
otor | +0.763 |
agher | +0.754 |
Neg logit contributions | |
irtual | -1.288 |
� | -1.253 |
Reply | -1.248 |
roll | -1.186 |
Stra | -1.170 |
Token | , |
Token ID | 11 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
merce | +0.740 |
bour | +0.717 |
onial | +0.715 |
agher | +0.651 |
otor | +0.651 |
Neg logit contributions | |
irtual | -0.626 |
� | -0.602 |
Reply | -0.599 |
roll | -0.561 |
Stra | -0.553 |
Token | as |
Token ID | 355 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
irtual | +0.039 |
� | +0.037 |
Reply | +0.037 |
roll | +0.034 |
Stra | +0.033 |
Neg logit contributions | |
merce | -0.066 |
bour | -0.064 |
onial | -0.064 |
agher | -0.059 |
otor | -0.059 |
Token | well |
Token ID | 880 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
merce | +0.297 |
bour | +0.288 |
onial | +0.285 |
agher | +0.257 |
otor | +0.257 |
Neg logit contributions | |
irtual | -0.322 |
� | -0.312 |
Reply | -0.311 |
roll | -0.294 |
Stra | -0.289 |
Token | as |
Token ID | 355 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
� | +4.236 |
irtual | +4.233 |
Reply | +4.093 |
roll | +3.939 |
Stra | +3.766 |
Neg logit contributions | |
merce | -6.721 |
bour | -6.681 |
onial | -6.649 |
otor | -6.054 |
agher | -6.025 |
Token | from |
Token ID | 422 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
irtual | +0.877 |
� | +0.853 |
Reply | +0.848 |
roll | +0.798 |
Stra | +0.785 |
Neg logit contributions | |
merce | -0.970 |
bour | -0.941 |
onial | -0.936 |
otor | -0.848 |
agher | -0.847 |
Token | those |
Token ID | 883 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
merce | +0.315 |
bour | +0.305 |
onial | +0.304 |
otor | +0.276 |
agher | +0.275 |
Neg logit contributions | |
irtual | -0.291 |
� | -0.281 |
Reply | -0.280 |
roll | -0.263 |
Stra | -0.258 |
Token | in |
Token ID | 287 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
irtual | +1.134 |
� | +1.099 |
Reply | +1.086 |
roll | +1.010 |
Stra | +0.990 |
Neg logit contributions | |
merce | -1.786 |
bour | -1.741 |
onial | -1.733 |
otor | -1.595 |
agher | -1.591 |
Token | the |
Token ID | 262 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
merce | +0.686 |
bour | +0.664 |
onial | +0.661 |
otor | +0.602 |
agher | +0.600 |
Neg logit contributions | |
irtual | -0.615 |
� | -0.595 |
Reply | -0.592 |
roll | -0.557 |
Stra | -0.547 |
Token | and |
Token ID | 290 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
merce | +1.897 |
bour | +1.845 |
onial | +1.834 |
agher | +1.662 |
otor | +1.660 |
Neg logit contributions | |
irtual | -1.669 |
� | -1.615 |
Reply | -1.607 |
roll | -1.499 |
Stra | -1.484 |
Token | stage |
Token ID | 3800 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
merce | +0.436 |
bour | +0.424 |
onial | +0.421 |
otor | +0.382 |
agher | +0.382 |
Neg logit contributions | |
irtual | -0.392 |
� | -0.379 |
Reply | -0.378 |
roll | -0.354 |
Stra | -0.349 |
Token | acts |
Token ID | 6529 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
merce | +1.535 |
bour | +1.497 |
onial | +1.486 |
otor | +1.357 |
agher | +1.353 |
Neg logit contributions | |
irtual | -1.256 |
� | -1.212 |
Reply | -1.207 |
roll | -1.124 |
Stra | -1.109 |
Token | , |
Token ID | 11 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
irtual | +0.253 |
� | +0.245 |
Reply | +0.244 |
roll | +0.230 |
Stra | +0.226 |
Neg logit contributions | |
merce | -0.274 |
bour | -0.266 |
onial | -0.264 |
otor | -0.240 |
agher | -0.239 |
Token | as |
Token ID | 355 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
irtual | +0.056 |
� | +0.054 |
Reply | +0.054 |
roll | +0.050 |
Stra | +0.049 |
Neg logit contributions | |
merce | -0.068 |
bour | -0.066 |
onial | -0.066 |
otor | -0.060 |
agher | -0.060 |
Token | well |
Token ID | 880 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
merce | +0.239 |
bour | +0.232 |
onial | +0.230 |
otor | +0.208 |
agher | +0.207 |
Neg logit contributions | |
irtual | -0.252 |
� | -0.245 |
Reply | -0.244 |
roll | -0.230 |
Stra | -0.227 |
Token | as |
Token ID | 355 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
irtual | +3.914 |
� | +3.863 |
Reply | +3.749 |
roll | +3.643 |
ELL | +3.410 |
Neg logit contributions | |
merce | -7.086 |
onial | -6.931 |
bour | -6.927 |
otor | -6.379 |
agher | -6.352 |
Token | private |
Token ID | 2839 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
irtual | +0.564 |
� | +0.547 |
Reply | +0.543 |
roll | +0.513 |
Stra | +0.502 |
Neg logit contributions | |
merce | -0.640 |
bour | -0.619 |
onial | -0.617 |
otor | -0.560 |
agher | -0.559 |
Token | space |
Token ID | 2272 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
merce | +0.953 |
bour | +0.927 |
onial | +0.921 |
otor | +0.840 |
agher | +0.837 |
Neg logit contributions | |
irtual | -0.825 |
� | -0.793 |
Reply | -0.793 |
roll | -0.740 |
Stra | -0.729 |
Token | for |
Token ID | 329 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
irtual | +0.444 |
� | +0.431 |
Reply | +0.426 |
roll | +0.402 |
Stra | +0.392 |
Neg logit contributions | |
merce | -0.561 |
bour | -0.542 |
onial | -0.540 |
otor | -0.494 |
agher | -0.493 |
Token | rent |
Token ID | 5602 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
irtual | +0.542 |
� | +0.526 |
Reply | +0.523 |
roll | +0.494 |
Stra | +0.484 |
Neg logit contributions | |
merce | -0.595 |
bour | -0.575 |
onial | -0.573 |
agher | -0.519 |
otor | -0.519 |
Token | official |
Token ID | 1743 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
irtual | +0.118 |
� | +0.114 |
Reply | +0.113 |
roll | +0.107 |
Stra | +0.106 |
Neg logit contributions | |
merce | -0.091 |
onial | -0.089 |
bour | -0.089 |
otor | -0.079 |
agher | -0.078 |
Token | statement |
Token ID | 2643 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
merce | +1.224 |
bour | +1.197 |
onial | +1.196 |
agher | +1.068 |
otor | +1.068 |
Neg logit contributions | |
irtual | -1.302 |
� | -1.247 |
Reply | -1.233 |
roll | -1.169 |
Stra | -1.148 |
Token | soon |
Token ID | 2582 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
irtual | +0.139 |
� | +0.129 |
Reply | +0.129 |
roll | +0.117 |
rules | +0.114 |
Neg logit contributions | |
merce | -0.229 |
bour | -0.227 |
onial | -0.224 |
otor | -0.207 |
agher | -0.206 |
Token | . |
Token ID | 13 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
irtual | +1.566 |
� | +1.514 |
Reply | +1.506 |
roll | +1.423 |
Stra | +1.400 |
Neg logit contributions | |
merce | -1.453 |
bour | -1.413 |
onial | -1.402 |
otor | -1.265 |
agher | -1.261 |
Token | As |
Token ID | 1081 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
irtual | +0.474 |
� | +0.459 |
Reply | +0.458 |
roll | +0.426 |
Stra | +0.418 |
Neg logit contributions | |
merce | -0.669 |
bour | -0.648 |
onial | -0.647 |
otor | -0.592 |
agher | -0.591 |
Token | well |
Token ID | 880 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
merce | +0.314 |
bour | +0.309 |
onial | +0.304 |
agher | +0.277 |
otor | +0.272 |
Neg logit contributions | |
irtual | -0.396 |
� | -0.379 |
Reply | -0.377 |
roll | -0.354 |
Stra | -0.352 |
Token | as |
Token ID | 355 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Reply | +3.740 |
� | +3.713 |
irtual | +3.639 |
roll | +3.512 |
Stra | +3.342 |
Neg logit contributions | |
merce | -7.511 |
onial | -7.196 |
bour | -7.101 |
otor | -6.619 |
agher | -6.522 |
Token | updates |
Token ID | 5992 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
irtual | +0.368 |
� | +0.306 |
Reply | +0.302 |
roll | +0.205 |
Stra | +0.196 |
Neg logit contributions | |
merce | -2.652 |
bour | -2.609 |
onial | -2.596 |
otor | -2.457 |
agher | -2.454 |
Token | regarding |
Token ID | 5115 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
irtual | +1.146 |
� | +1.102 |
Reply | +1.095 |
roll | +1.014 |
Stra | +0.991 |
Neg logit contributions | |
merce | -1.838 |
bour | -1.791 |
onial | -1.782 |
otor | -1.644 |
agher | -1.641 |
Token | the |
Token ID | 262 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
irtual | +1.894 |
� | +1.863 |
Reply | +1.853 |
roll | +1.750 |
Stra | +1.716 |
Neg logit contributions | |
merce | -2.162 |
onial | -2.072 |
bour | -2.071 |
agher | -1.878 |
otor | -1.878 |
Token | future |
Token ID | 2003 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
irtual | +0.527 |
� | +0.505 |
Reply | +0.502 |
roll | +0.471 |
Stra | +0.466 |
Neg logit contributions | |
merce | -0.502 |
bour | -0.492 |
onial | -0.487 |
otor | -0.441 |
agher | -0.436 |
Token | be |
Token ID | 307 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
merce | +0.102 |
bour | +0.099 |
onial | +0.098 |
otor | +0.089 |
agher | +0.089 |
Neg logit contributions | |
irtual | -0.091 |
� | -0.088 |
Reply | -0.088 |
roll | -0.083 |
Stra | -0.081 |
Token | in |
Token ID | 287 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
irtual | +0.346 |
� | +0.335 |
Reply | +0.333 |
roll | +0.313 |
Stra | +0.307 |
Neg logit contributions | |
merce | -0.389 |
bour | -0.378 |
onial | -0.375 |
otor | -0.342 |
agher | -0.341 |
Token | love |
Token ID | 1842 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
merce | +0.275 |
bour | +0.267 |
onial | +0.266 |
otor | +0.241 |
agher | +0.240 |
Neg logit contributions | |
irtual | -0.259 |
� | -0.251 |
Reply | -0.250 |
roll | -0.235 |
Stra | -0.232 |
Token | affairs |
Token ID | 9674 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
irtual | +0.698 |
� | +0.674 |
Reply | +0.670 |
roll | +0.625 |
Stra | +0.613 |
Neg logit contributions | |
merce | -0.958 |
bour | -0.932 |
onial | -0.927 |
otor | -0.850 |
agher | -0.848 |
Token | as |
Token ID | 355 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
irtual | +0.253 |
� | +0.245 |
Reply | +0.243 |
roll | +0.228 |
Stra | +0.224 |
Neg logit contributions | |
merce | -0.301 |
bour | -0.292 |
onial | -0.291 |
otor | -0.265 |
agher | -0.264 |
Token | well |
Token ID | 880 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
irtual | +0.319 |
� | +0.309 |
Reply | +0.307 |
roll | +0.289 |
Stra | +0.284 |
Neg logit contributions | |
merce | -0.356 |
bour | -0.347 |
onial | -0.344 |
otor | -0.313 |
agher | -0.312 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
irtual | +4.770 |
� | +4.651 |
Reply | +4.606 |
roll | +4.324 |
Stra | +4.213 |
Neg logit contributions | |
merce | -6.302 |
bour | -6.143 |
onial | -6.129 |
otor | -5.560 |
agher | -5.553 |
Token | so |
Token ID | 523 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
irtual | +0.449 |
� | +0.434 |
Reply | +0.431 |
roll | +0.404 |
Stra | +0.395 |
Neg logit contributions | |
merce | -0.564 |
bour | -0.549 |
onial | -0.546 |
otor | -0.499 |
agher | -0.499 |
Token | it |
Token ID | 340 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
merce | +0.041 |
bour | +0.040 |
onial | +0.040 |
otor | +0.037 |
agher | +0.037 |
Neg logit contributions | |
irtual | -0.033 |
� | -0.032 |
Reply | -0.032 |
roll | -0.030 |
Stra | -0.029 |
Token | isn |
Token ID | 2125 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
irtual | +1.085 |
� | +1.045 |
Reply | +1.039 |
roll | +0.968 |
Stra | +0.947 |
Neg logit contributions | |
merce | -1.563 |
bour | -1.521 |
onial | -1.514 |
otor | -1.391 |
agher | -1.388 |
Token | � |
Token ID | 447 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
bour | +0.591 |
merce | +0.583 |
onial | +0.573 |
otor | +0.526 |
agher | +0.522 |
Neg logit contributions | |
irtual | -0.606 |
� | -0.562 |
Reply | -0.561 |
roll | -0.524 |
rules | -0.518 |
Token | are |
Token ID | 389 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
merce | +0.211 |
bour | +0.205 |
onial | +0.204 |
otor | +0.187 |
agher | +0.186 |
Neg logit contributions | |
irtual | -0.158 |
� | -0.152 |
Reply | -0.152 |
roll | -0.141 |
Stra | -0.139 |
Token | extremely |
Token ID | 4457 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
merce | +0.680 |
bour | +0.661 |
onial | +0.658 |
otor | +0.600 |
agher | +0.600 |
Neg logit contributions | |
irtual | -0.563 |
� | -0.543 |
Reply | -0.541 |
roll | -0.507 |
Stra | -0.497 |
Token | passionate |
Token ID | 15347 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
irtual | +0.701 |
� | +0.682 |
Reply | +0.679 |
roll | +0.642 |
Stra | +0.631 |
Neg logit contributions | |
merce | -0.668 |
bour | -0.643 |
onial | -0.640 |
otor | -0.576 |
agher | -0.573 |
Token | about |
Token ID | 546 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
merce | +0.940 |
bour | +0.918 |
onial | +0.914 |
otor | +0.841 |
agher | +0.835 |
Neg logit contributions | |
irtual | -0.650 |
� | -0.623 |
Reply | -0.623 |
roll | -0.578 |
Stra | -0.566 |
Token | as |
Token ID | 355 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
irtual | +1.272 |
� | +1.236 |
Reply | +1.219 |
roll | +1.152 |
Stra | +1.129 |
Neg logit contributions | |
merce | -1.489 |
bour | -1.443 |
onial | -1.440 |
agher | -1.305 |
otor | -1.299 |
Token | well |
Token ID | 880 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
irtual | +0.388 |
� | +0.377 |
Reply | +0.374 |
roll | +0.354 |
Stra | +0.348 |
Neg logit contributions | |
merce | -0.375 |
bour | -0.362 |
onial | -0.361 |
otor | -0.325 |
agher | -0.324 |
Token | . |
Token ID | 13 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
irtual | +5.003 |
� | +4.925 |
Reply | +4.815 |
roll | +4.602 |
Stra | +4.483 |
Neg logit contributions | |
merce | -6.005 |
bour | -5.908 |
onial | -5.802 |
agher | -5.309 |
otor | -5.245 |
Token |
|
Token ID | 198 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
irtual | +0.149 |
� | +0.144 |
Reply | +0.143 |
roll | +0.133 |
Stra | +0.131 |
Neg logit contributions | |
merce | -0.195 |
bour | -0.191 |
onial | -0.189 |
otor | -0.173 |
agher | -0.173 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
bour | +0.446 |
merce | +0.439 |
onial | +0.435 |
otor | +0.399 |
agher | +0.397 |
Neg logit contributions | |
irtual | -0.413 |
� | -0.384 |
Reply | -0.378 |
roll | -0.352 |
rules | -0.346 |
Token | The |
Token ID | 464 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
merce | +0.079 |
bour | +0.077 |
onial | +0.077 |
otor | +0.071 |
agher | +0.071 |
Neg logit contributions | |
irtual | -0.047 |
� | -0.045 |
Reply | -0.045 |
roll | -0.041 |
Stra | -0.040 |
Token | first |
Token ID | 717 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
irtual | +0.266 |
� | +0.257 |
Reply | +0.256 |
roll | +0.241 |
Stra | +0.237 |
Neg logit contributions | |
merce | -0.295 |
bour | -0.286 |
onial | -0.285 |
otor | -0.258 |
agher | -0.258 |
Token | l |
Token ID | 300 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
irtual | +0.139 |
� | +0.134 |
Reply | +0.133 |
roll | +0.124 |
Stra | +0.122 |
Neg logit contributions | |
merce | -0.182 |
bour | -0.177 |
onial | -0.176 |
otor | -0.161 |
agher | -0.161 |
Token | ' |
Token ID | 6 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
merce | +0.062 |
bour | +0.061 |
onial | +0.060 |
otor | +0.054 |
agher | +0.054 |
Neg logit contributions | |
irtual | -0.071 |
� | -0.069 |
Reply | -0.069 |
roll | -0.065 |
Stra | -0.064 |
Token | acc |
Token ID | 4134 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
irtual | +1.417 |
� | +1.374 |
Reply | +1.368 |
roll | +1.287 |
Stra | +1.262 |
Neg logit contributions | |
merce | -1.613 |
bour | -1.558 |
onial | -1.552 |
otor | -1.411 |
agher | -1.406 |
Token | è |
Token ID | 14064 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
irtual | +1.536 |
� | +1.495 |
Reply | +1.489 |
roll | +1.417 |
Stra | +1.395 |
Neg logit contributions | |
merce | -1.170 |
bour | -1.126 |
onial | -1.118 |
otor | -0.992 |
agher | -0.990 |
Token | s |
Token ID | 82 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
irtual | +1.191 |
� | +1.157 |
Reply | +1.156 |
roll | +1.104 |
Stra | +1.078 |
Neg logit contributions | |
merce | -0.945 |
bour | -0.904 |
onial | -0.902 |
otor | -0.809 |
agher | -0.805 |
Token | aux |
Token ID | 27506 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
irtual | +1.070 |
� | +1.034 |
Reply | +1.028 |
roll | +0.962 |
Stra | +0.943 |
Neg logit contributions | |
merce | -1.390 |
bour | -1.350 |
onial | -1.343 |
otor | -1.230 |
agher | -1.227 |
Token | v |
Token ID | 410 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
irtual | +5.202 |
� | +5.077 |
Reply | +5.034 |
roll | +4.800 |
Stra | +4.658 |
Neg logit contributions | |
merce | -5.854 |
onial | -5.577 |
bour | -5.550 |
otor | -5.084 |
agher | -5.049 |
Token | ais |
Token ID | 15152 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
irtual | +1.915 |
� | +1.847 |
Reply | +1.841 |
roll | +1.742 |
Stra | +1.702 |
Neg logit contributions | |
merce | -2.190 |
bour | -2.119 |
onial | -2.108 |
otor | -1.916 |
agher | -1.911 |
Token | se |
Token ID | 325 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
irtual | +1.345 |
� | +1.303 |
Reply | +1.297 |
roll | +1.221 |
Stra | +1.199 |
Neg logit contributions | |
merce | -1.510 |
bour | -1.460 |
onial | -1.453 |
otor | -1.322 |
agher | -1.319 |
Token | aux |
Token ID | 14644 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
irtual | +0.624 |
� | +0.589 |
Reply | +0.584 |
roll | +0.519 |
Stra | +0.502 |
Neg logit contributions | |
merce | -1.718 |
bour | -1.681 |
onial | -1.674 |
otor | -1.565 |
agher | -1.563 |
Token | f |
Token ID | 277 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
irtual | +2.389 |
� | +2.315 |
Reply | +2.309 |
roll | +2.171 |
Stra | +2.123 |
Neg logit contributions | |
merce | -3.138 |
bour | -3.022 |
onial | -3.018 |
otor | -2.768 |
agher | -2.755 |
Token | ind |
Token ID | 521 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
merce | +0.230 |
bour | +0.224 |
onial | +0.222 |
otor | +0.202 |
agher | +0.201 |
Neg logit contributions | |
irtual | -0.219 |
� | -0.212 |
Reply | -0.211 |
roll | -0.199 |
Stra | -0.195 |
Token | ies |
Token ID | 444 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
irtual | +0.951 |
� | +0.922 |
Reply | +0.919 |
roll | +0.877 |
Stra | +0.849 |
Neg logit contributions | |
merce | -1.058 |
bour | -1.031 |
onial | -1.021 |
agher | -0.930 |
otor | -0.920 |
Token | � |
Token ID | 447 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
irtual | +0.448 |
� | +0.434 |
Reply | +0.431 |
roll | +0.405 |
Stra | +0.397 |
Neg logit contributions | |
merce | -0.540 |
bour | -0.524 |
onial | -0.522 |
otor | -0.476 |
agher | -0.475 |
Token | � |
Token ID | 251 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
merce | +0.840 |
bour | +0.822 |
onial | +0.818 |
otor | +0.751 |
agher | +0.747 |
Neg logit contributions | |
irtual | -0.592 |
� | -0.558 |
Reply | -0.554 |
roll | -0.518 |
Stra | -0.511 |
Token | as |
Token ID | 355 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
irtual | +0.517 |
� | +0.501 |
Reply | +0.498 |
roll | +0.468 |
Stra | +0.459 |
Neg logit contributions | |
merce | -0.606 |
bour | -0.587 |
onial | -0.585 |
otor | -0.532 |
agher | -0.532 |
Token | well |
Token ID | 880 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
irtual | +0.110 |
� | +0.107 |
Reply | +0.106 |
roll | +0.100 |
Stra | +0.098 |
Neg logit contributions | |
merce | -0.121 |
bour | -0.117 |
onial | -0.117 |
otor | -0.106 |
agher | -0.106 |
Token | as |
Token ID | 355 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
irtual | +3.773 |
� | +3.673 |
Reply | +3.599 |
roll | +3.470 |
Stra | +3.246 |
Neg logit contributions | |
merce | -7.110 |
onial | -6.953 |
bour | -6.946 |
agher | -6.430 |
otor | -6.368 |
Token | new |
Token ID | 649 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
irtual | +0.939 |
� | +0.912 |
Reply | +0.908 |
roll | +0.856 |
Stra | +0.840 |
Neg logit contributions | |
merce | -1.001 |
bour | -0.965 |
onial | -0.964 |
agher | -0.872 |
otor | -0.871 |
Token | games |
Token ID | 1830 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
irtual | +1.271 |
� | +1.232 |
Reply | +1.222 |
roll | +1.150 |
Stra | +1.126 |
Neg logit contributions | |
merce | -1.544 |
bour | -1.495 |
onial | -1.491 |
agher | -1.358 |
otor | -1.357 |
Token | at |
Token ID | 379 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
irtual | +0.933 |
� | +0.906 |
Reply | +0.893 |
roll | +0.844 |
Stra | +0.825 |
Neg logit contributions | |
merce | -1.214 |
bour | -1.176 |
onial | -1.171 |
agher | -1.072 |
otor | -1.071 |
Token | Indie |
Token ID | 31527 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
irtual | +0.167 |
� | +0.162 |
Reply | +0.161 |
roll | +0.151 |
Stra | +0.148 |
Neg logit contributions | |
merce | -0.192 |
bour | -0.186 |
onial | -0.185 |
otor | -0.168 |
agher | -0.168 |
Token | Motion |
Token ID | 20843 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
merce | +0.043 |
bour | +0.041 |
onial | +0.041 |
otor | +0.037 |
agher | +0.037 |
Neg logit contributions | |
irtual | -0.038 |
� | -0.036 |
Reply | -0.036 |
roll | -0.034 |
Stra | -0.033 |
Token | Plus |
Token ID | 17860 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
merce | +0.258 |
bour | +0.251 |
onial | +0.249 |
otor | +0.229 |
agher | +0.228 |
Neg logit contributions | |
irtual | -0.190 |
� | -0.183 |
Reply | -0.182 |
roll | -0.170 |
Stra | -0.166 |
Token | technology |
Token ID | 3037 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
irtual | +2.566 |
� | +2.478 |
Reply | +2.470 |
roll | +2.351 |
Stra | +2.301 |
Neg logit contributions | |
merce | -2.892 |
bour | -2.807 |
onial | -2.795 |
agher | -2.529 |
otor | -2.518 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
merce | +0.875 |
bour | +0.848 |
onial | +0.845 |
otor | +0.770 |
agher | +0.767 |
Neg logit contributions | |
irtual | -0.791 |
� | -0.767 |
Reply | -0.765 |
roll | -0.713 |
Stra | -0.703 |
Token | as |
Token ID | 355 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
merce | +0.439 |
bour | +0.427 |
onial | +0.424 |
otor | +0.386 |
agher | +0.385 |
Neg logit contributions | |
irtual | -0.393 |
� | -0.382 |
Reply | -0.380 |
roll | -0.355 |
Stra | -0.349 |
Token | well |
Token ID | 880 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
merce | +0.534 |
bour | +0.517 |
onial | +0.514 |
otor | +0.463 |
agher | +0.462 |
Neg logit contributions | |
irtual | -0.579 |
� | -0.563 |
Reply | -0.561 |
roll | -0.529 |
Stra | -0.520 |
Token | as |
Token ID | 355 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
irtual | +3.629 |
� | +3.597 |
Reply | +3.579 |
roll | +3.406 |
Stra | +3.247 |
Neg logit contributions | |
merce | -7.254 |
onial | -7.004 |
bour | -6.981 |
otor | -6.493 |
agher | -6.423 |
Token | creative |
Token ID | 7325 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
irtual | +0.923 |
� | +0.894 |
Reply | +0.889 |
roll | +0.842 |
Stra | +0.827 |
Neg logit contributions | |
merce | -0.977 |
bour | -0.947 |
onial | -0.942 |
otor | -0.852 |
agher | -0.851 |
Token | uses |
Token ID | 3544 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
merce | +0.556 |
bour | +0.539 |
onial | +0.535 |
otor | +0.486 |
agher | +0.483 |
Neg logit contributions | |
irtual | -0.519 |
� | -0.503 |
Reply | -0.501 |
roll | -0.470 |
Stra | -0.462 |
Token | of |
Token ID | 286 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
irtual | +0.317 |
� | +0.306 |
Reply | +0.302 |
roll | +0.283 |
Stra | +0.277 |
Neg logit contributions | |
merce | -0.457 |
bour | -0.445 |
onial | -0.443 |
agher | -0.407 |
otor | -0.407 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
irtual | +0.328 |
� | +0.318 |
Reply | +0.316 |
roll | +0.298 |
Stra | +0.293 |
Neg logit contributions | |
merce | -0.354 |
bour | -0.343 |
onial | -0.341 |
otor | -0.309 |
agher | -0.309 |
Token | group |
Token ID | 1448 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
irtual | +1.764 |
� | +1.727 |
Reply | +1.717 |
roll | +1.620 |
Stra | +1.585 |
Neg logit contributions | |
merce | -2.031 |
bour | -1.946 |
onial | -1.943 |
agher | -1.773 |
otor | -1.765 |
Token | of |
Token ID | 286 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
irtual | +1.290 |
� | +1.248 |
Reply | +1.239 |
roll | +1.168 |
Stra | +1.133 |
Neg logit contributions | |
merce | -1.832 |
bour | -1.774 |
onial | -1.767 |
otor | -1.614 |
agher | -1.613 |
Token | people |
Token ID | 661 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
irtual | +0.169 |
� | +0.164 |
Reply | +0.163 |
roll | +0.154 |
Stra | +0.151 |
Neg logit contributions | |
merce | -0.166 |
bour | -0.162 |
onial | -0.161 |
otor | -0.145 |
agher | -0.145 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
irtual | +1.080 |
� | +1.046 |
Reply | +1.037 |
roll | +0.978 |
Stra | +0.950 |
Neg logit contributions | |
merce | -1.508 |
bour | -1.462 |
onial | -1.455 |
otor | -1.330 |
agher | -1.326 |
Token | as |
Token ID | 355 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
irtual | +0.220 |
� | +0.213 |
Reply | +0.212 |
roll | +0.198 |
Stra | +0.194 |
Neg logit contributions | |
merce | -0.284 |
bour | -0.276 |
onial | -0.274 |
otor | -0.251 |
agher | -0.251 |
Token | well |
Token ID | 880 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
merce | +0.081 |
bour | +0.078 |
onial | +0.078 |
otor | +0.070 |
agher | +0.070 |
Neg logit contributions | |
irtual | -0.080 |
� | -0.077 |
Reply | -0.077 |
roll | -0.073 |
Stra | -0.072 |
Token | as |
Token ID | 355 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
irtual | +3.565 |
� | +3.426 |
Reply | +3.351 |
roll | +3.225 |
Stra | +3.052 |
Neg logit contributions | |
merce | -7.171 |
bour | -7.051 |
onial | -7.045 |
agher | -6.479 |
otor | -6.473 |
Token | if |
Token ID | 611 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
irtual | +0.962 |
� | +0.933 |
Reply | +0.927 |
roll | +0.873 |
Stra | +0.857 |
Neg logit contributions | |
merce | -1.098 |
bour | -1.064 |
onial | -1.059 |
otor | -0.962 |
agher | -0.960 |
Token | you |
Token ID | 345 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
irtual | +1.374 |
� | +1.323 |
Reply | +1.301 |
roll | +1.246 |
Stra | +1.205 |
Neg logit contributions | |
merce | -1.999 |
bour | -1.923 |
onial | -1.918 |
otor | -1.761 |
agher | -1.759 |
Token | don |
Token ID | 836 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
irtual | +0.293 |
� | +0.283 |
Reply | +0.281 |
roll | +0.263 |
Stra | +0.257 |
Neg logit contributions | |
merce | -0.406 |
bour | -0.394 |
onial | -0.393 |
otor | -0.360 |
agher | -0.360 |
Token | 't |
Token ID | 470 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
bour | +0.359 |
merce | +0.358 |
onial | +0.352 |
otor | +0.321 |
agher | +0.319 |
Neg logit contributions | |
irtual | -0.358 |
� | -0.339 |
Reply | -0.335 |
roll | -0.313 |
Stra | -0.310 |
Token | The |
Token ID | 383 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
merce | +0.671 |
bour | +0.652 |
onial | +0.648 |
otor | +0.593 |
agher | +0.593 |
Neg logit contributions | |
irtual | -0.515 |
� | -0.496 |
Reply | -0.492 |
roll | -0.458 |
Stra | -0.452 |
Token | guide |
Token ID | 5698 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
irtual | +0.695 |
� | +0.671 |
Reply | +0.666 |
roll | +0.622 |
Stra | +0.610 |
Neg logit contributions | |
merce | -0.918 |
bour | -0.894 |
onial | -0.889 |
otor | -0.814 |
agher | -0.813 |
Token | book |
Token ID | 2070 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
merce | +1.071 |
bour | +1.051 |
onial | +1.048 |
agher | +0.961 |
otor | +0.960 |
Neg logit contributions | |
irtual | -0.773 |
� | -0.751 |
Reply | -0.747 |
roll | -0.681 |
Stra | -0.678 |
Token | , |
Token ID | 11 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
merce | +0.086 |
bour | +0.084 |
onial | +0.084 |
agher | +0.077 |
otor | +0.077 |
Neg logit contributions | |
irtual | -0.061 |
� | -0.059 |
Reply | -0.059 |
roll | -0.054 |
Stra | -0.053 |
Token | as |
Token ID | 355 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
irtual | +0.212 |
� | +0.205 |
Reply | +0.204 |
roll | +0.189 |
Stra | +0.187 |
Neg logit contributions | |
merce | -0.260 |
bour | -0.254 |
onial | -0.253 |
agher | -0.230 |
otor | -0.230 |
Token | well |
Token ID | 880 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
merce | +0.091 |
bour | +0.089 |
onial | +0.088 |
otor | +0.080 |
agher | +0.080 |
Neg logit contributions | |
irtual | -0.078 |
� | -0.075 |
Reply | -0.075 |
roll | -0.070 |
Stra | -0.069 |
Token | as |
Token ID | 355 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
irtual | +3.782 |
� | +3.702 |
Reply | +3.691 |
roll | +3.502 |
Stra | +3.300 |
Neg logit contributions | |
merce | -7.056 |
bour | -6.867 |
onial | -6.845 |
otor | -6.336 |
agher | -6.279 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
irtual | +1.027 |
� | +0.994 |
Reply | +0.991 |
roll | +0.934 |
Stra | +0.914 |
Neg logit contributions | |
merce | -1.142 |
bour | -1.108 |
onial | -1.103 |
otor | -1.001 |
agher | -0.998 |
Token | programs |
Token ID | 4056 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
irtual | +0.275 |
� | +0.266 |
Reply | +0.264 |
roll | +0.247 |
Stra | +0.244 |
Neg logit contributions | |
merce | -0.327 |
bour | -0.318 |
onial | -0.316 |
otor | -0.288 |
agher | -0.288 |
Token | at |
Token ID | 379 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
merce | +1.814 |
bour | +1.765 |
onial | +1.755 |
otor | +1.603 |
agher | +1.594 |
Neg logit contributions | |
irtual | -1.487 |
Reply | -1.438 |
� | -1.436 |
roll | -1.332 |
Stra | -1.317 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
merce | +0.440 |
bour | +0.428 |
onial | +0.425 |
otor | +0.388 |
agher | +0.388 |
Neg logit contributions | |
irtual | -0.359 |
� | -0.347 |
Reply | -0.345 |
roll | -0.322 |
Stra | -0.317 |
Token | European |
Token ID | 3427 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
merce | +0.504 |
bour | +0.491 |
onial | +0.488 |
otor | +0.445 |
agher | +0.444 |
Neg logit contributions | |
irtual | -0.440 |
� | -0.426 |
Reply | -0.423 |
roll | -0.397 |
Stra | -0.391 |
Token | Knights |
Token ID | 15188 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
merce | +0.922 |
bour | +0.893 |
onial | +0.890 |
otor | +0.801 |
agher | +0.800 |
Neg logit contributions | |
irtual | -0.976 |
� | -0.946 |
Reply | -0.941 |
roll | -0.888 |
Stra | -0.874 |
Token | Project |
Token ID | 4935 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
merce | +0.522 |
bour | +0.509 |
onial | +0.506 |
otor | +0.463 |
agher | +0.463 |
Neg logit contributions | |
irtual | -0.413 |
� | -0.398 |
Reply | -0.394 |
roll | -0.367 |
Stra | -0.362 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
merce | +2.706 |
bour | +2.646 |
onial | +2.630 |
agher | +2.398 |
otor | +2.393 |
Neg logit contributions | |
irtual | -2.281 |
� | -2.191 |
Reply | -2.160 |
rules | -2.009 |
roll | -2.006 |
Token | as |
Token ID | 355 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
merce | +0.448 |
bour | +0.439 |
onial | +0.436 |
agher | +0.403 |
otor | +0.403 |
Neg logit contributions | |
irtual | -0.274 |
� | -0.263 |
Reply | -0.261 |
roll | -0.239 |
Stra | -0.235 |
Token | well |
Token ID | 880 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
merce | +0.259 |
bour | +0.252 |
onial | +0.250 |
otor | +0.226 |
agher | +0.225 |
Neg logit contributions | |
irtual | -0.272 |
� | -0.264 |
Reply | -0.263 |
roll | -0.247 |
Stra | -0.244 |
Token | as |
Token ID | 355 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
irtual | +3.739 |
Reply | +3.654 |
� | +3.624 |
roll | +3.408 |
Stra | +3.199 |
Neg logit contributions | |
merce | -7.036 |
onial | -6.911 |
bour | -6.875 |
otor | -6.369 |
agher | -6.304 |
Token | info |
Token ID | 7508 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
irtual | +0.952 |
� | +0.922 |
Reply | +0.919 |
roll | +0.863 |
Stra | +0.846 |
Neg logit contributions | |
merce | -1.135 |
bour | -1.101 |
onial | -1.096 |
otor | -1.000 |
agher | -0.996 |
Token | about |
Token ID | 546 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
merce | +0.159 |
bour | +0.155 |
onial | +0.154 |
otor | +0.141 |
agher | +0.141 |
Neg logit contributions | |
irtual | -0.124 |
� | -0.120 |
Reply | -0.119 |
roll | -0.112 |
Stra | -0.110 |
Token | our |
Token ID | 674 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
irtual | +1.282 |
� | +1.244 |
Reply | +1.238 |
roll | +1.163 |
Stra | +1.141 |
Neg logit contributions | |
merce | -1.517 |
bour | -1.469 |
onial | -1.463 |
otor | -1.331 |
agher | -1.327 |
Token | annual |
Token ID | 5079 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
merce | +0.132 |
bour | +0.128 |
onial | +0.128 |
otor | +0.116 |
agher | +0.115 |
Neg logit contributions | |
irtual | -0.123 |
� | -0.119 |
Reply | -0.119 |
roll | -0.112 |
Stra | -0.110 |
Token | roy |
Token ID | 3287 |
Feature activation | +8.86e-03 |
Pos logit contributions | |
merce | +3.465 |
bour | +3.465 |
onial | +3.385 |
agher | +3.084 |
otor | +3.055 |
Neg logit contributions | |
irtual | -3.173 |
� | -3.031 |
Reply | -2.992 |
Stra | -2.752 |
ELL | -2.733 |
Token | al |
Token ID | 282 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
merce | +0.023 |
bour | +0.022 |
onial | +0.022 |
otor | +0.020 |
agher | +0.020 |
Neg logit contributions | |
irtual | -0.015 |
� | -0.015 |
Reply | -0.015 |
roll | -0.014 |
Stra | -0.013 |
Token | Tea |
Token ID | 15777 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
irtual | +1.498 |
� | +1.460 |
Reply | +1.449 |
roll | +1.367 |
Stra | +1.339 |
Neg logit contributions | |
merce | -1.815 |
bour | -1.749 |
onial | -1.747 |
agher | -1.595 |
otor | -1.591 |
Token | ", |
Token ID | 1600 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
merce | +1.403 |
bour | +1.369 |
onial | +1.360 |
otor | +1.251 |
agher | +1.250 |
Neg logit contributions | |
irtual | -0.938 |
� | -0.902 |
Reply | -0.897 |
roll | -0.831 |
Stra | -0.815 |
Token | as |
Token ID | 355 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
irtual | +0.763 |
� | +0.738 |
Reply | +0.734 |
roll | +0.688 |
Stra | +0.675 |
Neg logit contributions | |
merce | -0.955 |
bour | -0.927 |
onial | -0.922 |
otor | -0.844 |
agher | -0.840 |
Token | well |
Token ID | 880 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
irtual | +0.171 |
� | +0.166 |
Reply | +0.165 |
roll | +0.156 |
Stra | +0.153 |
Neg logit contributions | |
merce | -0.169 |
bour | -0.164 |
onial | -0.163 |
agher | -0.147 |
otor | -0.147 |
Token | as |
Token ID | 355 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
irtual | +3.670 |
� | +3.596 |
Reply | +3.526 |
roll | +3.314 |
Stra | +3.177 |
Neg logit contributions | |
merce | -7.009 |
bour | -6.897 |
onial | -6.826 |
otor | -6.372 |
agher | -6.300 |
Token | women |
Token ID | 1466 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
irtual | +1.122 |
� | +1.085 |
Reply | +1.081 |
roll | +1.012 |
Stra | +0.993 |
Neg logit contributions | |
merce | -1.426 |
bour | -1.382 |
onial | -1.375 |
otor | -1.261 |
agher | -1.253 |
Token | 's |
Token ID | 338 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
merce | +0.380 |
bour | +0.369 |
onial | +0.367 |
otor | +0.336 |
agher | +0.335 |
Neg logit contributions | |
irtual | -0.299 |
� | -0.288 |
Reply | -0.287 |
roll | -0.268 |
Stra | -0.263 |
Token | rights |
Token ID | 2489 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
irtual | +1.846 |
� | +1.791 |
Reply | +1.783 |
roll | +1.671 |
Stra | +1.652 |
Neg logit contributions | |
merce | -2.194 |
bour | -2.130 |
onial | -2.123 |
otor | -1.940 |
agher | -1.938 |
Token | and |
Token ID | 290 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
irtual | +0.340 |
� | +0.329 |
Reply | +0.327 |
roll | +0.306 |
Stra | +0.301 |
Neg logit contributions | |
merce | -0.418 |
bour | -0.406 |
onial | -0.404 |
otor | -0.369 |
agher | -0.368 |
Token | official |
Token ID | 1743 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
irtual | +0.010 |
� | +0.009 |
Reply | +0.009 |
roll | +0.009 |
Stra | +0.009 |
Neg logit contributions | |
merce | -0.011 |
bour | -0.011 |
onial | -0.011 |
otor | -0.010 |
agher | -0.010 |
Token | statement |
Token ID | 2643 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
merce | +1.865 |
bour | +1.817 |
onial | +1.808 |
otor | +1.647 |
agher | +1.633 |
Neg logit contributions | |
irtual | -1.631 |
� | -1.578 |
Reply | -1.561 |
roll | -1.468 |
Stra | -1.446 |
Token | soon |
Token ID | 2582 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
merce | +0.442 |
bour | +0.431 |
onial | +0.429 |
otor | +0.392 |
agher | +0.391 |
Neg logit contributions | |
irtual | -0.346 |
� | -0.333 |
Reply | -0.331 |
roll | -0.309 |
Stra | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
irtual | +1.128 |
� | +1.093 |
Reply | +1.090 |
roll | +1.023 |
Stra | +1.005 |
Neg logit contributions | |
merce | -1.275 |
bour | -1.237 |
onial | -1.229 |
otor | -1.118 |
agher | -1.115 |
Token | As |
Token ID | 1081 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
irtual | +0.038 |
� | +0.037 |
Reply | +0.037 |
roll | +0.034 |
Stra | +0.033 |
Neg logit contributions | |
merce | -0.050 |
bour | -0.049 |
onial | -0.049 |
otor | -0.045 |
agher | -0.045 |
Token | well |
Token ID | 880 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
merce | +1.126 |
bour | +1.097 |
onial | +1.086 |
otor | +0.993 |
agher | +0.989 |
Neg logit contributions | |
irtual | -0.921 |
� | -0.889 |
Reply | -0.885 |
roll | -0.828 |
Stra | -0.814 |
Token | as |
Token ID | 355 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
irtual | +3.990 |
Reply | +3.927 |
� | +3.862 |
roll | +3.647 |
Stra | +3.492 |
Neg logit contributions | |
merce | -6.753 |
bour | -6.609 |
onial | -6.605 |
agher | -6.109 |
otor | -6.076 |
Token | updates |
Token ID | 5992 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
irtual | +1.065 |
� | +1.032 |
Reply | +1.031 |
roll | +0.968 |
Stra | +0.950 |
Neg logit contributions | |
merce | -1.201 |
bour | -1.161 |
onial | -1.158 |
otor | -1.052 |
agher | -1.048 |
Token | regarding |
Token ID | 5115 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
irtual | +0.894 |
� | +0.866 |
Reply | +0.862 |
roll | +0.806 |
Stra | +0.789 |
Neg logit contributions | |
merce | -1.204 |
bour | -1.169 |
onial | -1.164 |
otor | -1.066 |
agher | -1.066 |
Token | the |
Token ID | 262 |
Feature activation | -2.87e-03 |
Pos logit contributions | |
irtual | +1.567 |
� | +1.519 |
Reply | +1.517 |
roll | +1.430 |
Stra | +1.398 |
Neg logit contributions | |
merce | -1.756 |
bour | -1.696 |
onial | -1.695 |
otor | -1.534 |
agher | -1.532 |
Token | future |
Token ID | 2003 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
irtual | +0.006 |
� | +0.006 |
Reply | +0.006 |
roll | +0.005 |
Stra | +0.005 |
Neg logit contributions | |
merce | -0.006 |
bour | -0.006 |
onial | -0.006 |
otor | -0.006 |
agher | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
irtual | +1.556 |
� | +1.517 |
Reply | +1.484 |
roll | +1.411 |
Stra | +1.384 |
Neg logit contributions | |
merce | -1.813 |
bour | -1.755 |
onial | -1.747 |
agher | -1.585 |
otor | -1.583 |
Token | other |
Token ID | 584 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
irtual | +1.015 |
� | +0.983 |
Reply | +0.980 |
roll | +0.923 |
Stra | +0.903 |
Neg logit contributions | |
merce | -1.135 |
bour | -1.096 |
onial | -1.095 |
otor | -0.992 |
agher | -0.991 |
Token | merchandise |
Token ID | 20813 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
merce | +1.406 |
bour | +1.374 |
onial | +1.350 |
otor | +1.221 |
agher | +1.212 |
Neg logit contributions | |
irtual | -1.628 |
� | -1.580 |
Reply | -1.572 |
roll | -1.479 |
Stra | -1.464 |
Token | , |
Token ID | 11 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
merce | +1.096 |
bour | +1.063 |
onial | +1.056 |
otor | +0.955 |
agher | +0.953 |
Neg logit contributions | |
irtual | -1.087 |
� | -1.054 |
Reply | -1.049 |
roll | -0.989 |
Stra | -0.973 |
Token | as |
Token ID | 355 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
merce | +0.549 |
bour | +0.536 |
onial | +0.529 |
otor | +0.485 |
agher | +0.485 |
Neg logit contributions | |
irtual | -0.458 |
� | -0.444 |
Reply | -0.442 |
roll | -0.411 |
Stra | -0.405 |
Token | well |
Token ID | 880 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
merce | +0.544 |
bour | +0.529 |
onial | +0.522 |
otor | +0.470 |
agher | +0.470 |
Neg logit contributions | |
irtual | -0.612 |
Reply | -0.595 |
� | -0.595 |
roll | -0.558 |
Stra | -0.552 |
Token | as |
Token ID | 355 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
irtual | +3.712 |
� | +3.679 |
Reply | +3.676 |
roll | +3.495 |
rules | +3.294 |
Neg logit contributions | |
merce | -7.113 |
onial | -6.872 |
bour | -6.806 |
otor | -6.320 |
agher | -6.221 |
Token | in |
Token ID | 287 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
irtual | +0.863 |
� | +0.837 |
Reply | +0.833 |
roll | +0.786 |
Stra | +0.769 |
Neg logit contributions | |
merce | -0.955 |
bour | -0.925 |
onial | -0.922 |
otor | -0.835 |
agher | -0.833 |
Token | - |
Token ID | 12 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
irtual | +0.418 |
� | +0.403 |
Reply | +0.402 |
roll | +0.379 |
Stra | +0.369 |
Neg logit contributions | |
merce | -0.481 |
bour | -0.466 |
onial | -0.466 |
otor | -0.423 |
agher | -0.422 |
Token | game |
Token ID | 6057 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
irtual | +0.632 |
Reply | +0.607 |
� | +0.606 |
roll | +0.566 |
Stra | +0.545 |
Neg logit contributions | |
merce | -1.060 |
onial | -1.028 |
bour | -1.027 |
agher | -0.948 |
otor | -0.948 |
Token | bonuses |
Token ID | 17568 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
irtual | +1.708 |
� | +1.665 |
Reply | +1.658 |
roll | +1.576 |
Stra | +1.539 |
Neg logit contributions | |
merce | -1.613 |
onial | -1.560 |
bour | -1.553 |
agher | -1.393 |
otor | -1.391 |
Token | He |
Token ID | 679 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
merce | +0.815 |
bour | +0.804 |
onial | +0.794 |
otor | +0.732 |
agher | +0.731 |
Neg logit contributions | |
irtual | -0.628 |
� | -0.600 |
Reply | -0.596 |
roll | -0.553 |
Stra | -0.542 |
Token | now |
Token ID | 783 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
irtual | +0.550 |
� | +0.530 |
Reply | +0.528 |
roll | +0.494 |
Stra | +0.483 |
Neg logit contributions | |
merce | -0.750 |
bour | -0.730 |
onial | -0.726 |
otor | -0.665 |
agher | -0.664 |
Token | faces |
Token ID | 6698 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
merce | +1.868 |
bour | +1.820 |
onial | +1.807 |
otor | +1.647 |
agher | +1.644 |
Neg logit contributions | |
irtual | -1.650 |
� | -1.600 |
Reply | -1.588 |
roll | -1.463 |
Stra | -1.454 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
merce | +2.254 |
bour | +2.182 |
onial | +2.171 |
otor | +1.957 |
agher | +1.942 |
Neg logit contributions | |
irtual | -2.472 |
� | -2.402 |
Reply | -2.372 |
roll | -2.231 |
Stra | -2.193 |
Token | battery |
Token ID | 6555 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
merce | +0.313 |
bour | +0.302 |
onial | +0.300 |
otor | +0.265 |
agher | +0.265 |
Neg logit contributions | |
irtual | -0.419 |
� | -0.408 |
Reply | -0.407 |
roll | -0.388 |
Stra | -0.382 |
Token | charge |
Token ID | 3877 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
merce | +0.435 |
bour | +0.416 |
onial | +0.411 |
otor | +0.352 |
agher | +0.352 |
Neg logit contributions | |
irtual | -0.832 |
� | -0.813 |
Reply | -0.810 |
roll | -0.778 |
Stra | -0.767 |
Token | in |
Token ID | 287 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
merce | +2.601 |
bour | +2.541 |
onial | +2.531 |
otor | +2.291 |
agher | +2.289 |
Neg logit contributions | |
irtual | -2.472 |
� | -2.382 |
Reply | -2.375 |
roll | -2.200 |
Stra | -2.188 |
Token | connection |
Token ID | 4637 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
merce | +0.129 |
bour | +0.125 |
onial | +0.124 |
otor | +0.112 |
agher | +0.112 |
Neg logit contributions | |
irtual | -0.128 |
� | -0.124 |
Reply | -0.124 |
roll | -0.118 |
Stra | -0.115 |
Token | with |
Token ID | 351 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
irtual | +0.718 |
� | +0.696 |
Reply | +0.691 |
roll | +0.651 |
Stra | +0.634 |
Neg logit contributions | |
merce | -1.130 |
bour | -1.110 |
onial | -1.094 |
otor | -1.015 |
agher | -1.009 |
Token | the |
Token ID | 262 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
merce | +0.978 |
bour | +0.948 |
onial | +0.943 |
otor | +0.856 |
agher | +0.854 |
Neg logit contributions | |
irtual | -0.911 |
� | -0.883 |
Reply | -0.879 |
roll | -0.827 |
Stra | -0.813 |
Token | incident |
Token ID | 4519 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
merce | +0.570 |
bour | +0.552 |
onial | +0.549 |
otor | +0.495 |
agher | +0.494 |
Neg logit contributions | |
irtual | -0.591 |
� | -0.573 |
Reply | -0.571 |
roll | -0.540 |
Stra | -0.531 |
Token | pull |
Token ID | 2834 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
irtual | +0.266 |
� | +0.258 |
Reply | +0.257 |
roll | +0.242 |
Stra | +0.238 |
Neg logit contributions | |
merce | -0.293 |
bour | -0.284 |
onial | -0.282 |
otor | -0.256 |
agher | -0.256 |
Token | . |
Token ID | 13 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
irtual | +1.589 |
Reply | +1.552 |
� | +1.550 |
roll | +1.475 |
Stra | +1.432 |
Neg logit contributions | |
merce | -1.708 |
bour | -1.626 |
onial | -1.615 |
agher | -1.475 |
otor | -1.472 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
merce | +0.137 |
bour | +0.133 |
onial | +0.133 |
otor | +0.121 |
agher | +0.121 |
Neg logit contributions | |
irtual | -0.102 |
� | -0.099 |
Reply | -0.098 |
roll | -0.091 |
Stra | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
bour | +0.233 |
merce | +0.230 |
onial | +0.227 |
otor | +0.208 |
agher | +0.208 |
Neg logit contributions | |
irtual | -0.214 |
� | -0.200 |
Reply | -0.196 |
roll | -0.183 |
Stra | -0.180 |
Token | http |
Token ID | 4023 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
irtual | +0.204 |
� | +0.197 |
Reply | +0.196 |
roll | +0.181 |
Stra | +0.177 |
Neg logit contributions | |
merce | -0.344 |
bour | -0.335 |
onial | -0.334 |
otor | -0.308 |
agher | -0.308 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
bour | +1.006 |
merce | +0.991 |
onial | +0.977 |
otor | +0.895 |
agher | +0.886 |
Neg logit contributions | |
irtual | -0.977 |
� | -0.914 |
Reply | -0.898 |
roll | -0.839 |
Stra | -0.828 |
Token | api |
Token ID | 15042 |
Feature activation | -7.01e-03 |
Pos logit contributions | |
merce | +3.747 |
bour | +3.675 |
onial | +3.616 |
otor | +3.314 |
agher | +3.311 |
Neg logit contributions | |
irtual | -2.784 |
� | -2.699 |
Reply | -2.699 |
roll | -2.426 |
Stra | -2.424 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
irtual | +0.015 |
� | +0.014 |
Reply | +0.014 |
roll | +0.014 |
rules | +0.013 |
Neg logit contributions | |
merce | -0.015 |
bour | -0.015 |
onial | -0.015 |
agher | -0.013 |
otor | -0.013 |
Token | c |
Token ID | 66 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
irtual | +0.414 |
� | +0.399 |
Reply | +0.396 |
roll | +0.378 |
Stra | +0.368 |
Neg logit contributions | |
merce | -0.489 |
bour | -0.474 |
onial | -0.473 |
otor | -0.431 |
agher | -0.430 |
Token | ensus |
Token ID | 7314 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
merce | +0.156 |
bour | +0.151 |
onial | +0.149 |
otor | +0.136 |
agher | +0.135 |
Neg logit contributions | |
irtual | -0.179 |
� | -0.175 |
Reply | -0.175 |
Stra | -0.160 |
roll | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
merce | +0.110 |
bour | +0.106 |
onial | +0.106 |
agher | +0.096 |
otor | +0.096 |
Neg logit contributions | |
irtual | -0.111 |
� | -0.107 |
Reply | -0.107 |
roll | -0.102 |
Stra | -0.099 |
Token | works |
Token ID | 5225 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
merce | +0.360 |
bour | +0.350 |
onial | +0.349 |
otor | +0.320 |
agher | +0.320 |
Neg logit contributions | |
irtual | -0.254 |
� | -0.245 |
Reply | -0.244 |
roll | -0.228 |
Stra | -0.223 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
irtual | +1.786 |
� | +1.730 |
Reply | +1.723 |
roll | +1.629 |
rules | +1.577 |
Neg logit contributions | |
merce | -2.399 |
onial | -2.319 |
bour | -2.318 |
otor | -2.118 |
agher | -2.102 |
Token | 't |
Token ID | 470 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
irtual | +0.259 |
� | +0.245 |
Reply | +0.243 |
roll | +0.227 |
Stra | +0.225 |
Neg logit contributions | |
merce | -0.270 |
bour | -0.268 |
onial | -0.264 |
otor | -0.241 |
agher | -0.240 |
Token | say |
Token ID | 910 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
irtual | +0.040 |
� | +0.039 |
Reply | +0.039 |
roll | +0.036 |
Stra | +0.035 |
Neg logit contributions | |
merce | -0.051 |
bour | -0.049 |
onial | -0.049 |
otor | -0.045 |
agher | -0.045 |
Token | whether |
Token ID | 1771 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
merce | +1.544 |
bour | +1.507 |
onial | +1.497 |
agher | +1.373 |
otor | +1.367 |
Neg logit contributions | |
irtual | -1.169 |
� | -1.123 |
Reply | -1.111 |
roll | -1.036 |
Stra | -1.018 |
Token | either |
Token ID | 2035 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
merce | +3.156 |
bour | +3.103 |
onial | +3.070 |
agher | +2.805 |
otor | +2.782 |
Neg logit contributions | |
irtual | -2.872 |
� | -2.779 |
Reply | -2.748 |
roll | -2.562 |
Stra | -2.524 |
Token | show |
Token ID | 905 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
merce | +3.878 |
bour | +3.830 |
onial | +3.791 |
agher | +3.440 |
otor | +3.437 |
Neg logit contributions | |
irtual | -3.610 |
� | -3.485 |
Reply | -3.445 |
roll | -3.223 |
Stra | -3.165 |
Token | had |
Token ID | 550 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
merce | +0.459 |
bour | +0.445 |
onial | +0.443 |
otor | +0.406 |
agher | +0.406 |
Neg logit contributions | |
irtual | -0.339 |
� | -0.328 |
Reply | -0.326 |
roll | -0.305 |
Stra | -0.298 |
Token | a |
Token ID | 257 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
irtual | +0.140 |
� | +0.136 |
Reply | +0.135 |
roll | +0.127 |
Stra | +0.125 |
Neg logit contributions | |
merce | -0.151 |
bour | -0.146 |
onial | -0.145 |
otor | -0.132 |
agher | -0.132 |
Token | long |
Token ID | 890 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
irtual | +0.342 |
Reply | +0.332 |
� | +0.332 |
roll | +0.314 |
Stra | +0.307 |
Neg logit contributions | |
merce | -0.358 |
bour | -0.346 |
onial | -0.344 |
otor | -0.312 |
agher | -0.310 |
Token | - |
Token ID | 12 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
merce | +2.152 |
bour | +2.087 |
onial | +2.081 |
otor | +1.883 |
agher | +1.877 |
Neg logit contributions | |
irtual | -2.070 |
� | -2.006 |
Reply | -1.994 |
roll | -1.875 |
Stra | -1.849 |
Token | I |
Token ID | 314 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
merce | +0.768 |
bour | +0.751 |
onial | +0.748 |
agher | +0.684 |
otor | +0.681 |
Neg logit contributions | |
irtual | -0.585 |
� | -0.564 |
Reply | -0.561 |
roll | -0.522 |
Stra | -0.512 |
Token | have |
Token ID | 423 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
merce | +0.372 |
bour | +0.362 |
onial | +0.359 |
otor | +0.328 |
agher | +0.327 |
Neg logit contributions | |
irtual | -0.303 |
� | -0.293 |
Reply | -0.292 |
roll | -0.273 |
Stra | -0.268 |
Token | met |
Token ID | 1138 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
merce | +0.607 |
bour | +0.589 |
onial | +0.585 |
otor | +0.527 |
agher | +0.526 |
Neg logit contributions | |
irtual | -0.634 |
� | -0.615 |
Reply | -0.613 |
roll | -0.578 |
Stra | -0.569 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
merce | +3.069 |
bour | +2.980 |
onial | +2.969 |
agher | +2.690 |
otor | +2.686 |
Neg logit contributions | |
irtual | -3.110 |
� | -2.997 |
Reply | -2.978 |
roll | -2.786 |
Stra | -2.765 |
Token | He |
Token ID | 679 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
irtual | +0.287 |
� | +0.273 |
Reply | +0.272 |
roll | +0.254 |
Stra | +0.247 |
Neg logit contributions | |
merce | -0.398 |
bour | -0.391 |
onial | -0.387 |
agher | -0.357 |
otor | -0.357 |
Token | spent |
Token ID | 3377 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
irtual | +0.730 |
� | +0.704 |
Reply | +0.700 |
roll | +0.648 |
Stra | +0.636 |
Neg logit contributions | |
merce | -1.074 |
bour | -1.047 |
onial | -1.040 |
otor | -0.957 |
agher | -0.956 |
Token | much |
Token ID | 881 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
merce | +2.815 |
bour | +2.739 |
onial | +2.706 |
otor | +2.465 |
agher | +2.445 |
Neg logit contributions | |
irtual | -2.941 |
� | -2.824 |
Reply | -2.802 |
roll | -2.630 |
Stra | -2.603 |
Token | of |
Token ID | 286 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
irtual | +0.266 |
� | +0.257 |
Reply | +0.255 |
roll | +0.238 |
Stra | +0.233 |
Neg logit contributions | |
merce | -0.396 |
bour | -0.384 |
onial | -0.383 |
otor | -0.352 |
agher | -0.352 |
Token | his |
Token ID | 465 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
irtual | +0.181 |
� | +0.175 |
Reply | +0.174 |
roll | +0.163 |
Stra | +0.160 |
Neg logit contributions | |
merce | -0.242 |
bour | -0.234 |
onial | -0.233 |
otor | -0.213 |
agher | -0.213 |
Token | early |
Token ID | 1903 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
irtual | +0.947 |
� | +0.921 |
Reply | +0.917 |
roll | +0.867 |
Stra | +0.854 |
Neg logit contributions | |
merce | -0.909 |
bour | -0.876 |
onial | -0.870 |
otor | -0.785 |
agher | -0.784 |
Token | career |
Token ID | 3451 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
irtual | +0.324 |
� | +0.314 |
Reply | +0.313 |
roll | +0.296 |
Stra | +0.291 |
Neg logit contributions | |
merce | -0.314 |
bour | -0.303 |
onial | -0.302 |
otor | -0.272 |
agher | -0.272 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
merce | +1.690 |
bour | +1.637 |
onial | +1.633 |
otor | +1.479 |
agher | +1.479 |
Neg logit contributions | |
irtual | -1.569 |
� | -1.512 |
Reply | -1.505 |
roll | -1.404 |
Stra | -1.390 |
Token |
|
Token ID | 198 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
merce | +0.456 |
bour | +0.444 |
onial | +0.442 |
otor | +0.405 |
agher | +0.404 |
Neg logit contributions | |
irtual | -0.365 |
� | -0.352 |
Reply | -0.350 |
roll | -0.327 |
Stra | -0.320 |
Token |
|
Token ID | 198 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
bour | +0.398 |
merce | +0.394 |
onial | +0.389 |
otor | +0.357 |
agher | +0.356 |
Neg logit contributions | |
irtual | -0.365 |
� | -0.340 |
Reply | -0.335 |
roll | -0.312 |
Stra | -0.307 |
Token | The |
Token ID | 464 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
merce | +0.178 |
bour | +0.174 |
onial | +0.173 |
otor | +0.159 |
agher | +0.159 |
Neg logit contributions | |
irtual | -0.114 |
� | -0.109 |
Reply | -0.108 |
roll | -0.100 |
Stra | -0.098 |
Token | company |
Token ID | 1664 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
irtual | +0.026 |
� | +0.025 |
Reply | +0.025 |
roll | +0.023 |
Stra | +0.023 |
Neg logit contributions | |
merce | -0.026 |
bour | -0.026 |
onial | -0.025 |
otor | -0.023 |
agher | -0.023 |
Token | received |
Token ID | 2722 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
irtual | +1.250 |
� | +1.210 |
Reply | +1.206 |
roll | +1.137 |
Stra | +1.109 |
Neg logit contributions | |
merce | -1.571 |
bour | -1.530 |
onial | -1.520 |
otor | -1.389 |
agher | -1.387 |
Token | an |
Token ID | 281 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
merce | +2.688 |
bour | +2.581 |
onial | +2.575 |
otor | +2.364 |
agher | +2.324 |
Neg logit contributions | |
irtual | -2.469 |
� | -2.404 |
Reply | -2.354 |
roll | -2.207 |
Stra | -2.193 |
Token | estimated |
Token ID | 6108 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
merce | +0.091 |
onial | +0.088 |
bour | +0.088 |
otor | +0.080 |
agher | +0.080 |
Neg logit contributions | |
irtual | -0.084 |
� | -0.082 |
Reply | -0.081 |
roll | -0.076 |
Stra | -0.075 |
Token | $ |
Token ID | 720 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
merce | +1.279 |
bour | +1.236 |
onial | +1.236 |
otor | +1.130 |
agher | +1.123 |
Neg logit contributions | |
irtual | -1.042 |
� | -1.005 |
Reply | -0.992 |
roll | -0.924 |
Stra | -0.910 |
Token | 9 |
Token ID | 24 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
merce | +0.479 |
bour | +0.470 |
onial | +0.467 |
otor | +0.433 |
agher | +0.431 |
Neg logit contributions | |
irtual | -0.285 |
� | -0.271 |
Reply | -0.269 |
roll | -0.248 |
Stra | -0.242 |
Token | . |
Token ID | 13 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
irtual | +0.696 |
� | +0.672 |
Reply | +0.671 |
roll | +0.633 |
Stra | +0.620 |
Neg logit contributions | |
merce | -0.801 |
bour | -0.772 |
onial | -0.768 |
agher | -0.701 |
otor | -0.698 |
Token | ( |
Token ID | 357 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
merce | +0.939 |
bour | +0.917 |
onial | +0.913 |
otor | +0.827 |
agher | +0.820 |
Neg logit contributions | |
irtual | -0.942 |
� | -0.910 |
Reply | -0.902 |
roll | -0.851 |
Stra | -0.835 |
Token | K |
Token ID | 42 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
merce | +1.417 |
bour | +1.403 |
onial | +1.390 |
otor | +1.290 |
agher | +1.282 |
Neg logit contributions | |
irtual | -0.822 |
� | -0.777 |
Reply | -0.770 |
roll | -0.705 |
rules | -0.687 |
Token | FS |
Token ID | 10652 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
merce | +0.330 |
bour | +0.324 |
onial | +0.322 |
otor | +0.301 |
agher | +0.298 |
Neg logit contributions | |
irtual | -0.189 |
� | -0.182 |
Reply | -0.180 |
roll | -0.163 |
Stra | -0.161 |
Token | N |
Token ID | 45 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
irtual | +1.002 |
Reply | +0.967 |
� | +0.966 |
roll | +0.896 |
Stra | +0.878 |
Neg logit contributions | |
merce | -1.514 |
onial | -1.460 |
bour | -1.460 |
agher | -1.342 |
otor | -1.340 |
Token | ) |
Token ID | 8 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
merce | +0.941 |
bour | +0.917 |
onial | +0.907 |
otor | +0.833 |
agher | +0.826 |
Neg logit contributions | |
irtual | -0.836 |
� | -0.807 |
Reply | -0.807 |
roll | -0.748 |
Stra | -0.738 |
Token | -- |
Token ID | 1377 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
merce | +1.113 |
bour | +1.095 |
onial | +1.085 |
otor | +0.979 |
agher | +0.972 |
Neg logit contributions | |
irtual | -1.281 |
� | -1.230 |
Reply | -1.222 |
roll | -1.158 |
Stra | -1.135 |
Token | The |
Token ID | 383 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
merce | +0.179 |
bour | +0.176 |
onial | +0.174 |
otor | +0.160 |
agher | +0.159 |
Neg logit contributions | |
irtual | -0.149 |
� | -0.143 |
Reply | -0.142 |
roll | -0.133 |
Stra | -0.130 |
Token | revelation |
Token ID | 16084 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
irtual | +0.273 |
� | +0.264 |
Reply | +0.263 |
roll | +0.247 |
Stra | +0.243 |
Neg logit contributions | |
merce | -0.315 |
bour | -0.305 |
onial | -0.304 |
otor | -0.276 |
agher | -0.276 |
Token | that |
Token ID | 326 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
merce | +0.366 |
bour | +0.357 |
onial | +0.355 |
otor | +0.324 |
agher | +0.324 |
Neg logit contributions | |
irtual | -0.283 |
� | -0.273 |
Reply | -0.272 |
roll | -0.254 |
Stra | -0.249 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
merce | +0.967 |
bour | +0.945 |
onial | +0.938 |
otor | +0.855 |
agher | +0.852 |
Neg logit contributions | |
irtual | -0.855 |
� | -0.824 |
Reply | -0.822 |
roll | -0.769 |
Stra | -0.755 |
Token | murdered |
Token ID | 12864 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
irtual | +0.232 |
� | +0.225 |
Reply | +0.224 |
roll | +0.212 |
Stra | +0.208 |
Neg logit contributions | |
merce | -0.238 |
bour | -0.230 |
onial | -0.229 |
otor | -0.207 |
agher | -0.207 |
Token | ; |
Token ID | 26 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
irtual | +1.900 |
Reply | +1.871 |
� | +1.870 |
roll | +1.789 |
Stra | +1.751 |
Neg logit contributions | |
merce | -1.324 |
bour | -1.268 |
onial | -1.249 |
otor | -1.107 |
agher | -1.095 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
merce | +1.156 |
bour | +1.124 |
onial | +1.117 |
otor | +1.006 |
agher | +1.003 |
Neg logit contributions | |
irtual | -1.173 |
� | -1.137 |
Reply | -1.131 |
roll | -1.064 |
Stra | -1.051 |
Token | deadline |
Token ID | 12508 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
irtual | +0.245 |
� | +0.236 |
Reply | +0.235 |
roll | +0.221 |
Stra | +0.218 |
Neg logit contributions | |
merce | -0.250 |
bour | -0.244 |
onial | -0.242 |
otor | -0.219 |
agher | -0.218 |
Token | for |
Token ID | 329 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
irtual | +2.514 |
� | +2.488 |
Reply | +2.470 |
roll | +2.305 |
Stra | +2.240 |
Neg logit contributions | |
merce | -4.028 |
bour | -3.868 |
onial | -3.850 |
otor | -3.562 |
agher | -3.556 |
Token | consideration |
Token ID | 9110 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
irtual | +0.376 |
� | +0.361 |
Reply | +0.356 |
roll | +0.332 |
Stra | +0.328 |
Neg logit contributions | |
merce | -0.533 |
bour | -0.522 |
onial | -0.520 |
otor | -0.477 |
agher | -0.475 |
Token | for |
Token ID | 329 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
irtual | +2.294 |
� | +2.224 |
Reply | +2.209 |
roll | +2.059 |
Stra | +2.014 |
Neg logit contributions | |
merce | -3.363 |
bour | -3.263 |
onial | -3.249 |
otor | -2.987 |
agher | -2.982 |
Token | the |
Token ID | 262 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
merce | +0.081 |
bour | +0.079 |
onial | +0.078 |
otor | +0.071 |
agher | +0.070 |
Neg logit contributions | |
irtual | -0.083 |
� | -0.080 |
Reply | -0.079 |
roll | -0.074 |
Stra | -0.074 |
Token | 2019 |
Token ID | 13130 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
merce | +0.276 |
bour | +0.270 |
onial | +0.269 |
otor | +0.251 |
agher | +0.250 |
Neg logit contributions | |
irtual | -0.118 |
� | -0.112 |
Reply | -0.112 |
roll | -0.101 |
Stra | -0.098 |
Token | award |
Token ID | 5764 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
irtual | +2.153 |
� | +2.119 |
Reply | +2.110 |
roll | +2.013 |
Stra | +1.976 |
Neg logit contributions | |
merce | -1.824 |
bour | -1.737 |
onial | -1.721 |
agher | -1.544 |
otor | -1.537 |
Token | is |
Token ID | 318 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
irtual | +1.391 |
� | +1.351 |
Reply | +1.342 |
roll | +1.251 |
Stra | +1.224 |
Neg logit contributions | |
merce | -2.048 |
bour | -1.980 |
onial | -1.970 |
otor | -1.814 |
agher | -1.812 |
Token | February |
Token ID | 3945 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
irtual | +0.249 |
� | +0.240 |
Reply | +0.239 |
roll | +0.223 |
Stra | +0.218 |
Neg logit contributions | |
merce | -0.351 |
bour | -0.342 |
onial | -0.339 |
otor | -0.312 |
agher | -0.311 |
Token | we |
Token ID | 356 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
merce | +1.045 |
bour | +1.020 |
onial | +1.013 |
agher | +0.931 |
otor | +0.930 |
Neg logit contributions | |
irtual | -0.750 |
� | -0.719 |
Reply | -0.715 |
roll | -0.664 |
Stra | -0.654 |
Token | all |
Token ID | 477 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
merce | +0.429 |
bour | +0.418 |
onial | +0.415 |
otor | +0.381 |
agher | +0.380 |
Neg logit contributions | |
irtual | -0.323 |
� | -0.312 |
Reply | -0.310 |
roll | -0.288 |
Stra | -0.284 |
Token | want |
Token ID | 765 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
irtual | +1.093 |
� | +1.056 |
Reply | +1.051 |
roll | +0.983 |
Stra | +0.961 |
Neg logit contributions | |
merce | -1.449 |
bour | -1.408 |
onial | -1.401 |
otor | -1.283 |
agher | -1.280 |
Token | is |
Token ID | 318 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
merce | +0.800 |
bour | +0.781 |
onial | +0.777 |
agher | +0.715 |
otor | +0.715 |
Neg logit contributions | |
irtual | -0.538 |
� | -0.516 |
Reply | -0.512 |
roll | -0.475 |
Stra | -0.466 |
Token | peace |
Token ID | 4167 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
irtual | +0.519 |
� | +0.502 |
Reply | +0.499 |
roll | +0.469 |
Stra | +0.460 |
Neg logit contributions | |
merce | -0.621 |
bour | -0.603 |
onial | -0.600 |
otor | -0.547 |
agher | -0.546 |
Token | and |
Token ID | 290 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
merce | +0.487 |
bour | +0.475 |
onial | +0.470 |
agher | +0.428 |
otor | +0.428 |
Neg logit contributions | |
irtual | -0.442 |
� | -0.427 |
Reply | -0.425 |
roll | -0.399 |
Stra | -0.393 |
Token | it |
Token ID | 340 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
merce | +0.006 |
bour | +0.006 |
onial | +0.006 |
otor | +0.005 |
agher | +0.005 |
Neg logit contributions | |
irtual | -0.005 |
� | -0.005 |
Reply | -0.005 |
roll | -0.005 |
Stra | -0.005 |
Token | � |
Token ID | 447 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
irtual | +0.379 |
� | +0.365 |
Reply | +0.363 |
roll | +0.336 |
Stra | +0.330 |
Neg logit contributions | |
merce | -0.567 |
bour | -0.553 |
onial | -0.550 |
otor | -0.506 |
agher | -0.505 |
Token | � |
Token ID | 247 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
merce | +0.935 |
bour | +0.920 |
onial | +0.913 |
otor | +0.844 |
agher | +0.838 |
Neg logit contributions | |
irtual | -0.580 |
� | -0.540 |
Reply | -0.536 |
roll | -0.495 |
Stra | -0.492 |
Token | s |
Token ID | 82 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
irtual | +0.025 |
� | +0.024 |
Reply | +0.024 |
roll | +0.022 |
Stra | +0.022 |
Neg logit contributions | |
merce | -0.033 |
bour | -0.032 |
onial | -0.032 |
otor | -0.029 |
agher | -0.029 |
Token | heartbreaking |
Token ID | 37154 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
merce | +0.675 |
bour | +0.659 |
onial | +0.653 |
otor | +0.595 |
agher | +0.595 |
Neg logit contributions | |
irtual | -0.565 |
� | -0.543 |
Reply | -0.540 |
roll | -0.505 |
Stra | -0.497 |
Token | Mobile |
Token ID | 12173 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
merce | +0.681 |
bour | +0.661 |
onial | +0.657 |
otor | +0.597 |
agher | +0.595 |
Neg logit contributions | |
irtual | -0.619 |
� | -0.600 |
Reply | -0.597 |
roll | -0.561 |
Stra | -0.552 |
Token | World |
Token ID | 2159 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
merce | +1.114 |
bour | +1.081 |
onial | +1.077 |
otor | +0.989 |
agher | +0.985 |
Neg logit contributions | |
irtual | -0.807 |
� | -0.776 |
Reply | -0.772 |
roll | -0.721 |
Stra | -0.704 |
Token | Congress |
Token ID | 3162 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
merce | +0.064 |
bour | +0.062 |
onial | +0.061 |
otor | +0.056 |
agher | +0.056 |
Neg logit contributions | |
irtual | -0.060 |
� | -0.058 |
Reply | -0.058 |
roll | -0.054 |
Stra | -0.053 |
Token | 2019 |
Token ID | 13130 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
irtual | +0.234 |
� | +0.223 |
Reply | +0.222 |
roll | +0.203 |
Stra | +0.197 |
Neg logit contributions | |
merce | -0.467 |
bour | -0.457 |
onial | -0.454 |
otor | -0.422 |
agher | -0.421 |
Token | with |
Token ID | 351 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
irtual | +1.016 |
� | +0.985 |
Reply | +0.976 |
roll | +0.921 |
Stra | +0.901 |
Neg logit contributions | |
merce | -1.199 |
bour | -1.162 |
onial | -1.156 |
otor | -1.052 |
agher | -1.051 |
Token | a |
Token ID | 257 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
merce | +0.149 |
bour | +0.145 |
onial | +0.144 |
otor | +0.131 |
agher | +0.131 |
Neg logit contributions | |
irtual | -0.130 |
� | -0.126 |
Reply | -0.125 |
roll | -0.118 |
Stra | -0.115 |
Token | two |
Token ID | 734 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
irtual | +0.438 |
� | +0.425 |
Reply | +0.423 |
roll | +0.399 |
Stra | +0.392 |
Neg logit contributions | |
merce | -0.470 |
bour | -0.456 |
onial | -0.453 |
otor | -0.410 |
agher | -0.410 |
Token | - |
Token ID | 12 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
merce | +0.658 |
bour | +0.639 |
onial | +0.636 |
otor | +0.579 |
agher | +0.578 |
Neg logit contributions | |
irtual | -0.564 |
� | -0.546 |
Reply | -0.543 |
roll | -0.510 |
Stra | -0.501 |
Token | day |
Token ID | 820 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
irtual | +0.168 |
� | +0.162 |
Reply | +0.161 |
roll | +0.151 |
Stra | +0.148 |
Neg logit contributions | |
merce | -0.233 |
bour | -0.226 |
onial | -0.225 |
agher | -0.207 |
otor | -0.207 |
Token | Executive |
Token ID | 10390 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
irtual | +2.406 |
� | +2.333 |
Reply | +2.319 |
roll | +2.189 |
Stra | +2.160 |
Neg logit contributions | |
merce | -2.822 |
bour | -2.732 |
onial | -2.700 |
agher | -2.454 |
otor | -2.448 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
irtual | +0.627 |
� | +0.607 |
Reply | +0.605 |
roll | +0.569 |
Stra | +0.559 |
Neg logit contributions | |
merce | -0.700 |
bour | -0.679 |
onial | -0.674 |
otor | -0.613 |
agher | -0.613 |
Token | for |
Token ID | 329 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
merce | +0.215 |
bour | +0.209 |
onial | +0.208 |
otor | +0.191 |
agher | +0.190 |
Neg logit contributions | |
irtual | -0.160 |
� | -0.155 |
Reply | -0.154 |
roll | -0.144 |
Stra | -0.141 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
merce | +0.310 |
bour | +0.301 |
onial | +0.299 |
otor | +0.272 |
agher | +0.272 |
Neg logit contributions | |
irtual | -0.270 |
� | -0.261 |
Reply | -0.260 |
roll | -0.244 |
Stra | -0.240 |
Token | stay |
Token ID | 2652 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
merce | +0.313 |
bour | +0.303 |
onial | +0.301 |
otor | +0.273 |
agher | +0.273 |
Neg logit contributions | |
irtual | -0.297 |
� | -0.288 |
Reply | -0.287 |
roll | -0.270 |
Stra | -0.265 |
Token | while |
Token ID | 981 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
merce | +0.409 |
bour | +0.398 |
onial | +0.396 |
agher | +0.362 |
otor | +0.362 |
Neg logit contributions | |
irtual | -0.329 |
� | -0.317 |
Reply | -0.315 |
roll | -0.294 |
Stra | -0.289 |
Token | it |
Token ID | 340 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
merce | +2.148 |
bour | +2.110 |
onial | +2.095 |
agher | +1.899 |
otor | +1.892 |
Neg logit contributions | |
irtual | -1.909 |
� | -1.831 |
Reply | -1.822 |
roll | -1.706 |
Stra | -1.673 |
Token | asks |
Token ID | 7893 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
merce | +0.584 |
bour | +0.571 |
onial | +0.567 |
agher | +0.517 |
otor | +0.515 |
Neg logit contributions | |
irtual | -0.472 |
� | -0.452 |
Reply | -0.450 |
roll | -0.416 |
Stra | -0.414 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
merce | +1.144 |
bour | +1.116 |
onial | +1.108 |
agher | +1.005 |
otor | +1.004 |
Neg logit contributions | |
irtual | -1.030 |
� | -0.991 |
Reply | -0.991 |
roll | -0.925 |
Stra | -0.909 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
merce | +0.544 |
bour | +0.526 |
onial | +0.522 |
otor | +0.465 |
agher | +0.464 |
Neg logit contributions | |
irtual | -0.688 |
� | -0.669 |
Reply | -0.666 |
roll | -0.632 |
Stra | -0.623 |
Token | Court |
Token ID | 3078 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
merce | +0.853 |
bour | +0.842 |
onial | +0.815 |
otor | +0.710 |
agher | +0.705 |
Neg logit contributions | |
irtual | -1.638 |
� | -1.585 |
Reply | -1.583 |
roll | -1.494 |
Stra | -1.479 |
Token | to |
Token ID | 284 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
merce | +0.037 |
bour | +0.036 |
onial | +0.035 |
otor | +0.033 |
agher | +0.033 |
Neg logit contributions | |
irtual | -0.026 |
� | -0.025 |
Reply | -0.025 |
roll | -0.023 |
Stra | -0.023 |
Token | hear |
Token ID | 3285 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
merce | +0.534 |
bour | +0.520 |
onial | +0.516 |
otor | +0.472 |
agher | +0.471 |
Neg logit contributions | |
irtual | -0.415 |
� | -0.400 |
Reply | -0.397 |
roll | -0.370 |
Stra | -0.364 |
Token | Washington |
Token ID | 2669 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
irtual | +1.247 |
� | +1.211 |
Reply | +1.206 |
roll | +1.134 |
Stra | +1.113 |
Neg logit contributions | |
merce | -1.422 |
bour | -1.373 |
onial | -1.370 |
otor | -1.244 |
agher | -1.239 |
Token | DC |
Token ID | 6257 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
irtual | +0.615 |
� | +0.594 |
Reply | +0.591 |
roll | +0.552 |
Stra | +0.542 |
Neg logit contributions | |
merce | -0.793 |
bour | -0.771 |
onial | -0.766 |
otor | -0.702 |
agher | -0.701 |
Token | is |
Token ID | 318 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
irtual | +0.726 |
� | +0.699 |
Reply | +0.695 |
roll | +0.645 |
Stra | +0.636 |
Neg logit contributions | |
merce | -1.010 |
bour | -0.985 |
onial | -0.979 |
agher | -0.900 |
otor | -0.900 |
Token | that |
Token ID | 326 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
irtual | +0.229 |
� | +0.221 |
Reply | +0.220 |
roll | +0.206 |
Stra | +0.202 |
Neg logit contributions | |
merce | -0.275 |
bour | -0.267 |
onial | -0.266 |
otor | -0.242 |
agher | -0.242 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
merce | +0.103 |
bour | +0.101 |
onial | +0.100 |
otor | +0.091 |
agher | +0.091 |
Neg logit contributions | |
irtual | -0.081 |
� | -0.078 |
Reply | -0.078 |
roll | -0.073 |
Stra | -0.071 |
Token | M |
Token ID | 337 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
irtual | +0.204 |
� | +0.197 |
Reply | +0.196 |
roll | +0.184 |
Stra | +0.181 |
Neg logit contributions | |
merce | -0.233 |
bour | -0.227 |
onial | -0.226 |
otor | -0.206 |
agher | -0.205 |
Token | WC |
Token ID | 27353 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
irtual | +0.721 |
� | +0.700 |
Reply | +0.696 |
roll | +0.657 |
Stra | +0.647 |
Neg logit contributions | |
merce | -0.706 |
bour | -0.684 |
onial | -0.680 |
otor | -0.614 |
agher | -0.613 |
Token | has |
Token ID | 468 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
merce | +0.374 |
bour | +0.364 |
onial | +0.362 |
otor | +0.331 |
agher | +0.330 |
Neg logit contributions | |
irtual | -0.298 |
� | -0.287 |
Reply | -0.286 |
roll | -0.266 |
Stra | -0.262 |
Token | invited |
Token ID | 9392 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
merce | +0.118 |
bour | +0.115 |
onial | +0.114 |
otor | +0.104 |
agher | +0.104 |
Neg logit contributions | |
irtual | -0.102 |
� | -0.099 |
Reply | -0.098 |
roll | -0.092 |
Stra | -0.091 |
Token | Boise |
Token ID | 38830 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
irtual | +0.218 |
� | +0.211 |
Reply | +0.210 |
roll | +0.197 |
Stra | +0.193 |
Neg logit contributions | |
merce | -0.251 |
bour | -0.244 |
onial | -0.243 |
otor | -0.221 |
agher | -0.221 |
Token | State |
Token ID | 1812 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
irtual | +1.842 |
� | +1.789 |
Reply | +1.781 |
roll | +1.668 |
Stra | +1.631 |
Neg logit contributions | |
merce | -2.388 |
bour | -2.319 |
onial | -2.307 |
agher | -2.108 |
otor | -2.105 |
Token | the |
Token ID | 262 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
irtual | +0.580 |
� | +0.561 |
Reply | +0.559 |
roll | +0.525 |
Stra | +0.516 |
Neg logit contributions | |
merce | -0.652 |
bour | -0.633 |
onial | -0.629 |
otor | -0.571 |
agher | -0.570 |
Token | subject |
Token ID | 2426 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
irtual | +0.060 |
� | +0.058 |
Reply | +0.057 |
roll | +0.054 |
Stra | +0.053 |
Neg logit contributions | |
merce | -0.066 |
bour | -0.064 |
onial | -0.064 |
otor | -0.059 |
agher | -0.058 |
Token | ) |
Token ID | 8 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
irtual | +0.253 |
� | +0.245 |
Reply | +0.243 |
roll | +0.228 |
Stra | +0.224 |
Neg logit contributions | |
merce | -0.314 |
bour | -0.305 |
onial | -0.303 |
otor | -0.277 |
agher | -0.276 |
Token | then |
Token ID | 788 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
merce | +0.737 |
bour | +0.716 |
onial | +0.714 |
otor | +0.655 |
agher | +0.654 |
Neg logit contributions | |
irtual | -0.544 |
� | -0.526 |
Reply | -0.521 |
roll | -0.485 |
Stra | -0.477 |
Token | the |
Token ID | 262 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
irtual | +0.501 |
� | +0.484 |
Reply | +0.482 |
roll | +0.451 |
Stra | +0.442 |
Neg logit contributions | |
merce | -0.634 |
bour | -0.616 |
onial | -0.613 |
otor | -0.560 |
agher | -0.559 |
Token | sport |
Token ID | 6332 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
merce | +0.085 |
bour | +0.083 |
onial | +0.082 |
otor | +0.075 |
agher | +0.075 |
Neg logit contributions | |
irtual | -0.078 |
� | -0.075 |
Reply | -0.075 |
roll | -0.070 |
Stra | -0.069 |
Token | is |
Token ID | 318 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
irtual | +1.292 |
� | +1.252 |
Reply | +1.245 |
roll | +1.175 |
rules | +1.147 |
Neg logit contributions | |
merce | -1.568 |
bour | -1.523 |
onial | -1.514 |
agher | -1.382 |
otor | -1.371 |
Token | in |
Token ID | 287 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
irtual | +0.211 |
� | +0.204 |
Reply | +0.203 |
roll | +0.190 |
Stra | +0.186 |
Neg logit contributions | |
merce | -0.262 |
bour | -0.254 |
onial | -0.253 |
otor | -0.231 |
agher | -0.231 |
Token | deeper |
Token ID | 9211 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
merce | +0.526 |
bour | +0.510 |
onial | +0.507 |
otor | +0.460 |
agher | +0.459 |
Neg logit contributions | |
irtual | -0.493 |
� | -0.478 |
Reply | -0.475 |
roll | -0.448 |
Stra | -0.440 |
Token | trouble |
Token ID | 5876 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
merce | +0.335 |
bour | +0.325 |
onial | +0.323 |
otor | +0.292 |
agher | +0.292 |
Neg logit contributions | |
irtual | -0.327 |
� | -0.317 |
Reply | -0.315 |
roll | -0.297 |
Stra | -0.292 |
Token | than |
Token ID | 621 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
merce | +0.363 |
bour | +0.352 |
onial | +0.350 |
otor | +0.318 |
agher | +0.317 |
Neg logit contributions | |
irtual | -0.326 |
� | -0.316 |
Reply | -0.314 |
roll | -0.295 |
Stra | -0.290 |
Token | a |
Token ID | 257 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
irtual | +0.594 |
� | +0.576 |
Reply | +0.573 |
roll | +0.539 |
Stra | +0.530 |
Neg logit contributions | |
merce | -0.659 |
bour | -0.638 |
onial | -0.635 |
otor | -0.577 |
agher | -0.576 |
Token | little |
Token ID | 1310 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
irtual | +0.046 |
� | +0.044 |
Reply | +0.044 |
roll | +0.041 |
Stra | +0.041 |
Neg logit contributions | |
merce | -0.048 |
bour | -0.047 |
onial | -0.046 |
otor | -0.042 |
agher | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
merce | +1.494 |
bour | +1.463 |
onial | +1.448 |
otor | +1.311 |
agher | +1.310 |
Neg logit contributions | |
irtual | -1.426 |
� | -1.374 |
Reply | -1.370 |
roll | -1.286 |
Stra | -1.265 |
Token | curtain |
Token ID | 29461 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
irtual | +0.071 |
� | +0.068 |
Reply | +0.068 |
roll | +0.064 |
Stra | +0.063 |
Neg logit contributions | |
merce | -0.082 |
bour | -0.080 |
onial | -0.079 |
otor | -0.072 |
agher | -0.072 |
Token | - |
Token ID | 12 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
merce | +0.803 |
bour | +0.786 |
onial | +0.781 |
otor | +0.712 |
agher | +0.707 |
Neg logit contributions | |
irtual | -0.721 |
Reply | -0.693 |
� | -0.691 |
roll | -0.642 |
Stra | -0.636 |
Token | like |
Token ID | 2339 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
merce | +0.508 |
bour | +0.496 |
onial | +0.493 |
otor | +0.449 |
agher | +0.447 |
Neg logit contributions | |
irtual | -0.425 |
Reply | -0.410 |
� | -0.409 |
roll | -0.379 |
Stra | -0.374 |
Token | slit |
Token ID | 40724 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
irtual | +0.755 |
� | +0.733 |
Reply | +0.730 |
roll | +0.688 |
Stra | +0.675 |
Neg logit contributions | |
merce | -0.816 |
bour | -0.790 |
onial | -0.786 |
otor | -0.713 |
agher | -0.711 |
Token | in |
Token ID | 287 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
merce | +1.801 |
bour | +1.770 |
onial | +1.751 |
otor | +1.596 |
agher | +1.589 |
Neg logit contributions | |
irtual | -1.486 |
Reply | -1.436 |
� | -1.434 |
roll | -1.327 |
Stra | -1.312 |
Token | the |
Token ID | 262 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
irtual | +0.421 |
� | +0.408 |
Reply | +0.406 |
roll | +0.383 |
Stra | +0.377 |
Neg logit contributions | |
merce | -0.458 |
bour | -0.441 |
onial | -0.440 |
otor | -0.400 |
agher | -0.399 |
Token | bottom |
Token ID | 4220 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
irtual | +0.066 |
� | +0.064 |
Reply | +0.063 |
roll | +0.060 |
Stra | +0.059 |
Neg logit contributions | |
merce | -0.070 |
bour | -0.068 |
onial | -0.067 |
otor | -0.061 |
agher | -0.061 |
Token | – |
Token ID | 784 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
merce | +0.846 |
bour | +0.822 |
onial | +0.817 |
otor | +0.742 |
agher | +0.740 |
Neg logit contributions | |
irtual | -0.757 |
� | -0.732 |
Reply | -0.730 |
roll | -0.684 |
Stra | -0.672 |
Token | Allah |
Token ID | 11475 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
irtual | +0.080 |
� | +0.076 |
Reply | +0.075 |
roll | +0.069 |
Stra | +0.067 |
Neg logit contributions | |
merce | -0.161 |
bour | -0.157 |
onial | -0.157 |
agher | -0.146 |
otor | -0.145 |
Token | ( |
Token ID | 357 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
merce | +0.751 |
bour | +0.727 |
onial | +0.723 |
agher | +0.661 |
otor | +0.659 |
Neg logit contributions | |
irtual | -0.591 |
� | -0.563 |
Reply | -0.563 |
roll | -0.527 |
Stra | -0.515 |
Token | peace |
Token ID | 22988 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
irtual | +0.882 |
� | +0.868 |
Reply | +0.861 |
roll | +0.812 |
Stra | +0.800 |
Neg logit contributions | |
merce | -0.989 |
onial | -0.955 |
bour | -0.955 |
otor | -0.866 |
agher | -0.864 |
Token | be |
Token ID | 307 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
merce | +1.518 |
bour | +1.484 |
onial | +1.473 |
agher | +1.341 |
otor | +1.333 |
Neg logit contributions | |
irtual | -1.406 |
� | -1.342 |
Reply | -1.338 |
roll | -1.248 |
rules | -1.229 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
irtual | +0.300 |
� | +0.285 |
Reply | +0.284 |
roll | +0.263 |
Stra | +0.255 |
Neg logit contributions | |
merce | -0.485 |
bour | -0.472 |
onial | -0.471 |
agher | -0.434 |
otor | -0.433 |
Token | him |
Token ID | 683 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
irtual | +0.292 |
Reply | +0.277 |
� | +0.274 |
roll | +0.249 |
Stra | +0.244 |
Neg logit contributions | |
merce | -0.592 |
bour | -0.577 |
onial | -0.574 |
agher | -0.532 |
otor | -0.532 |
Token | ) |
Token ID | 8 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
irtual | +1.321 |
� | +1.302 |
Reply | +1.287 |
roll | +1.197 |
Stra | +1.178 |
Neg logit contributions | |
merce | -1.733 |
bour | -1.694 |
onial | -1.682 |
otor | -1.541 |
agher | -1.538 |
Token | was |
Token ID | 373 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
merce | +0.337 |
bour | +0.327 |
onial | +0.325 |
agher | +0.297 |
otor | +0.296 |
Neg logit contributions | |
irtual | -0.268 |
� | -0.256 |
Reply | -0.255 |
roll | -0.239 |
Stra | -0.234 |
Token | killing |
Token ID | 5170 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
irtual | +0.595 |
� | +0.576 |
Reply | +0.573 |
roll | +0.539 |
Stra | +0.529 |
Neg logit contributions | |
merce | -0.682 |
bour | -0.662 |
onial | -0.659 |
otor | -0.599 |
agher | -0.598 |
Token | her |
Token ID | 607 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
irtual | +0.323 |
� | +0.312 |
Reply | +0.310 |
roll | +0.292 |
Stra | +0.287 |
Neg logit contributions | |
merce | -0.345 |
bour | -0.335 |
onial | -0.333 |
otor | -0.302 |
agher | -0.302 |
Token | people |
Token ID | 661 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
merce | +0.660 |
bour | +0.643 |
onial | +0.640 |
otor | +0.580 |
agher | +0.579 |
Neg logit contributions | |
irtual | -0.585 |
� | -0.562 |
Reply | -0.559 |
roll | -0.526 |
Stra | -0.516 |
Token | - |
Token ID | 12 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
merce | +1.731 |
bour | +1.684 |
onial | +1.669 |
otor | +1.502 |
agher | +1.489 |
Neg logit contributions | |
irtual | -1.844 |
� | -1.787 |
Reply | -1.777 |
roll | -1.673 |
Stra | -1.659 |
Token | capitalist |
Token ID | 49970 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
irtual | +0.604 |
Reply | +0.585 |
� | +0.582 |
roll | +0.543 |
Stra | +0.532 |
Neg logit contributions | |
merce | -0.932 |
onial | -0.898 |
bour | -0.893 |
agher | -0.829 |
otor | -0.828 |
Token | " |
Token ID | 366 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
irtual | +1.074 |
� | +1.040 |
Reply | +1.034 |
roll | +0.972 |
Stra | +0.954 |
Neg logit contributions | |
merce | -1.248 |
bour | -1.210 |
onial | -1.204 |
otor | -1.097 |
agher | -1.094 |
Token | national |
Token ID | 14648 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
irtual | +0.043 |
� | +0.041 |
Reply | +0.041 |
roll | +0.039 |
Stra | +0.038 |
Neg logit contributions | |
merce | -0.046 |
bour | -0.044 |
onial | -0.044 |
otor | -0.040 |
agher | -0.040 |
Token | liberation |
Token ID | 22256 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
merce | +0.771 |
bour | +0.753 |
onial | +0.748 |
otor | +0.676 |
agher | +0.670 |
Neg logit contributions | |
irtual | -0.734 |
� | -0.713 |
Reply | -0.708 |
roll | -0.669 |
Stra | -0.658 |
Token | " |
Token ID | 1 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
irtual | +0.362 |
� | +0.347 |
Reply | +0.345 |
roll | +0.320 |
Stra | +0.313 |
Neg logit contributions | |
merce | -0.573 |
bour | -0.561 |
onial | -0.558 |
otor | -0.514 |
agher | -0.512 |
Token | movements |
Token ID | 8650 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
irtual | +1.268 |
� | +1.216 |
Reply | +1.209 |
roll | +1.112 |
Stra | +1.085 |
Neg logit contributions | |
merce | -2.282 |
bour | -2.224 |
onial | -2.214 |
otor | -2.050 |
agher | -2.047 |
Token | , |
Token ID | 11 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
irtual | +1.358 |
� | +1.322 |
Reply | +1.314 |
roll | +1.242 |
Stra | +1.216 |
Neg logit contributions | |
merce | -1.512 |
bour | -1.461 |
onial | -1.450 |
otor | -1.321 |
agher | -1.319 |
Token | forces |
Token ID | 3386 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
irtual | +0.624 |
� | +0.604 |
Reply | +0.601 |
roll | +0.564 |
Stra | +0.553 |
Neg logit contributions | |
merce | -0.746 |
bour | -0.724 |
onial | -0.720 |
otor | -0.657 |
agher | -0.655 |
Token | the |
Token ID | 262 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
irtual | +1.590 |
� | +1.546 |
Reply | +1.539 |
roll | +1.442 |
Stra | +1.415 |
Neg logit contributions | |
merce | -2.025 |
bour | -1.952 |
onial | -1.940 |
otor | -1.783 |
agher | -1.774 |
Token | Tro |
Token ID | 8498 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
irtual | +0.262 |
� | +0.254 |
Reply | +0.252 |
roll | +0.237 |
Stra | +0.233 |
Neg logit contributions | |
merce | -0.282 |
bour | -0.274 |
onial | -0.272 |
otor | -0.247 |
agher | -0.247 |
Token | been |
Token ID | 587 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
merce | +1.225 |
bour | +1.196 |
onial | +1.191 |
agher | +1.079 |
otor | +1.070 |
Neg logit contributions | |
irtual | -1.257 |
Reply | -1.211 |
� | -1.210 |
roll | -1.140 |
Stra | -1.121 |
Token | much |
Token ID | 881 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
merce | +0.497 |
bour | +0.487 |
onial | +0.483 |
agher | +0.443 |
otor | +0.442 |
Neg logit contributions | |
irtual | -0.422 |
� | -0.405 |
Reply | -0.401 |
roll | -0.376 |
Stra | -0.371 |
Token | bigger |
Token ID | 5749 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
merce | +0.587 |
bour | +0.574 |
onial | +0.570 |
agher | +0.524 |
otor | +0.524 |
Neg logit contributions | |
irtual | -0.402 |
� | -0.386 |
Reply | -0.383 |
roll | -0.356 |
Stra | -0.350 |
Token | satellites |
Token ID | 20372 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
merce | +0.719 |
bour | +0.708 |
onial | +0.697 |
otor | +0.645 |
agher | +0.640 |
Neg logit contributions | |
irtual | -0.539 |
� | -0.515 |
Reply | -0.509 |
roll | -0.472 |
Stra | -0.468 |
Token | making |
Token ID | 1642 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
merce | +0.140 |
bour | +0.136 |
onial | +0.135 |
otor | +0.123 |
agher | +0.123 |
Neg logit contributions | |
irtual | -0.123 |
� | -0.119 |
Reply | -0.118 |
roll | -0.111 |
Stra | -0.109 |
Token | uncontrolled |
Token ID | 47913 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
irtual | +1.757 |
� | +1.705 |
Reply | +1.704 |
roll | +1.617 |
Stra | +1.577 |
Neg logit contributions | |
merce | -1.939 |
bour | -1.886 |
onial | -1.880 |
agher | -1.704 |
otor | -1.694 |
Token | re |
Token ID | 302 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
irtual | +3.234 |
� | +3.136 |
Reply | +3.121 |
roll | +2.985 |
Stra | +2.902 |
Neg logit contributions | |
merce | -4.269 |
bour | -4.134 |
onial | -4.113 |
agher | -3.777 |
otor | -3.727 |
Token | - |
Token ID | 12 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
merce | +0.324 |
bour | +0.314 |
onial | +0.313 |
otor | +0.285 |
agher | +0.284 |
Neg logit contributions | |
irtual | -0.279 |
� | -0.270 |
Reply | -0.269 |
roll | -0.252 |
Stra | -0.248 |
Token | ent |
Token ID | 298 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
merce | +0.388 |
bour | +0.380 |
onial | +0.376 |
otor | +0.344 |
agher | +0.341 |
Neg logit contributions | |
irtual | -0.338 |
� | -0.329 |
Reply | -0.327 |
roll | -0.301 |
Stra | -0.299 |
Token | ries |
Token ID | 1678 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
merce | +1.685 |
bour | +1.659 |
onial | +1.648 |
otor | +1.476 |
agher | +1.443 |
Neg logit contributions | |
irtual | -1.895 |
� | -1.863 |
Reply | -1.845 |
Stra | -1.708 |
ELL | -1.703 |
Token | in |
Token ID | 287 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
merce | +0.104 |
bour | +0.102 |
onial | +0.101 |
otor | +0.092 |
agher | +0.092 |
Neg logit contributions | |
irtual | -0.084 |
� | -0.081 |
Reply | -0.081 |
roll | -0.076 |
Stra | -0.074 |
Token | it |
Token ID | 340 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
irtual | +1.114 |
� | +1.083 |
Reply | +1.062 |
roll | +1.003 |
Stra | +0.979 |
Neg logit contributions | |
merce | -1.879 |
bour | -1.820 |
onial | -1.812 |
otor | -1.676 |
agher | -1.669 |
Token | ble |
Token ID | 7245 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
irtual | +0.210 |
� | +0.201 |
Reply | +0.201 |
roll | +0.185 |
Stra | +0.182 |
Neg logit contributions | |
merce | -0.319 |
bour | -0.312 |
onial | -0.310 |
otor | -0.285 |
agher | -0.285 |
Token | eds |
Token ID | 5379 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
irtual | +0.088 |
� | +0.086 |
Reply | +0.085 |
roll | +0.082 |
Stra | +0.080 |
Neg logit contributions | |
merce | -0.071 |
bour | -0.069 |
onial | -0.069 |
otor | -0.061 |
agher | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | +6.98e-04 |
Pos logit contributions | |
merce | +0.535 |
bour | +0.519 |
onial | +0.517 |
otor | +0.471 |
agher | +0.470 |
Neg logit contributions | |
irtual | -0.444 |
� | -0.429 |
Reply | -0.427 |
roll | -0.401 |
Stra | -0.393 |
Token | you |
Token ID | 345 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
merce | +0.002 |
bour | +0.002 |
onial | +0.002 |
otor | +0.002 |
agher | +0.002 |
Neg logit contributions | |
irtual | -0.001 |
� | -0.001 |
Reply | -0.001 |
roll | -0.001 |
Stra | -0.001 |
Token | let |
Token ID | 1309 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
irtual | +0.082 |
� | +0.079 |
Reply | +0.079 |
roll | +0.073 |
Stra | +0.072 |
Neg logit contributions | |
merce | -0.123 |
bour | -0.119 |
onial | -0.119 |
otor | -0.109 |
agher | -0.109 |
Token | it |
Token ID | 340 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
irtual | +3.194 |
� | +3.124 |
Reply | +3.040 |
roll | +2.990 |
Stra | +2.868 |
Neg logit contributions | |
merce | -4.821 |
onial | -4.657 |
bour | -4.603 |
agher | -4.243 |
otor | -4.240 |
Token | dry |
Token ID | 5894 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
irtual | +0.130 |
� | +0.126 |
Reply | +0.126 |
roll | +0.119 |
Stra | +0.117 |
Neg logit contributions | |
merce | -0.125 |
bour | -0.121 |
onial | -0.120 |
otor | -0.108 |
agher | -0.108 |
Token | and |
Token ID | 290 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
merce | +0.412 |
bour | +0.400 |
onial | +0.398 |
otor | +0.364 |
agher | +0.363 |
Neg logit contributions | |
irtual | -0.333 |
� | -0.322 |
Reply | -0.320 |
roll | -0.300 |
Stra | -0.294 |
Token | paint |
Token ID | 7521 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
merce | +0.400 |
bour | +0.391 |
onial | +0.388 |
otor | +0.358 |
agher | +0.357 |
Neg logit contributions | |
irtual | -0.262 |
� | -0.252 |
Reply | -0.250 |
roll | -0.231 |
Stra | -0.226 |
Token | over |
Token ID | 625 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
merce | +1.296 |
bour | +1.261 |
onial | +1.251 |
otor | +1.145 |
agher | +1.142 |
Neg logit contributions | |
irtual | -1.092 |
� | -1.056 |
Reply | -1.050 |
roll | -0.978 |
Stra | -0.965 |
Token | will |
Token ID | 481 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
irtual | +0.059 |
� | +0.057 |
Reply | +0.057 |
roll | +0.053 |
Stra | +0.052 |
Neg logit contributions | |
merce | -0.075 |
bour | -0.074 |
onial | -0.073 |
otor | -0.067 |
agher | -0.067 |
Token | have |
Token ID | 423 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
irtual | +0.054 |
� | +0.052 |
Reply | +0.052 |
roll | +0.049 |
Stra | +0.048 |
Neg logit contributions | |
merce | -0.068 |
bour | -0.066 |
onial | -0.066 |
otor | -0.060 |
agher | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
irtual | +0.494 |
� | +0.478 |
Reply | +0.476 |
roll | +0.450 |
Stra | +0.441 |
Neg logit contributions | |
merce | -0.523 |
bour | -0.505 |
onial | -0.503 |
otor | -0.456 |
agher | -0.454 |
Token | stall |
Token ID | 22549 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
irtual | +0.675 |
� | +0.657 |
Reply | +0.655 |
roll | +0.623 |
Stra | +0.612 |
Neg logit contributions | |
merce | -0.572 |
bour | -0.551 |
onial | -0.549 |
otor | -0.490 |
agher | -0.489 |
Token | as |
Token ID | 355 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
merce | +1.361 |
bour | +1.326 |
onial | +1.317 |
otor | +1.205 |
agher | +1.201 |
Neg logit contributions | |
irtual | -1.095 |
� | -1.058 |
Reply | -1.053 |
roll | -0.982 |
Stra | -0.967 |
Token | well |
Token ID | 880 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
merce | +0.058 |
bour | +0.056 |
onial | +0.056 |
otor | +0.050 |
agher | +0.050 |
Neg logit contributions | |
irtual | -0.061 |
� | -0.059 |
Reply | -0.059 |
roll | -0.056 |
Stra | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
irtual | +4.347 |
� | +4.170 |
Reply | +4.150 |
roll | +4.027 |
Stra | +3.829 |
Neg logit contributions | |
merce | -5.641 |
bour | -5.434 |
onial | -5.430 |
agher | -4.967 |
otor | -4.941 |
Token | so |
Token ID | 523 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
irtual | +0.111 |
� | +0.108 |
Reply | +0.107 |
roll | +0.100 |
Stra | +0.098 |
Neg logit contributions | |
merce | -0.141 |
bour | -0.137 |
onial | -0.136 |
otor | -0.124 |
agher | -0.124 |
Token | pop |
Token ID | 1461 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
merce | +0.763 |
bour | +0.749 |
onial | +0.743 |
otor | +0.682 |
agher | +0.680 |
Neg logit contributions | |
irtual | -0.564 |
� | -0.544 |
Reply | -0.540 |
roll | -0.498 |
Stra | -0.492 |
Token | by |
Token ID | 416 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
irtual | +0.671 |
� | +0.648 |
Reply | +0.645 |
roll | +0.602 |
Stra | +0.590 |
Neg logit contributions | |
merce | -0.899 |
bour | -0.874 |
onial | -0.869 |
otor | -0.797 |
agher | -0.795 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
irtual | +0.045 |
� | +0.043 |
Reply | +0.043 |
roll | +0.040 |
Stra | +0.040 |
Neg logit contributions | |
merce | -0.057 |
bour | -0.055 |
onial | -0.055 |
otor | -0.050 |
agher | -0.050 |
Token | fy |
Token ID | 24928 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
irtual | +0.618 |
� | +0.595 |
Reply | +0.590 |
roll | +0.549 |
Stra | +0.540 |
Neg logit contributions | |
merce | -0.810 |
bour | -0.794 |
onial | -0.789 |
otor | -0.721 |
agher | -0.719 |
Token | mini |
Token ID | 9927 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
irtual | +0.323 |
� | +0.313 |
Reply | +0.311 |
roll | +0.293 |
Stra | +0.288 |
Neg logit contributions | |
merce | -0.357 |
bour | -0.346 |
onial | -0.344 |
otor | -0.313 |
agher | -0.312 |
Token | Tin |
Token ID | 22894 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
irtual | +0.369 |
� | +0.357 |
Reply | +0.355 |
roll | +0.335 |
Stra | +0.328 |
Neg logit contributions | |
merce | -0.434 |
bour | -0.421 |
onial | -0.419 |
otor | -0.382 |
agher | -0.381 |
Token | Man |
Token ID | 1869 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
merce | +1.262 |
bour | +1.242 |
onial | +1.230 |
agher | +1.128 |
otor | +1.126 |
Neg logit contributions | |
irtual | -1.003 |
� | -0.962 |
Reply | -0.955 |
roll | -0.886 |
Stra | -0.877 |
Token | as |
Token ID | 355 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
irtual | +0.893 |
� | +0.864 |
Reply | +0.862 |
roll | +0.814 |
Stra | +0.798 |
Neg logit contributions | |
merce | -0.994 |
bour | -0.963 |
onial | -0.960 |
otor | -0.869 |
agher | -0.868 |
Token | well |
Token ID | 880 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
merce | +0.316 |
bour | +0.307 |
onial | +0.305 |
otor | +0.275 |
agher | +0.275 |
Neg logit contributions | |
irtual | -0.322 |
� | -0.312 |
Reply | -0.311 |
roll | -0.293 |
Stra | -0.289 |
Token | as |
Token ID | 355 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
irtual | +3.333 |
� | +3.221 |
Reply | +3.163 |
roll | +3.068 |
Stra | +2.848 |
Neg logit contributions | |
merce | -6.424 |
bour | -6.285 |
onial | -6.284 |
otor | -5.822 |
agher | -5.782 |
Token | the |
Token ID | 262 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
irtual | +0.950 |
� | +0.920 |
Reply | +0.918 |
roll | +0.867 |
Stra | +0.848 |
Neg logit contributions | |
merce | -1.097 |
bour | -1.059 |
onial | -1.056 |
otor | -0.962 |
agher | -0.958 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
irtual | +0.364 |
� | +0.352 |
Reply | +0.350 |
roll | +0.329 |
Stra | +0.323 |
Neg logit contributions | |
merce | -0.423 |
bour | -0.410 |
onial | -0.408 |
otor | -0.372 |
agher | -0.371 |
Token | Never |
Token ID | 7236 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
irtual | +1.408 |
� | +1.366 |
Reply | +1.364 |
roll | +1.290 |
Stra | +1.261 |
Neg logit contributions | |
merce | -1.640 |
bour | -1.582 |
onial | -1.573 |
otor | -1.436 |
agher | -1.433 |
Token | land |
Token ID | 1044 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
merce | +0.768 |
bour | +0.746 |
onial | +0.743 |
otor | +0.680 |
agher | +0.679 |
Neg logit contributions | |
irtual | -0.582 |
� | -0.563 |
Reply | -0.561 |
roll | -0.524 |
Stra | -0.514 |
Token | content |
Token ID | 2695 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
merce | +1.327 |
bour | +1.301 |
onial | +1.291 |
agher | +1.192 |
otor | +1.182 |
Neg logit contributions | |
irtual | -0.941 |
� | -0.903 |
Reply | -0.894 |
roll | -0.828 |
Stra | -0.811 |
Token | on |
Token ID | 319 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
merce | +1.496 |
bour | +1.467 |
onial | +1.462 |
agher | +1.335 |
otor | +1.325 |
Neg logit contributions | |
irtual | -1.285 |
� | -1.231 |
Reply | -1.222 |
roll | -1.141 |
Stra | -1.125 |
Token | social |
Token ID | 1919 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
irtual | +0.547 |
� | +0.529 |
Reply | +0.525 |
roll | +0.490 |
Stra | +0.482 |
Neg logit contributions | |
merce | -0.704 |
bour | -0.685 |
onial | -0.682 |
otor | -0.624 |
agher | -0.623 |
Token | media |
Token ID | 2056 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
irtual | +1.568 |
� | +1.496 |
Reply | +1.478 |
roll | +1.353 |
Stra | +1.294 |
Neg logit contributions | |
merce | -3.692 |
bour | -3.610 |
onial | -3.595 |
agher | -3.353 |
otor | -3.349 |
Token | as |
Token ID | 355 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
irtual | +1.939 |
� | +1.885 |
Reply | +1.877 |
roll | +1.767 |
Stra | +1.732 |
Neg logit contributions | |
merce | -2.268 |
bour | -2.193 |
onial | -2.183 |
otor | -1.989 |
agher | -1.977 |
Token | well |
Token ID | 880 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
merce | +0.122 |
bour | +0.119 |
onial | +0.118 |
agher | +0.107 |
otor | +0.106 |
Neg logit contributions | |
irtual | -0.138 |
� | -0.133 |
Reply | -0.133 |
roll | -0.126 |
Stra | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
irtual | +4.471 |
� | +4.389 |
Reply | +4.386 |
roll | +4.172 |
Stra | +4.014 |
Neg logit contributions | |
merce | -5.583 |
bour | -5.412 |
onial | -5.330 |
otor | -4.895 |
agher | -4.790 |
Token | such |
Token ID | 884 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
irtual | +0.148 |
� | +0.143 |
Reply | +0.142 |
roll | +0.133 |
Stra | +0.131 |
Neg logit contributions | |
merce | -0.180 |
bour | -0.175 |
onial | -0.174 |
agher | -0.159 |
otor | -0.159 |
Token | as |
Token ID | 355 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
irtual | +0.307 |
� | +0.294 |
Reply | +0.291 |
roll | +0.270 |
Stra | +0.267 |
Neg logit contributions | |
merce | -0.403 |
bour | -0.395 |
onial | -0.391 |
agher | -0.360 |
otor | -0.359 |
Token | when |
Token ID | 618 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
merce | +0.290 |
bour | +0.282 |
onial | +0.281 |
agher | +0.256 |
otor | +0.255 |
Neg logit contributions | |
irtual | -0.257 |
� | -0.248 |
Reply | -0.246 |
roll | -0.231 |
Stra | -0.228 |
Token | he |
Token ID | 339 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
irtual | +0.260 |
� | +0.250 |
Reply | +0.249 |
roll | +0.232 |
Stra | +0.228 |
Neg logit contributions | |
merce | -0.349 |
bour | -0.340 |
onial | -0.338 |
agher | -0.310 |
otor | -0.310 |