Token | league |
Token ID | 4652 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
asma | +1.502 |
Hermes | +1.308 |
alion | +1.239 |
yrus | +1.200 |
rodent | +1.195 |
Neg logit contributions | |
ancial | -1.248 |
culosis | -1.219 |
pload | -1.013 |
Klu | -1.009 |
reck | -1.003 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
asma | +1.950 |
Hermes | +1.669 |
alion | +1.579 |
yrus | +1.518 |
rodent | +1.502 |
Neg logit contributions | |
ancial | -1.929 |
culosis | -1.877 |
Klu | -1.617 |
pload | -1.598 |
orkshire | -1.591 |
Token | The |
Token ID | 383 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ancial | +1.659 |
culosis | +1.604 |
Klu | +1.421 |
reck | +1.369 |
pload | +1.362 |
Neg logit contributions | |
asma | -1.839 |
Hermes | -1.559 |
alion | -1.502 |
yrus | -1.463 |
rodent | -1.434 |
Token | future |
Token ID | 2003 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ancial | +1.198 |
culosis | +1.158 |
Klu | +0.991 |
reck | +0.973 |
pload | +0.970 |
Neg logit contributions | |
asma | -1.441 |
Hermes | -1.247 |
alion | -1.187 |
yrus | -1.146 |
rodent | -1.131 |
Token | Hall |
Token ID | 4789 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
asma | +0.099 |
Hermes | +0.085 |
alion | +0.080 |
yrus | +0.077 |
rodent | +0.076 |
Neg logit contributions | |
ancial | -0.099 |
culosis | -0.096 |
Klu | -0.082 |
pload | -0.082 |
reck | -0.081 |
Token | of |
Token ID | 286 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ancial | +1.940 |
culosis | +1.869 |
Klu | +1.617 |
reck | +1.591 |
ilege | +1.586 |
Neg logit contributions | |
asma | -2.237 |
Hermes | -1.921 |
alion | -1.825 |
yrus | -1.775 |
rodent | -1.737 |
Token | F |
Token ID | 376 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
ancial | +7.689 |
culosis | +7.336 |
Klu | +6.799 |
FIN | +6.066 |
ilege | +6.039 |
Neg logit contributions | |
asma | -13.001 |
alion | -11.184 |
yrus | -11.051 |
Hermes | -10.841 |
ods | -10.558 |
Token | amer |
Token ID | 2382 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ancial | +2.185 |
culosis | +2.070 |
reck | +1.708 |
ilege | +1.666 |
Klu | +1.652 |
Neg logit contributions | |
asma | -4.124 |
Hermes | -3.717 |
alion | -3.544 |
rodent | -3.477 |
yrus | -3.421 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ancial | +1.825 |
culosis | +1.778 |
Klu | +1.560 |
reck | +1.530 |
pload | +1.524 |
Neg logit contributions | |
asma | -1.730 |
Hermes | -1.470 |
alion | -1.393 |
yrus | -1.334 |
rodent | -1.310 |
Token | reigning |
Token ID | 40098 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
ancial | +1.125 |
culosis | +1.090 |
Klu | +0.947 |
reck | +0.931 |
pload | +0.928 |
Neg logit contributions | |
asma | -1.154 |
Hermes | -0.985 |
alion | -0.935 |
yrus | -0.899 |
rodent | -0.886 |
Token | Super |
Token ID | 3115 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
asma | +2.699 |
Hermes | +2.387 |
alion | +2.216 |
rodent | +2.145 |
yrus | +2.113 |
Neg logit contributions | |
ancial | -2.443 |
culosis | -2.392 |
ilege | -1.997 |
reck | -1.995 |
pload | -1.994 |
Token | hugely |
Token ID | 22641 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ancial | +0.611 |
culosis | +0.594 |
Klu | +0.522 |
reck | +0.512 |
pload | +0.510 |
Neg logit contributions | |
asma | -0.568 |
Hermes | -0.480 |
alion | -0.455 |
yrus | -0.436 |
rodent | -0.427 |
Token | popular |
Token ID | 2968 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ancial | +1.442 |
culosis | +1.400 |
Klu | +1.223 |
reck | +1.200 |
pload | +1.191 |
Neg logit contributions | |
asma | -1.475 |
Hermes | -1.256 |
alion | -1.197 |
yrus | -1.151 |
rodent | -1.122 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ancial | +1.205 |
culosis | +1.166 |
Klu | +1.010 |
reck | +0.991 |
pload | +0.988 |
Neg logit contributions | |
asma | -1.295 |
Hermes | -1.110 |
alion | -1.053 |
yrus | -1.012 |
rodent | -0.997 |
Token | Future |
Token ID | 10898 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
ancial | +0.126 |
culosis | +0.123 |
Klu | +0.106 |
reck | +0.105 |
pload | +0.105 |
Neg logit contributions | |
asma | -0.120 |
Hermes | -0.102 |
alion | -0.097 |
yrus | -0.093 |
rodent | -0.091 |
Token | Hall |
Token ID | 4789 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
asma | +0.366 |
Hermes | +0.311 |
alion | +0.293 |
yrus | +0.282 |
rodent | +0.280 |
Neg logit contributions | |
ancial | -0.384 |
culosis | -0.373 |
Klu | -0.322 |
reck | -0.319 |
pload | -0.318 |
Token | of |
Token ID | 286 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ancial | +1.101 |
culosis | +1.066 |
Klu | +0.924 |
reck | +0.903 |
pload | +0.899 |
Neg logit contributions | |
asma | -1.257 |
Hermes | -1.079 |
alion | -1.024 |
yrus | -0.996 |
rodent | -0.977 |
Token | Fame |
Token ID | 18864 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ancial | +7.690 |
culosis | +7.468 |
Klu | +6.739 |
pload | +6.137 |
ilege | +6.132 |
Neg logit contributions | |
asma | -10.557 |
alion | -8.931 |
Hermes | -8.785 |
yrus | -8.748 |
opus | -8.286 |
Token | slug |
Token ID | 31065 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
ancial | +1.176 |
culosis | +1.142 |
Klu | +1.004 |
reck | +0.985 |
pload | +0.982 |
Neg logit contributions | |
asma | -1.076 |
Hermes | -0.907 |
alion | -0.860 |
yrus | -0.825 |
rodent | -0.806 |
Token | ger |
Token ID | 1362 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
asma | +2.898 |
Hermes | +2.548 |
alion | +2.416 |
yrus | +2.330 |
rodent | +2.325 |
Neg logit contributions | |
ancial | -2.179 |
culosis | -2.097 |
ilege | -1.769 |
Klu | -1.743 |
orkshire | -1.738 |
Token | Stan |
Token ID | 7299 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
ancial | +0.777 |
culosis | +0.750 |
Klu | +0.635 |
reck | +0.624 |
pload | +0.623 |
Neg logit contributions | |
asma | -1.000 |
Hermes | -0.870 |
alion | -0.829 |
yrus | -0.801 |
rodent | -0.792 |
Token | Mus |
Token ID | 2629 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
ancial | +2.977 |
culosis | +2.896 |
Klu | +2.563 |
pload | +2.480 |
reck | +2.475 |
Neg logit contributions | |
asma | -3.048 |
Hermes | -2.569 |
alion | -2.470 |
yrus | -2.392 |
rodent | -2.352 |
Token | into |
Token ID | 656 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ancial | +0.576 |
culosis | +0.560 |
Klu | +0.493 |
reck | +0.485 |
pload | +0.483 |
Neg logit contributions | |
asma | -0.520 |
Hermes | -0.435 |
alion | -0.414 |
yrus | -0.396 |
rodent | -0.389 |
Token | Canada |
Token ID | 3340 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ancial | +0.167 |
culosis | +0.162 |
Klu | +0.141 |
reck | +0.138 |
pload | +0.138 |
Neg logit contributions | |
asma | -0.160 |
Hermes | -0.136 |
alion | -0.129 |
yrus | -0.124 |
rodent | -0.122 |
Token | 's |
Token ID | 338 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
ancial | +1.707 |
culosis | +1.646 |
Klu | +1.417 |
reck | +1.377 |
pload | +1.375 |
Neg logit contributions | |
asma | -2.222 |
Hermes | -1.926 |
alion | -1.850 |
yrus | -1.785 |
rodent | -1.757 |
Token | Soccer |
Token ID | 15872 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ancial | +3.388 |
culosis | +3.237 |
Klu | +2.956 |
reck | +2.779 |
ement | +2.767 |
Neg logit contributions | |
asma | -3.981 |
Hermes | -3.349 |
alion | -3.278 |
yrus | -3.166 |
rodent | -3.048 |
Token | Hall |
Token ID | 4789 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
asma | +0.200 |
Hermes | +0.171 |
alion | +0.163 |
yrus | +0.156 |
rodent | +0.154 |
Neg logit contributions | |
ancial | -0.197 |
culosis | -0.191 |
Klu | -0.165 |
pload | -0.164 |
reck | -0.163 |
Token | of |
Token ID | 286 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
ancial | +1.658 |
culosis | +1.601 |
Klu | +1.371 |
reck | +1.352 |
ilege | +1.349 |
Neg logit contributions | |
asma | -1.990 |
Hermes | -1.710 |
alion | -1.608 |
yrus | -1.583 |
rodent | -1.550 |
Token | Fame |
Token ID | 18864 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
ancial | +4.827 |
culosis | +4.495 |
Klu | +3.810 |
ilege | +3.533 |
ement | +3.335 |
Neg logit contributions | |
asma | -12.387 |
yrus | -10.706 |
alion | -10.703 |
Hermes | -10.645 |
opus | -10.343 |
Token | on |
Token ID | 319 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ancial | +2.666 |
culosis | +2.589 |
Klu | +2.277 |
reck | +2.234 |
pload | +2.225 |
Neg logit contributions | |
asma | -2.973 |
Hermes | -2.507 |
alion | -2.424 |
yrus | -2.326 |
rodent | -2.257 |
Token | Nov |
Token ID | 5267 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
ancial | +0.219 |
culosis | +0.212 |
Klu | +0.183 |
reck | +0.180 |
pload | +0.180 |
Neg logit contributions | |
asma | -0.245 |
Hermes | -0.210 |
alion | -0.200 |
yrus | -0.193 |
rodent | -0.190 |
Token | . |
Token ID | 13 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
ancial | +2.689 |
culosis | +2.534 |
Klu | +2.284 |
reck | +2.210 |
ement | +2.191 |
Neg logit contributions | |
asma | -3.750 |
Hermes | -3.229 |
alion | -3.131 |
yrus | -3.053 |
rodent | -3.003 |
Token | 8 |
Token ID | 807 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
ancial | +2.689 |
culosis | +2.603 |
Klu | +2.420 |
reck | +2.289 |
ement | +2.263 |
Neg logit contributions | |
asma | -3.060 |
Hermes | -2.534 |
alion | -2.513 |
yrus | -2.461 |
rodent | -2.368 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
asma | +0.284 |
Hermes | +0.241 |
alion | +0.228 |
yrus | +0.219 |
rodent | +0.216 |
Neg logit contributions | |
ancial | -0.294 |
culosis | -0.285 |
Klu | -0.249 |
reck | -0.245 |
pload | -0.244 |
Token | a |
Token ID | 257 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
asma | +0.825 |
Hermes | +0.707 |
alion | +0.664 |
yrus | +0.638 |
rodent | +0.633 |
Neg logit contributions | |
ancial | -0.879 |
culosis | -0.852 |
Klu | -0.735 |
reck | -0.728 |
pload | -0.726 |
Token | fellow |
Token ID | 5891 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ancial | +0.453 |
culosis | +0.439 |
Klu | +0.380 |
reck | +0.375 |
pload | +0.374 |
Neg logit contributions | |
asma | -0.445 |
Hermes | -0.380 |
alion | -0.358 |
yrus | -0.345 |
rodent | -0.342 |
Token | future |
Token ID | 2003 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ancial | +1.032 |
culosis | +1.001 |
Klu | +0.864 |
reck | +0.852 |
pload | +0.849 |
Neg logit contributions | |
asma | -1.067 |
Hermes | -0.914 |
alion | -0.864 |
yrus | -0.832 |
rodent | -0.823 |
Token | Hall |
Token ID | 4789 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
asma | +1.123 |
Hermes | +0.964 |
alion | +0.900 |
rodent | +0.869 |
yrus | +0.865 |
Neg logit contributions | |
ancial | -1.158 |
culosis | -1.128 |
Klu | -0.960 |
reck | -0.959 |
ilege | -0.952 |
Token | of |
Token ID | 286 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
ancial | +0.967 |
culosis | +0.934 |
Klu | +0.809 |
reck | +0.792 |
pload | +0.792 |
Neg logit contributions | |
asma | -1.075 |
Hermes | -0.924 |
alion | -0.875 |
yrus | -0.848 |
rodent | -0.832 |
Token | F |
Token ID | 376 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ancial | +6.152 |
culosis | +5.851 |
Klu | +5.346 |
pload | +4.966 |
ilege | +4.914 |
Neg logit contributions | |
asma | -10.576 |
alion | -9.150 |
yrus | -8.896 |
Hermes | -8.789 |
ods | -8.387 |
Token | amer |
Token ID | 2382 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ancial | +1.155 |
culosis | +1.106 |
reck | +0.902 |
Klu | +0.897 |
ilege | +0.893 |
Neg logit contributions | |
asma | -2.029 |
Hermes | -1.810 |
alion | -1.730 |
rodent | -1.685 |
yrus | -1.673 |
Token | , |
Token ID | 11 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
ancial | +0.926 |
culosis | +0.899 |
Klu | +0.781 |
reck | +0.767 |
pload | +0.765 |
Neg logit contributions | |
asma | -0.943 |
Hermes | -0.805 |
alion | -0.763 |
yrus | -0.734 |
rodent | -0.723 |
Token | stopped |
Token ID | 5025 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ancial | +0.734 |
culosis | +0.716 |
Klu | +0.631 |
pload | +0.617 |
reck | +0.617 |
Neg logit contributions | |
asma | -0.686 |
Hermes | -0.578 |
alion | -0.549 |
yrus | -0.527 |
rodent | -0.514 |
Token | by |
Token ID | 416 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
asma | +1.379 |
Hermes | +1.175 |
alion | +1.097 |
yrus | +1.063 |
rodent | +1.052 |
Neg logit contributions | |
ancial | -1.610 |
culosis | -1.561 |
Klu | -1.347 |
pload | -1.344 |
reck | -1.341 |
Token | the |
Token ID | 262 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
asma | +0.351 |
Hermes | +0.297 |
alion | +0.281 |
yrus | +0.270 |
rodent | +0.266 |
Neg logit contributions | |
ancial | -0.369 |
culosis | -0.358 |
Klu | -0.312 |
reck | -0.307 |
pload | -0.306 |
Token | National |
Token ID | 2351 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
asma | +0.248 |
Hermes | +0.212 |
alion | +0.201 |
yrus | +0.193 |
rodent | +0.191 |
Neg logit contributions | |
ancial | -0.242 |
culosis | -0.235 |
Klu | -0.204 |
reck | -0.200 |
pload | -0.200 |
Token | Women |
Token ID | 6926 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
asma | +0.881 |
Hermes | +0.745 |
alion | +0.704 |
yrus | +0.676 |
rodent | +0.666 |
Neg logit contributions | |
ancial | -0.959 |
culosis | -0.932 |
Klu | -0.815 |
reck | -0.802 |
pload | -0.800 |
Token | 's |
Token ID | 338 |
Feature activation | +6.71e+00 |
Pos logit contributions | |
ancial | +0.378 |
culosis | +0.366 |
Klu | +0.312 |
reck | +0.307 |
pload | +0.306 |
Neg logit contributions | |
asma | -0.460 |
Hermes | -0.398 |
alion | -0.379 |
yrus | -0.366 |
rodent | -0.362 |
Token | Hall |
Token ID | 4789 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
ancial | +5.547 |
culosis | +5.381 |
Klu | +4.812 |
ilege | +4.608 |
reck | +4.594 |
Neg logit contributions | |
asma | -5.271 |
Hermes | -4.317 |
alion | -4.262 |
yrus | -4.218 |
rodent | -3.971 |
Token | of |
Token ID | 286 |
Feature activation | +9.79e+00 |
Pos logit contributions | |
ancial | +2.343 |
culosis | +2.283 |
Klu | +1.948 |
reck | +1.928 |
ilege | +1.915 |
Neg logit contributions | |
asma | -2.794 |
Hermes | -2.394 |
alion | -2.276 |
yrus | -2.217 |
rodent | -2.187 |
Token | Fame |
Token ID | 18864 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ancial | +5.197 |
culosis | +4.977 |
Klu | +4.187 |
ilege | +3.921 |
reck | +3.787 |
Neg logit contributions | |
asma | -10.398 |
alion | -8.867 |
Hermes | -8.759 |
yrus | -8.714 |
ods | -8.469 |
Token | .[ |
Token ID | 3693 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
ancial | +2.286 |
culosis | +2.225 |
Klu | +1.915 |
reck | +1.894 |
pload | +1.875 |
Neg logit contributions | |
asma | -2.591 |
Hermes | -2.207 |
alion | -2.120 |
yrus | -2.038 |
rodent | -2.010 |
Token | 49 |
Token ID | 2920 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
ancial | +0.040 |
culosis | +0.039 |
Klu | +0.033 |
pload | +0.032 |
reck | +0.032 |
Neg logit contributions | |
asma | -0.051 |
Hermes | -0.044 |
alion | -0.042 |
yrus | -0.041 |
rodent | -0.040 |
Token | ] |
Token ID | 60 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ancial | +0.654 |
culosis | +0.632 |
Klu | +0.539 |
reck | +0.529 |
pload | +0.528 |
Neg logit contributions | |
asma | -0.820 |
Hermes | -0.712 |
alion | -0.679 |
yrus | -0.657 |
rodent | -0.649 |
Token | On |
Token ID | 1550 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
asma | +0.782 |
Hermes | +0.664 |
alion | +0.619 |
yrus | +0.590 |
rodent | +0.583 |
Neg logit contributions | |
ancial | -0.902 |
culosis | -0.876 |
Klu | -0.764 |
reck | -0.757 |
pload | -0.757 |
Token | � |
Token ID | 447 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
asma | +0.317 |
Hermes | +0.272 |
alion | +0.258 |
yrus | +0.248 |
rodent | +0.245 |
Neg logit contributions | |
ancial | -0.301 |
culosis | -0.292 |
Klu | -0.252 |
reck | -0.248 |
pload | -0.247 |
Token | � |
Token ID | 247 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
ancial | +0.691 |
culosis | +0.675 |
Klu | +0.620 |
reck | +0.614 |
ilege | +0.611 |
Neg logit contributions | |
asma | -0.255 |
Hermes | -0.188 |
alion | -0.164 |
yrus | -0.151 |
rodent | -0.145 |
Token | s |
Token ID | 82 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
asma | +0.608 |
Hermes | +0.519 |
alion | +0.489 |
yrus | +0.470 |
rodent | +0.464 |
Neg logit contributions | |
ancial | -0.632 |
culosis | -0.614 |
Klu | -0.534 |
reck | -0.527 |
pload | -0.525 |
Token | protests |
Token ID | 8536 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
ancial | +0.746 |
culosis | +0.719 |
Klu | +0.619 |
reck | +0.604 |
ilege | +0.598 |
Neg logit contributions | |
asma | -0.963 |
Hermes | -0.834 |
alion | -0.799 |
yrus | -0.773 |
rodent | -0.758 |
Token | with |
Token ID | 351 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ancial | +2.153 |
culosis | +2.089 |
Klu | +1.812 |
reck | +1.803 |
pload | +1.775 |
Neg logit contributions | |
asma | -2.441 |
Hermes | -2.099 |
alion | -1.986 |
yrus | -1.935 |
rodent | -1.885 |
Token | relative |
Token ID | 3585 |
Feature activation | +9.57e+00 |
Pos logit contributions | |
ancial | +1.177 |
culosis | +1.143 |
Klu | +0.995 |
reck | +0.980 |
pload | +0.977 |
Neg logit contributions | |
asma | -1.160 |
Hermes | -0.987 |
alion | -0.935 |
yrus | -0.900 |
rodent | -0.883 |
Token | len |
Token ID | 18896 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
ancial | +6.454 |
culosis | +6.400 |
Klu | +5.584 |
reck | +5.550 |
ilege | +5.486 |
Neg logit contributions | |
asma | -8.413 |
Hermes | -7.143 |
alion | -7.042 |
yrus | -6.870 |
opus | -6.523 |
Token | iency |
Token ID | 6160 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
ancial | +2.487 |
culosis | +2.342 |
ilege | +1.916 |
reck | +1.897 |
Klu | +1.896 |
Neg logit contributions | |
asma | -4.353 |
Hermes | -3.889 |
alion | -3.695 |
yrus | -3.602 |
rodent | -3.561 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ancial | +2.946 |
culosis | +2.824 |
Klu | +2.434 |
reck | +2.413 |
ement | +2.385 |
Neg logit contributions | |
asma | -3.561 |
Hermes | -3.075 |
alion | -2.930 |
yrus | -2.832 |
rodent | -2.765 |
Token | Although |
Token ID | 4900 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ancial | +2.187 |
culosis | +2.115 |
Klu | +1.882 |
reck | +1.823 |
pload | +1.810 |
Neg logit contributions | |
asma | -2.074 |
Hermes | -1.736 |
alion | -1.674 |
yrus | -1.626 |
rodent | -1.599 |
Token | tear |
Token ID | 11626 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
ancial | +1.727 |
culosis | +1.652 |
Klu | +1.461 |
reck | +1.421 |
pload | +1.415 |
Neg logit contributions | |
asma | -1.773 |
Hermes | -1.508 |
alion | -1.442 |
yrus | -1.389 |
rodent | -1.351 |
Token | suspect |
Token ID | 4099 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
asma | +2.755 |
Hermes | +2.381 |
alion | +2.227 |
yrus | +2.167 |
rodent | +2.160 |
Neg logit contributions | |
ancial | -2.785 |
culosis | -2.696 |
Klu | -2.328 |
reck | -2.294 |
pload | -2.290 |
Token | most |
Token ID | 749 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
asma | +1.746 |
Hermes | +1.482 |
alion | +1.376 |
yrus | +1.323 |
rodent | +1.306 |
Neg logit contributions | |
ancial | -2.136 |
culosis | -2.069 |
Klu | -1.791 |
pload | -1.783 |
orkshire | -1.782 |
Token | of |
Token ID | 286 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ancial | +1.830 |
culosis | +1.781 |
Klu | +1.558 |
reck | +1.530 |
pload | +1.526 |
Neg logit contributions | |
asma | -1.862 |
Hermes | -1.580 |
alion | -1.500 |
yrus | -1.442 |
rodent | -1.417 |
Token | the |
Token ID | 262 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
ancial | +0.272 |
culosis | +0.264 |
Klu | +0.230 |
reck | +0.226 |
pload | +0.226 |
Neg logit contributions | |
asma | -0.259 |
Hermes | -0.220 |
alion | -0.208 |
yrus | -0.200 |
rodent | -0.197 |
Token | World |
Token ID | 2159 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
ancial | +0.712 |
culosis | +0.691 |
Klu | +0.602 |
reck | +0.593 |
pload | +0.591 |
Neg logit contributions | |
asma | -0.702 |
Hermes | -0.596 |
alion | -0.565 |
yrus | -0.542 |
rodent | -0.535 |
Token | 's |
Token ID | 338 |
Feature activation | +9.32e+00 |
Pos logit contributions | |
ancial | +3.413 |
culosis | +3.318 |
Klu | +2.854 |
reck | +2.812 |
pload | +2.762 |
Neg logit contributions | |
asma | -4.335 |
Hermes | -3.693 |
alion | -3.537 |
yrus | -3.461 |
rodent | -3.375 |
Token | Best |
Token ID | 6705 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ancial | +6.864 |
culosis | +6.786 |
Klu | +5.895 |
reck | +5.858 |
pload | +5.704 |
Neg logit contributions | |
asma | -7.838 |
Hermes | -6.598 |
alion | -6.415 |
yrus | -6.237 |
rodent | -5.972 |
Token | Times |
Token ID | 3782 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
ancial | +2.368 |
culosis | +2.306 |
Klu | +2.006 |
reck | +1.974 |
pload | +1.966 |
Neg logit contributions | |
asma | -2.373 |
Hermes | -2.012 |
alion | -1.913 |
yrus | -1.840 |
rodent | -1.807 |
Token | were |
Token ID | 547 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
ancial | +2.653 |
culosis | +2.571 |
Klu | +2.238 |
reck | +2.203 |
pload | +2.190 |
Neg logit contributions | |
asma | -2.787 |
Hermes | -2.373 |
alion | -2.245 |
yrus | -2.167 |
rodent | -2.146 |
Token | done |
Token ID | 1760 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ancial | +0.844 |
culosis | +0.820 |
Klu | +0.715 |
reck | +0.704 |
pload | +0.703 |
Neg logit contributions | |
asma | -0.784 |
Hermes | -0.665 |
alion | -0.627 |
yrus | -0.602 |
rodent | -0.594 |
Token | on |
Token ID | 319 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
ancial | +1.592 |
culosis | +1.548 |
Klu | +1.342 |
reck | +1.324 |
pload | +1.319 |
Neg logit contributions | |
asma | -1.639 |
Hermes | -1.397 |
alion | -1.326 |
yrus | -1.273 |
rodent | -1.258 |
Token | using |
Token ID | 1262 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
ancial | +0.860 |
culosis | +0.837 |
Klu | +0.728 |
reck | +0.718 |
pload | +0.718 |
Neg logit contributions | |
asma | -0.793 |
Hermes | -0.673 |
alion | -0.632 |
yrus | -0.609 |
rodent | -0.601 |
Token | a |
Token ID | 257 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
asma | +0.507 |
Hermes | +0.435 |
alion | +0.407 |
yrus | +0.391 |
rodent | +0.388 |
Neg logit contributions | |
ancial | -0.534 |
culosis | -0.520 |
Klu | -0.448 |
reck | -0.445 |
pload | -0.443 |
Token | 3 |
Token ID | 513 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ancial | +1.449 |
culosis | +1.406 |
Klu | +1.227 |
reck | +1.206 |
pload | +1.204 |
Neg logit contributions | |
asma | -1.391 |
Hermes | -1.180 |
alion | -1.118 |
yrus | -1.073 |
rodent | -1.057 |
Token | x |
Token ID | 87 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
ancial | +1.731 |
culosis | +1.672 |
Klu | +1.433 |
reck | +1.412 |
pload | +1.408 |
Neg logit contributions | |
asma | -2.068 |
Hermes | -1.796 |
alion | -1.704 |
yrus | -1.638 |
rodent | -1.622 |
Token | 3 |
Token ID | 18 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
ancial | +0.388 |
culosis | +0.377 |
Klu | +0.326 |
reck | +0.321 |
pload | +0.321 |
Neg logit contributions | |
asma | -0.401 |
Hermes | -0.344 |
alion | -0.325 |
yrus | -0.313 |
rodent | -0.309 |
Token | Ga |
Token ID | 12822 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
ancial | +0.756 |
culosis | +0.735 |
Klu | +0.638 |
reck | +0.628 |
pload | +0.626 |
Neg logit contributions | |
asma | -0.733 |
Hermes | -0.625 |
alion | -0.591 |
yrus | -0.568 |
rodent | -0.560 |
Token | ussian |
Token ID | 31562 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ancial | +3.671 |
culosis | +3.409 |
Klu | +2.686 |
Strike | +2.609 |
ilege | +2.566 |
Neg logit contributions | |
asma | -10.772 |
Hermes | -9.776 |
alion | -9.419 |
yrus | -9.194 |
rodent | -9.102 |
Token | , |
Token ID | 11 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
ancial | +1.903 |
culosis | +1.851 |
Klu | +1.629 |
reck | +1.606 |
pload | +1.603 |
Neg logit contributions | |
asma | -1.571 |
Hermes | -1.315 |
alion | -1.236 |
yrus | -1.182 |
rodent | -1.163 |
Token | then |
Token ID | 788 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
ancial | +0.310 |
culosis | +0.301 |
Klu | +0.262 |
reck | +0.258 |
pload | +0.258 |
Neg logit contributions | |
asma | -0.299 |
Hermes | -0.254 |
alion | -0.240 |
yrus | -0.231 |
rodent | -0.227 |
Token | apply |
Token ID | 4174 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
asma | +0.829 |
Hermes | +0.713 |
alion | +0.670 |
yrus | +0.649 |
rodent | +0.640 |
Neg logit contributions | |
ancial | -0.818 |
culosis | -0.793 |
Klu | -0.683 |
reck | -0.676 |
pload | -0.670 |
Token | the |
Token ID | 262 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
ancial | +2.699 |
culosis | +2.608 |
Klu | +2.302 |
pload | +2.240 |
ilege | +2.239 |
Neg logit contributions | |
asma | -2.641 |
Hermes | -2.220 |
alion | -2.129 |
yrus | -2.036 |
rodent | -1.992 |
Token | utils |
Token ID | 26791 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ancial | +3.059 |
culosis | +2.953 |
pload | +2.550 |
reck | +2.487 |
ilege | +2.475 |
Neg logit contributions | |
asma | -4.154 |
Hermes | -3.747 |
alion | -3.523 |
rodent | -3.448 |
Cao | -3.413 |
Token | import |
Token ID | 1330 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
ancial | +1.650 |
culosis | +1.591 |
Klu | +1.363 |
pload | +1.325 |
ilege | +1.318 |
Neg logit contributions | |
asma | -2.466 |
Hermes | -2.143 |
alion | -2.101 |
yrus | -2.020 |
ods | -1.964 |
Token | c |
Token ID | 269 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
ancial | +4.974 |
culosis | +4.804 |
Klu | +4.200 |
ilege | +4.143 |
pload | +4.118 |
Neg logit contributions | |
asma | -4.814 |
Hermes | -4.065 |
alion | -3.817 |
yrus | -3.749 |
rodent | -3.584 |
Token | v |
Token ID | 85 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
ancial | +3.196 |
culosis | +3.072 |
reck | +2.746 |
Klu | +2.696 |
ement | +2.691 |
Neg logit contributions | |
asma | -3.053 |
Hermes | -2.713 |
alion | -2.508 |
rodent | -2.401 |
Cao | -2.328 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
ancial | +1.936 |
culosis | +1.866 |
Klu | +1.621 |
reck | +1.606 |
ilege | +1.597 |
Neg logit contributions | |
asma | -2.807 |
Hermes | -2.485 |
alion | -2.384 |
yrus | -2.301 |
rodent | -2.298 |
Token | # |
Token ID | 1303 |
Feature activation | +8.85e+00 |
Pos logit contributions | |
ancial | +4.179 |
culosis | +4.039 |
Klu | +3.530 |
ilege | +3.458 |
pload | +3.431 |
Neg logit contributions | |
asma | -4.787 |
Hermes | -4.095 |
alion | -3.930 |
yrus | -3.792 |
ods | -3.694 |
Token | construct |
Token ID | 5678 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
ancial | +4.751 |
culosis | +4.486 |
ilege | +3.606 |
pload | +3.571 |
Klu | +3.529 |
Neg logit contributions | |
asma | -9.557 |
Hermes | -8.284 |
alion | -7.987 |
yrus | -7.803 |
ods | -7.633 |
Token | the |
Token ID | 262 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
ancial | +4.047 |
culosis | +3.764 |
Klu | +3.481 |
ement | +3.424 |
ilege | +3.347 |
Neg logit contributions | |
asma | -5.436 |
Hermes | -4.611 |
alion | -4.559 |
yrus | -4.435 |
rodent | -4.275 |
Token | argument |
Token ID | 4578 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
ancial | +3.828 |
culosis | +3.579 |
Klu | +3.291 |
ement | +3.261 |
reck | +3.181 |
Neg logit contributions | |
asma | -5.055 |
Hermes | -4.332 |
alion | -4.278 |
yrus | -4.073 |
ods | -4.016 |
Token | parse |
Token ID | 21136 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
ancial | +3.038 |
culosis | +2.978 |
Klu | +2.730 |
ilege | +2.694 |
reck | +2.690 |
Neg logit contributions | |
asma | -1.325 |
Hermes | -0.985 |
alion | -0.933 |
yrus | -0.817 |
rodent | -0.782 |
Token | and |
Token ID | 290 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ancial | +3.219 |
culosis | +3.078 |
Klu | +2.695 |
ement | +2.655 |
reck | +2.623 |
Neg logit contributions | |
asma | -4.606 |
Hermes | -3.990 |
alion | -3.868 |
yrus | -3.783 |
rodent | -3.705 |
Token | it |
Token ID | 340 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ancial | +1.322 |
culosis | +1.277 |
Klu | +1.119 |
reck | +1.105 |
pload | +1.096 |
Neg logit contributions | |
asma | -1.274 |
Hermes | -1.075 |
alion | -1.026 |
yrus | -0.983 |
rodent | -0.958 |
Token | notes |
Token ID | 4710 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ancial | +0.285 |
culosis | +0.277 |
Klu | +0.240 |
reck | +0.238 |
pload | +0.237 |
Neg logit contributions | |
asma | -0.274 |
Hermes | -0.234 |
alion | -0.220 |
yrus | -0.212 |
rodent | -0.209 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ancial | +0.814 |
culosis | +0.787 |
Klu | +0.680 |
reck | +0.669 |
pload | +0.666 |
Neg logit contributions | |
asma | -0.906 |
Hermes | -0.781 |
alion | -0.739 |
yrus | -0.714 |
rodent | -0.704 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ancial | +0.141 |
culosis | +0.137 |
Klu | +0.120 |
reck | +0.118 |
pload | +0.118 |
Neg logit contributions | |
asma | -0.128 |
Hermes | -0.108 |
alion | -0.102 |
yrus | -0.098 |
rodent | -0.096 |
Token | World |
Token ID | 10603 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ancial | +0.893 |
culosis | +0.866 |
Klu | +0.739 |
reck | +0.734 |
pload | +0.725 |
Neg logit contributions | |
asma | -1.069 |
Hermes | -0.928 |
alion | -0.881 |
yrus | -0.849 |
rodent | -0.841 |
Token | 's |
Token ID | 338 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
ancial | +1.194 |
culosis | +1.159 |
Klu | +1.008 |
reck | +0.993 |
pload | +0.988 |
Neg logit contributions | |
asma | -1.175 |
Hermes | -0.999 |
alion | -0.948 |
yrus | -0.913 |
rodent | -0.896 |
Token | most |
Token ID | 749 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ancial | +6.376 |
culosis | +6.367 |
Klu | +5.563 |
reck | +5.430 |
ilege | +5.320 |
Neg logit contributions | |
asma | -7.486 |
alion | -6.269 |
Hermes | -6.216 |
yrus | -5.967 |
rodent | -5.605 |
Token | complete |
Token ID | 1844 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
ancial | +1.111 |
culosis | +1.082 |
Klu | +0.945 |
reck | +0.929 |
pload | +0.922 |
Neg logit contributions | |
asma | -1.098 |
Hermes | -0.930 |
alion | -0.885 |
yrus | -0.849 |
rodent | -0.830 |
Token | mammoth |
Token ID | 44268 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
ancial | +3.611 |
culosis | +3.529 |
Klu | +3.148 |
reck | +3.049 |
pload | +3.030 |
Neg logit contributions | |
asma | -3.191 |
Hermes | -2.627 |
alion | -2.587 |
yrus | -2.431 |
ods | -2.330 |
Token | was |
Token ID | 373 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
asma | +0.021 |
Hermes | +0.018 |
alion | +0.017 |
yrus | +0.016 |
rodent | +0.016 |
Neg logit contributions | |
ancial | -0.026 |
culosis | -0.025 |
Klu | -0.022 |
reck | -0.022 |
pload | -0.022 |
Token | found |
Token ID | 1043 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ancial | +0.316 |
culosis | +0.308 |
Klu | +0.273 |
reck | +0.269 |
pload | +0.269 |
Neg logit contributions | |
asma | -0.237 |
Hermes | -0.196 |
alion | -0.184 |
yrus | -0.175 |
rodent | -0.172 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
ancial | +1.743 |
culosis | +1.689 |
Klu | +1.475 |
reck | +1.442 |
pload | +1.438 |
Neg logit contributions | |
asma | -1.943 |
Hermes | -1.647 |
alion | -1.582 |
yrus | -1.530 |
rodent | -1.497 |
Token | 76 |
Token ID | 4304 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
ancial | +3.238 |
culosis | +3.098 |
Klu | +2.707 |
reck | +2.658 |
pload | +2.625 |
Neg logit contributions | |
asma | -3.900 |
Hermes | -3.372 |
alion | -3.216 |
yrus | -3.130 |
rodent | -3.084 |
Token | 14 |
Token ID | 1478 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
ancial | +2.084 |
culosis | +2.005 |
Klu | +1.754 |
pload | +1.714 |
reck | +1.710 |
Neg logit contributions | |
asma | -2.329 |
Hermes | -1.981 |
alion | -1.895 |
yrus | -1.839 |
rodent | -1.811 |
Token | 05 |
Token ID | 2713 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
ancial | +3.050 |
culosis | +2.925 |
Klu | +2.600 |
reck | +2.516 |
ement | +2.487 |
Neg logit contributions | |
asma | -3.940 |
Hermes | -3.364 |
alion | -3.262 |
yrus | -3.184 |
rodent | -3.122 |
Token | ; |
Token ID | 26 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
ancial | +4.265 |
culosis | +4.084 |
Klu | +3.574 |
pload | +3.540 |
reck | +3.517 |
Neg logit contributions | |
asma | -4.267 |
Hermes | -3.600 |
alion | -3.446 |
yrus | -3.366 |
rodent | -3.254 |
Token | trek |
Token ID | 30784 |
Feature activation | +8.67e+00 |
Pos logit contributions | |
ancial | +3.779 |
culosis | +3.710 |
Klu | +3.189 |
reck | +3.182 |
pload | +3.162 |
Neg logit contributions | |
asma | -4.198 |
Hermes | -3.537 |
alion | -3.417 |
yrus | -3.250 |
Cao | -3.218 |
Token | amer |
Token ID | 2382 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
ancial | +5.454 |
culosis | +5.189 |
reck | +4.356 |
orkshire | +4.273 |
ilege | +4.271 |
Neg logit contributions | |
asma | -8.345 |
Hermes | -7.610 |
alion | -7.039 |
Cao | -7.028 |
rodent | -6.994 |
Token | ica |
Token ID | 3970 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
ancial | +3.361 |
culosis | +3.252 |
reck | +2.812 |
ilege | +2.772 |
pload | +2.769 |
Neg logit contributions | |
asma | -3.284 |
Hermes | -2.885 |
alion | -2.664 |
rodent | -2.591 |
yrus | -2.564 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ancial | +4.016 |
culosis | +3.839 |
reck | +3.284 |
pload | +3.266 |
orkshire | +3.239 |
Neg logit contributions | |
asma | -4.988 |
Hermes | -4.369 |
alion | -4.145 |
rodent | -4.022 |
yrus | -3.967 |
Token | co |
Token ID | 1073 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ancial | +1.337 |
culosis | +1.297 |
Klu | +1.122 |
reck | +1.116 |
pload | +1.112 |
Neg logit contributions | |
asma | -1.297 |
Hermes | -1.105 |
alion | -1.044 |
rodent | -1.000 |
yrus | -0.999 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
asma | +1.154 |
Hermes | +0.997 |
alion | +0.947 |
yrus | +0.912 |
rodent | +0.904 |
Neg logit contributions | |
ancial | -1.012 |
culosis | -0.978 |
Klu | -0.838 |
reck | -0.828 |
pload | -0.826 |
Token | advice |
Token ID | 5608 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ancial | +2.358 |
culosis | +2.282 |
Klu | +2.007 |
reck | +1.977 |
pload | +1.975 |
Neg logit contributions | |
asma | -2.186 |
Hermes | -1.836 |
alion | -1.735 |
yrus | -1.670 |
rodent | -1.632 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
asma | +0.010 |
Hermes | +0.009 |
alion | +0.008 |
yrus | +0.008 |
rodent | +0.008 |
Neg logit contributions | |
ancial | -0.011 |
culosis | -0.010 |
Klu | -0.009 |
reck | -0.009 |
pload | -0.009 |
Token | F |
Token ID | 376 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
asma | +1.001 |
Hermes | +0.848 |
alion | +0.792 |
yrus | +0.761 |
rodent | +0.748 |
Neg logit contributions | |
ancial | -1.155 |
culosis | -1.126 |
Klu | -0.977 |
reck | -0.971 |
pload | -0.968 |
Token | ACT |
Token ID | 10659 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
asma | +1.182 |
Hermes | +1.012 |
alion | +0.969 |
yrus | +0.937 |
rodent | +0.917 |
Neg logit contributions | |
ancial | -1.037 |
culosis | -1.005 |
Klu | -0.874 |
pload | -0.848 |
orkshire | -0.840 |
Token | and |
Token ID | 290 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
asma | +1.753 |
Hermes | +1.487 |
alion | +1.404 |
yrus | +1.339 |
rodent | +1.326 |
Neg logit contributions | |
ancial | -1.937 |
culosis | -1.884 |
Klu | -1.639 |
pload | -1.621 |
reck | -1.614 |
Token | La |
Token ID | 4689 |
Feature activation | +8.66e+00 |
Pos logit contributions | |
ancial | +1.526 |
culosis | +1.480 |
Klu | +1.304 |
reck | +1.269 |
pload | +1.268 |
Neg logit contributions | |
asma | -1.501 |
Hermes | -1.262 |
alion | -1.204 |
yrus | -1.159 |
rodent | -1.142 |
Token | Be |
Token ID | 3856 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ancial | +6.712 |
culosis | +6.464 |
Klu | +5.717 |
ilege | +5.689 |
reck | +5.666 |
Neg logit contributions | |
asma | -7.135 |
Hermes | -6.067 |
alion | -5.731 |
yrus | -5.621 |
rodent | -5.472 |
Token | ouf |
Token ID | 37116 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ancial | +1.593 |
culosis | +1.507 |
reck | +1.244 |
Klu | +1.241 |
ilege | +1.226 |
Neg logit contributions | |
asma | -2.780 |
Hermes | -2.479 |
alion | -2.356 |
yrus | -2.288 |
rodent | -2.283 |
Token | , |
Token ID | 11 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
ancial | +1.597 |
culosis | +1.549 |
Klu | +1.355 |
reck | +1.332 |
pload | +1.327 |
Neg logit contributions | |
asma | -1.559 |
Hermes | -1.325 |
alion | -1.256 |
yrus | -1.203 |
rodent | -1.187 |
Token | R |
Token ID | 371 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ancial | +0.651 |
culosis | +0.631 |
Klu | +0.550 |
reck | +0.541 |
pload | +0.540 |
Neg logit contributions | |
asma | -0.635 |
Hermes | -0.540 |
alion | -0.511 |
yrus | -0.491 |
rodent | -0.484 |
Token | ön |
Token ID | 48863 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
asma | +0.460 |
Hermes | +0.394 |
alion | +0.373 |
yrus | +0.359 |
rodent | +0.354 |
Neg logit contributions | |
ancial | -0.445 |
culosis | -0.431 |
Klu | -0.373 |
reck | -0.368 |
pload | -0.367 |
Token |
|
Token ID | 198 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ancial | +0.327 |
culosis | +0.318 |
Klu | +0.282 |
reck | +0.277 |
pload | +0.275 |
Neg logit contributions | |
asma | -0.264 |
Hermes | -0.219 |
alion | -0.207 |
yrus | -0.200 |
rodent | -0.196 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ancial | +1.382 |
culosis | +1.342 |
Klu | +1.221 |
reck | +1.204 |
ement | +1.188 |
Neg logit contributions | |
asma | -1.172 |
Hermes | -0.978 |
alion | -0.928 |
yrus | -0.902 |
rodent | -0.881 |
Token | Get |
Token ID | 3855 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ancial | +1.056 |
culosis | +1.022 |
reck | +0.880 |
Klu | +0.878 |
ilege | +0.862 |
Neg logit contributions | |
asma | -1.222 |
Hermes | -1.060 |
alion | -0.999 |
yrus | -0.970 |
rodent | -0.960 |
Token | The |
Token ID | 383 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
asma | +2.160 |
Hermes | +1.843 |
alion | +1.705 |
rodent | +1.641 |
yrus | +1.623 |
Neg logit contributions | |
ancial | -2.673 |
culosis | -2.637 |
pload | -2.334 |
Klu | -2.317 |
orkshire | -2.271 |
Token | Times |
Token ID | 3782 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
asma | +0.920 |
Hermes | +0.782 |
alion | +0.720 |
yrus | +0.672 |
rodent | +0.669 |
Neg logit contributions | |
ancial | -1.223 |
culosis | -1.179 |
pload | -1.049 |
reck | -1.046 |
Klu | -1.039 |
Token | of |
Token ID | 286 |
Feature activation | +8.62e+00 |
Pos logit contributions | |
asma | +0.667 |
Hermes | +0.575 |
alion | +0.542 |
rodent | +0.514 |
yrus | +0.513 |
Neg logit contributions | |
ancial | -0.685 |
culosis | -0.668 |
Klu | -0.577 |
pload | -0.569 |
orkshire | -0.564 |
Token | Israel |
Token ID | 2692 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ancial | +5.318 |
culosis | +5.069 |
reck | +4.267 |
ilege | +4.225 |
ement | +4.173 |
Neg logit contributions | |
asma | -8.627 |
Hermes | -7.246 |
alion | -7.142 |
rodent | -7.030 |
yrus | -7.002 |
Token | 's |
Token ID | 338 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
asma | +1.635 |
Hermes | +1.421 |
alion | +1.336 |
yrus | +1.285 |
rodent | +1.274 |
Neg logit contributions | |
ancial | -1.485 |
culosis | -1.454 |
Klu | -1.241 |
pload | -1.237 |
reck | -1.224 |
Token | Daily |
Token ID | 6714 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
ancial | +3.547 |
culosis | +3.366 |
Klu | +2.735 |
reck | +2.692 |
ilege | +2.650 |
Neg logit contributions | |
asma | -6.356 |
Hermes | -5.488 |
alion | -5.348 |
yrus | -5.231 |
rodent | -5.128 |
Token | Edition |
Token ID | 5061 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
asma | +0.517 |
Hermes | +0.440 |
alion | +0.416 |
yrus | +0.403 |
rodent | +0.397 |
Neg logit contributions | |
ancial | -0.509 |
culosis | -0.494 |
Klu | -0.428 |
reck | -0.422 |
pload | -0.420 |
Token | by |
Token ID | 416 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ancial | +1.138 |
culosis | +1.114 |
Klu | +0.962 |
reck | +0.952 |
ilege | +0.946 |
Neg logit contributions | |
asma | -1.080 |
Hermes | -0.913 |
alion | -0.861 |
yrus | -0.832 |
rodent | -0.816 |
Token | , |
Token ID | 11 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ancial | +2.593 |
culosis | +2.497 |
Klu | +2.169 |
reck | +2.152 |
pload | +2.148 |
Neg logit contributions | |
asma | -2.813 |
Hermes | -2.378 |
alion | -2.292 |
yrus | -2.218 |
rodent | -2.150 |
Token | returning |
Token ID | 8024 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ancial | +1.421 |
culosis | +1.375 |
Klu | +1.196 |
reck | +1.178 |
pload | +1.176 |
Neg logit contributions | |
asma | -1.450 |
Hermes | -1.228 |
alion | -1.173 |
yrus | -1.129 |
rodent | -1.106 |
Token | on |
Token ID | 319 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
ancial | +1.170 |
culosis | +1.131 |
Klu | +0.979 |
reck | +0.967 |
pload | +0.964 |
Neg logit contributions | |
asma | -1.239 |
Hermes | -1.050 |
alion | -1.006 |
yrus | -0.968 |
rodent | -0.946 |
Token | New |
Token ID | 968 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
asma | +0.456 |
Hermes | +0.390 |
alion | +0.368 |
yrus | +0.354 |
rodent | +0.350 |
Neg logit contributions | |
ancial | -0.456 |
culosis | -0.443 |
Klu | -0.384 |
reck | -0.378 |
pload | -0.377 |
Token | Year |
Token ID | 6280 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
ancial | +2.790 |
culosis | +2.705 |
Klu | +2.393 |
ement | +2.353 |
reck | +2.346 |
Neg logit contributions | |
asma | -2.435 |
Hermes | -2.012 |
alion | -1.937 |
yrus | -1.839 |
rodent | -1.779 |
Token | 's |
Token ID | 338 |
Feature activation | +8.62e+00 |
Pos logit contributions | |
ancial | +3.235 |
culosis | +3.122 |
Klu | +2.630 |
pload | +2.609 |
reck | +2.592 |
Neg logit contributions | |
asma | -4.595 |
Hermes | -3.953 |
alion | -3.811 |
yrus | -3.749 |
rodent | -3.603 |
Token | Day |
Token ID | 3596 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ancial | +6.265 |
culosis | +6.206 |
Klu | +5.372 |
pload | +5.295 |
ement | +5.279 |
Neg logit contributions | |
asma | -7.519 |
Hermes | -6.190 |
alion | -6.080 |
yrus | -6.012 |
opus | -5.631 |
Token | . |
Token ID | 13 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
ancial | +1.789 |
culosis | +1.731 |
Klu | +1.501 |
reck | +1.484 |
pload | +1.480 |
Neg logit contributions | |
asma | -1.889 |
Hermes | -1.603 |
alion | -1.535 |
yrus | -1.481 |
rodent | -1.443 |
Token |
|
Token ID | 198 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
ancial | +0.713 |
culosis | +0.693 |
Klu | +0.609 |
reck | +0.600 |
pload | +0.599 |
Neg logit contributions | |
asma | -0.609 |
Hermes | -0.512 |
alion | -0.481 |
yrus | -0.461 |
rodent | -0.454 |
Token |
|
Token ID | 198 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
ancial | +0.396 |
culosis | +0.385 |
Klu | +0.346 |
reck | +0.343 |
ilege | +0.338 |
Neg logit contributions | |
asma | -0.310 |
Hermes | -0.257 |
alion | -0.244 |
yrus | -0.235 |
rodent | -0.229 |
Token | C |
Token ID | 34 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ancial | +0.597 |
culosis | +0.576 |
Klu | +0.488 |
reck | +0.480 |
pload | +0.478 |
Neg logit contributions | |
asma | -0.773 |
Hermes | -0.672 |
alion | -0.641 |
yrus | -0.620 |
rodent | -0.613 |
Token | Color |
Token ID | 10258 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
ancial | +1.321 |
culosis | +1.287 |
Klu | +1.133 |
reck | +1.119 |
ilege | +1.113 |
Neg logit contributions | |
asma | -1.087 |
Hermes | -0.912 |
alion | -0.856 |
yrus | -0.818 |
rodent | -0.806 |
Token | ] |
Token ID | 60 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ancial | +0.411 |
culosis | +0.397 |
Klu | +0.340 |
reck | +0.335 |
pload | +0.334 |
Neg logit contributions | |
asma | -0.477 |
Hermes | -0.412 |
alion | -0.392 |
yrus | -0.378 |
rodent | -0.373 |
Token | :: |
Token ID | 3712 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
ancial | +2.032 |
culosis | +1.970 |
Klu | +1.720 |
reck | +1.689 |
ilege | +1.689 |
Neg logit contributions | |
asma | -1.944 |
Hermes | -1.647 |
alion | -1.563 |
yrus | -1.505 |
rodent | -1.473 |
Token | From |
Token ID | 4863 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
ancial | +0.338 |
culosis | +0.326 |
Klu | +0.276 |
reck | +0.271 |
pload | +0.270 |
Neg logit contributions | |
asma | -0.454 |
Hermes | -0.397 |
alion | -0.378 |
yrus | -0.366 |
rodent | -0.362 |
Token | Ar |
Token ID | 3163 |
Feature activation | +6.82e+00 |
Pos logit contributions | |
ancial | +3.220 |
culosis | +3.108 |
Klu | +2.642 |
Strike | +2.589 |
ilege | +2.589 |
Neg logit contributions | |
asma | -4.285 |
Hermes | -3.758 |
alion | -3.586 |
yrus | -3.482 |
rodent | -3.431 |
Token | gb |
Token ID | 22296 |
Feature activation | +8.53e+00 |
Pos logit contributions | |
ancial | +3.482 |
culosis | +3.285 |
reck | +2.619 |
Klu | +2.577 |
ement | +2.563 |
Neg logit contributions | |
asma | -7.580 |
Hermes | -6.884 |
alion | -6.583 |
rodent | -6.443 |
yrus | -6.371 |
Token | ($ |
Token ID | 16763 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ancial | +6.057 |
culosis | +5.847 |
Klu | +4.986 |
ilege | +4.967 |
Strike | +4.959 |
Neg logit contributions | |
asma | -7.530 |
Hermes | -6.540 |
alion | -6.195 |
yrus | -6.065 |
rodent | -5.985 |
Token | BG |
Token ID | 40469 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
ancial | +0.974 |
culosis | +0.946 |
Klu | +0.804 |
reck | +0.792 |
ilege | +0.788 |
Neg logit contributions | |
asma | -1.208 |
Hermes | -1.058 |
alion | -1.003 |
yrus | -0.967 |
rodent | -0.958 |
Token | [ |
Token ID | 58 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ancial | +3.114 |
culosis | +3.021 |
Klu | +2.586 |
reck | +2.539 |
ilege | +2.519 |
Neg logit contributions | |
asma | -3.846 |
Hermes | -3.335 |
alion | -3.181 |
rodent | -3.071 |
yrus | -3.060 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ancial | +2.017 |
culosis | +1.970 |
Klu | +1.667 |
ilege | +1.644 |
reck | +1.643 |
Neg logit contributions | |
asma | -2.539 |
Hermes | -2.217 |
alion | -2.119 |
yrus | -2.035 |
rodent | -2.015 |
Token | ], |
Token ID | 4357 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ancial | +0.882 |
culosis | +0.855 |
Klu | +0.730 |
reck | +0.718 |
pload | +0.717 |
Neg logit contributions | |
asma | -1.066 |
Hermes | -0.921 |
alion | -0.877 |
yrus | -0.849 |
rodent | -0.839 |
Token | 7 |
Token ID | 22 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
asma | +0.934 |
Hermes | +0.808 |
alion | +0.770 |
yrus | +0.743 |
rodent | +0.734 |
Neg logit contributions | |
ancial | -0.770 |
culosis | -0.745 |
Klu | -0.636 |
pload | -0.623 |
reck | -0.623 |
Token | . |
Token ID | 13 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ancial | +0.289 |
culosis | +0.279 |
Klu | +0.242 |
reck | +0.238 |
pload | +0.236 |
Neg logit contributions | |
asma | -0.349 |
Hermes | -0.301 |
alion | -0.288 |
yrus | -0.279 |
rodent | -0.276 |
Token | While |
Token ID | 2893 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
ancial | +1.876 |
culosis | +1.806 |
Klu | +1.584 |
pload | +1.538 |
reck | +1.536 |
Neg logit contributions | |
asma | -2.140 |
Hermes | -1.818 |
alion | -1.746 |
yrus | -1.699 |
rodent | -1.662 |
Token | we |
Token ID | 356 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
ancial | +4.866 |
culosis | +4.675 |
Klu | +4.211 |
pload | +4.018 |
ilege | +3.997 |
Neg logit contributions | |
asma | -5.539 |
Hermes | -4.674 |
alion | -4.507 |
yrus | -4.341 |
ods | -4.221 |
Token | are |
Token ID | 389 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
ancial | +3.997 |
culosis | +3.756 |
reck | +3.212 |
Klu | +3.208 |
pload | +3.173 |
Neg logit contributions | |
asma | -5.115 |
Hermes | -4.498 |
alion | -4.223 |
yrus | -4.132 |
rodent | -4.023 |
Token | waiting |
Token ID | 4953 |
Feature activation | +8.53e+00 |
Pos logit contributions | |
ancial | +4.763 |
culosis | +4.550 |
Klu | +4.080 |
reck | +3.962 |
pload | +3.901 |
Neg logit contributions | |
asma | -5.512 |
Hermes | -4.733 |
alion | -4.503 |
yrus | -4.363 |
ods | -4.210 |
Token | for |
Token ID | 329 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
ancial | +5.866 |
culosis | +5.496 |
Klu | +4.838 |
pload | +4.686 |
ement | +4.686 |
Neg logit contributions | |
asma | -7.748 |
Hermes | -6.672 |
alion | -6.435 |
yrus | -6.208 |
rodent | -6.000 |
Token | the |
Token ID | 262 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
ancial | +3.792 |
culosis | +3.615 |
Klu | +3.258 |
ement | +3.103 |
pload | +3.086 |
Neg logit contributions | |
asma | -3.896 |
Hermes | -3.253 |
alion | -3.152 |
yrus | -3.061 |
ods | -2.906 |
Token | curry |
Token ID | 34611 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ancial | +3.737 |
culosis | +3.593 |
Klu | +3.273 |
reck | +3.153 |
pload | +3.150 |
Neg logit contributions | |
asma | -2.760 |
Hermes | -2.236 |
alion | -2.178 |
yrus | -2.057 |
ods | -1.940 |
Token | mix |
Token ID | 5022 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ancial | +0.105 |
culosis | +0.101 |
Klu | +0.085 |
reck | +0.084 |
pload | +0.083 |
Neg logit contributions | |
asma | -0.139 |
Hermes | -0.122 |
alion | -0.116 |
yrus | -0.112 |
rodent | -0.111 |
Token | to |
Token ID | 284 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
ancial | +2.124 |
culosis | +2.054 |
Klu | +1.786 |
reck | +1.748 |
pload | +1.744 |
Neg logit contributions | |
asma | -2.211 |
Hermes | -1.893 |
alion | -1.793 |
yrus | -1.724 |
rodent | -1.702 |
Token | 224 |
Token ID | 26063 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
ancial | +2.222 |
culosis | +2.163 |
Klu | +1.885 |
pload | +1.849 |
reck | +1.847 |
Neg logit contributions | |
asma | -2.514 |
Hermes | -2.153 |
alion | -2.079 |
yrus | -1.996 |
rodent | -1.951 |
Token | km |
Token ID | 13276 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
asma | +0.317 |
Hermes | +0.272 |
alion | +0.259 |
yrus | +0.250 |
rodent | +0.246 |
Neg logit contributions | |
ancial | -0.293 |
culosis | -0.283 |
Klu | -0.245 |
reck | -0.241 |
pload | -0.240 |
Token | above |
Token ID | 2029 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
asma | +0.594 |
Hermes | +0.507 |
alion | +0.479 |
yrus | +0.461 |
rodent | +0.455 |
Neg logit contributions | |
ancial | -0.592 |
culosis | -0.574 |
Klu | -0.498 |
reck | -0.490 |
pload | -0.489 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ancial | +1.148 |
culosis | +1.116 |
Klu | +0.976 |
reck | +0.962 |
pload | +0.960 |
Neg logit contributions | |
asma | -1.019 |
Hermes | -0.861 |
alion | -0.810 |
yrus | -0.776 |
rodent | -0.766 |
Token | Earth |
Token ID | 3668 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
ancial | +1.374 |
culosis | +1.330 |
Klu | +1.155 |
reck | +1.132 |
pload | +1.129 |
Neg logit contributions | |
asma | -1.467 |
Hermes | -1.255 |
alion | -1.195 |
yrus | -1.152 |
rodent | -1.131 |
Token | 's |
Token ID | 338 |
Feature activation | +8.50e+00 |
Pos logit contributions | |
ancial | +2.385 |
culosis | +2.307 |
Klu | +2.015 |
reck | +1.994 |
pload | +1.965 |
Neg logit contributions | |
asma | -2.240 |
Hermes | -1.909 |
alion | -1.829 |
yrus | -1.751 |
rodent | -1.708 |
Token | surface |
Token ID | 4417 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ancial | +4.995 |
culosis | +4.748 |
Klu | +4.207 |
reck | +4.026 |
ement | +3.875 |
Neg logit contributions | |
asma | -8.338 |
alion | -7.396 |
Hermes | -7.300 |
yrus | -7.072 |
opus | -6.693 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ancial | +1.556 |
culosis | +1.518 |
Klu | +1.344 |
reck | +1.328 |
ilege | +1.311 |
Neg logit contributions | |
asma | -1.180 |
Hermes | -0.976 |
alion | -0.927 |
yrus | -0.874 |
rodent | -0.858 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ancial | +0.296 |
culosis | +0.288 |
Klu | +0.260 |
reck | +0.256 |
pload | +0.251 |
Neg logit contributions | |
asma | -0.230 |
Hermes | -0.190 |
alion | -0.181 |
yrus | -0.175 |
rodent | -0.169 |
Token | The |
Token ID | 464 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ancial | +0.249 |
culosis | +0.241 |
Klu | +0.207 |
reck | +0.204 |
pload | +0.203 |
Neg logit contributions | |
asma | -0.282 |
Hermes | -0.243 |
alion | -0.231 |
yrus | -0.222 |
rodent | -0.220 |
Token | European |
Token ID | 3427 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
asma | +0.167 |
Hermes | +0.143 |
alion | +0.136 |
yrus | +0.130 |
rodent | +0.129 |
Neg logit contributions | |
ancial | -0.161 |
culosis | -0.156 |
Klu | -0.135 |
reck | -0.133 |
pload | -0.133 |
Token | Qu |
Token ID | 4507 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ancial | +1.736 |
culosis | +1.625 |
Klu | +1.350 |
reck | +1.309 |
Strike | +1.273 |
Neg logit contributions | |
asma | -4.055 |
Hermes | -3.625 |
alion | -3.474 |
yrus | -3.408 |
rodent | -3.373 |
Token | ill |
Token ID | 359 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ancial | +0.831 |
culosis | +0.766 |
reck | +0.583 |
ilege | +0.578 |
Klu | +0.575 |
Neg logit contributions | |
asma | -2.297 |
Hermes | -2.084 |
alion | -1.983 |
rodent | -1.954 |
yrus | -1.947 |
Token | an |
Token ID | 272 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
asma | +1.277 |
Hermes | +0.999 |
alion | +0.913 |
yrus | +0.854 |
rodent | +0.834 |
Neg logit contributions | |
ancial | -2.500 |
culosis | -2.443 |
Klu | -2.201 |
reck | -2.176 |
pload | -2.173 |
Token | told |
Token ID | 1297 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ancial | +0.127 |
culosis | +0.123 |
Klu | +0.106 |
reck | +0.105 |
pload | +0.104 |
Neg logit contributions | |
asma | -0.135 |
Hermes | -0.116 |
alion | -0.110 |
yrus | -0.106 |
rodent | -0.104 |
Token | Polit |
Token ID | 7793 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ancial | +2.148 |
culosis | +2.096 |
Klu | +1.865 |
reck | +1.814 |
pload | +1.813 |
Neg logit contributions | |
asma | -1.773 |
Hermes | -1.463 |
alion | -1.408 |
yrus | -1.337 |
rodent | -1.304 |
Token | i |
Token ID | 72 |
Feature activation | +8.48e+00 |
Pos logit contributions | |
ancial | +3.586 |
culosis | +3.492 |
reck | +3.119 |
pload | +3.108 |
ilege | +3.096 |
Neg logit contributions | |
asma | -2.090 |
Hermes | -1.720 |
alion | -1.570 |
yrus | -1.480 |
rodent | -1.471 |
Token | Fact |
Token ID | 29054 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ancial | +0.921 |
culosis | +0.647 |
Fact | +0.183 |
reck | +0.043 |
Klu | +0.004 |
Neg logit contributions | |
asma | -12.616 |
Hermes | -11.494 |
alion | -11.475 |
yrus | -11.078 |
rodent | -11.015 |
Token | in |
Token ID | 287 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
asma | +1.218 |
Hermes | +1.035 |
alion | +0.974 |
yrus | +0.939 |
rodent | +0.924 |
Neg logit contributions | |
ancial | -1.264 |
culosis | -1.227 |
Klu | -1.067 |
reck | -1.052 |
pload | -1.049 |
Token | March |
Token ID | 2805 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ancial | +0.182 |
culosis | +0.176 |
Klu | +0.154 |
reck | +0.150 |
pload | +0.150 |
Neg logit contributions | |
asma | -0.185 |
Hermes | -0.157 |
alion | -0.150 |
yrus | -0.144 |
rodent | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
ancial | +0.117 |
culosis | +0.113 |
Klu | +0.098 |
reck | +0.096 |
pload | +0.096 |
Neg logit contributions | |
asma | -0.131 |
Hermes | -0.113 |
alion | -0.107 |
yrus | -0.103 |
rodent | -0.102 |
Token | " |
Token ID | 366 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
ancial | +0.749 |
culosis | +0.732 |
Klu | +0.653 |
reck | +0.639 |
pload | +0.639 |
Neg logit contributions | |
asma | -0.528 |
Hermes | -0.430 |
alion | -0.404 |
yrus | -0.388 |
rodent | -0.381 |
Token | other |
Token ID | 584 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
ancial | +2.742 |
culosis | +2.602 |
Klu | +2.297 |
ement | +2.207 |
pload | +2.185 |
Neg logit contributions | |
asma | -4.214 |
Hermes | -3.634 |
alion | -3.611 |
yrus | -3.431 |
ods | -3.290 |
Token | ingredients |
Token ID | 9391 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ancial | +2.015 |
culosis | +1.878 |
Klu | +1.514 |
reck | +1.492 |
pload | +1.469 |
Neg logit contributions | |
asma | -4.778 |
Hermes | -4.172 |
alion | -4.144 |
yrus | -3.956 |
rodent | -3.867 |
Token | and |
Token ID | 290 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
ancial | +1.529 |
culosis | +1.471 |
Klu | +1.282 |
reck | +1.260 |
ilege | +1.242 |
Neg logit contributions | |
asma | -1.877 |
Hermes | -1.622 |
alion | -1.556 |
yrus | -1.506 |
rodent | -1.476 |
Token | mix |
Token ID | 5022 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
ancial | +2.405 |
culosis | +2.256 |
Klu | +1.945 |
pload | +1.858 |
ilege | +1.837 |
Neg logit contributions | |
asma | -5.056 |
Hermes | -4.546 |
alion | -4.322 |
yrus | -4.198 |
ods | -4.089 |
Token | well |
Token ID | 880 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
ancial | +3.997 |
culosis | +3.564 |
ement | +3.347 |
Klu | +3.256 |
reck | +3.107 |
Neg logit contributions | |
asma | -9.008 |
Hermes | -7.851 |
alion | -7.557 |
yrus | -7.482 |
Cao | -7.201 |
Token | until |
Token ID | 1566 |
Feature activation | +8.47e+00 |
Pos logit contributions | |
ancial | +3.159 |
culosis | +2.863 |
ement | +2.438 |
Klu | +2.346 |
reck | +2.285 |
Neg logit contributions | |
asma | -7.968 |
Hermes | -7.082 |
alion | -6.897 |
Cao | -6.596 |
yrus | -6.540 |
Token | the |
Token ID | 262 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
ancial | +5.113 |
culosis | +4.784 |
Klu | +4.602 |
ement | +4.290 |
ilege | +4.253 |
Neg logit contributions | |
asma | -8.001 |
Hermes | -7.050 |
alion | -6.940 |
yrus | -6.519 |
Cao | -6.299 |
Token | mixture |
Token ID | 11710 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
ancial | +3.048 |
culosis | +2.815 |
Klu | +2.439 |
pload | +2.276 |
reck | +2.245 |
Neg logit contributions | |
asma | -6.661 |
Hermes | -5.983 |
alion | -5.771 |
yrus | -5.606 |
ods | -5.539 |
Token | feels |
Token ID | 5300 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
ancial | +4.724 |
culosis | +4.594 |
Klu | +4.177 |
pload | +4.038 |
reck | +4.019 |
Neg logit contributions | |
asma | -6.356 |
Hermes | -5.738 |
alion | -5.322 |
Cao | -4.968 |
yrus | -4.963 |
Token | like |
Token ID | 588 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ancial | +3.771 |
culosis | +3.653 |
Klu | +3.436 |
reck | +3.370 |
ilege | +3.341 |
Neg logit contributions | |
asma | -4.367 |
Hermes | -3.774 |
alion | -3.676 |
yrus | -3.448 |
Cao | -3.290 |
Token | it |
Token ID | 340 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
ancial | +2.223 |
culosis | +2.139 |
Klu | +1.972 |
reck | +1.934 |
pload | +1.923 |
Neg logit contributions | |
asma | -1.998 |
Hermes | -1.691 |
alion | -1.606 |
yrus | -1.539 |
rodent | -1.484 |
Token | would |
Token ID | 561 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ancial | +0.975 |
culosis | +0.948 |
Klu | +0.831 |
reck | +0.818 |
pload | +0.817 |
Neg logit contributions | |
asma | -0.855 |
Hermes | -0.721 |
alion | -0.679 |
yrus | -0.651 |
rodent | -0.641 |
Token | have |
Token ID | 423 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ancial | +2.385 |
culosis | +2.314 |
reck | +2.015 |
Klu | +2.015 |
pload | +1.994 |
Neg logit contributions | |
asma | -2.192 |
Hermes | -1.857 |
alion | -1.753 |
yrus | -1.670 |
rodent | -1.644 |
Token | to |
Token ID | 284 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ancial | +1.990 |
culosis | +1.917 |
Klu | +1.655 |
reck | +1.641 |
pload | +1.627 |
Neg logit contributions | |
asma | -2.161 |
Hermes | -1.861 |
alion | -1.777 |
yrus | -1.713 |
rodent | -1.684 |
Token | buy |
Token ID | 2822 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
ancial | +1.297 |
culosis | +1.250 |
Klu | +1.075 |
reck | +1.060 |
pload | +1.058 |
Neg logit contributions | |
asma | -1.505 |
Hermes | -1.289 |
alion | -1.233 |
yrus | -1.183 |
rodent | -1.165 |
Token | an |
Token ID | 281 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
ancial | +0.589 |
culosis | +0.571 |
Klu | +0.500 |
reck | +0.492 |
pload | +0.492 |
Neg logit contributions | |
asma | -0.551 |
Hermes | -0.464 |
alion | -0.441 |
yrus | -0.423 |
rodent | -0.416 |
Token | entirely |
Token ID | 5000 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
ancial | +0.681 |
culosis | +0.659 |
Klu | +0.581 |
pload | +0.571 |
reck | +0.571 |
Neg logit contributions | |
asma | -0.597 |
Hermes | -0.497 |
alion | -0.472 |
yrus | -0.452 |
rodent | -0.443 |
Token | new |
Token ID | 649 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ancial | +6.016 |
culosis | +5.731 |
pload | +5.034 |
reck | +5.027 |
Klu | +5.025 |
Neg logit contributions | |
asma | -7.032 |
Hermes | -5.828 |
alion | -5.781 |
yrus | -5.463 |
ods | -5.192 |
Token | shif |
Token ID | 7143 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ancial | +2.354 |
culosis | +2.263 |
Klu | +1.967 |
reck | +1.936 |
pload | +1.929 |
Neg logit contributions | |
asma | -2.734 |
Hermes | -2.332 |
alion | -2.248 |
yrus | -2.157 |
rodent | -2.099 |
Token | ter |
Token ID | 353 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
ancial | +0.994 |
culosis | +0.955 |
Klu | +0.806 |
reck | +0.795 |
pload | +0.794 |
Neg logit contributions | |
asma | -1.375 |
Hermes | -1.201 |
alion | -1.144 |
yrus | -1.108 |
rodent | -1.095 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ancial | +1.797 |
culosis | +1.726 |
Klu | +1.507 |
reck | +1.485 |
pload | +1.481 |
Neg logit contributions | |
asma | -1.865 |
Hermes | -1.593 |
alion | -1.507 |
yrus | -1.451 |
rodent | -1.425 |
Token | I |
Token ID | 314 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ancial | +1.231 |
culosis | +1.195 |
Klu | +1.049 |
reck | +1.031 |
pload | +1.029 |
Neg logit contributions | |
asma | -1.115 |
Hermes | -0.938 |
alion | -0.888 |
yrus | -0.854 |
rodent | -0.840 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
asma | +0.852 |
Hermes | +0.728 |
alion | +0.690 |
yrus | +0.663 |
rodent | +0.655 |
Neg logit contributions | |
ancial | -0.842 |
culosis | -0.819 |
Klu | -0.706 |
pload | -0.696 |
reck | -0.694 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
asma | +1.568 |
Hermes | +1.322 |
alion | +1.217 |
yrus | +1.159 |
rodent | +1.139 |
Neg logit contributions | |
ancial | -1.986 |
culosis | -1.934 |
Klu | -1.680 |
ilege | -1.674 |
reck | -1.674 |
Token | Abstract |
Token ID | 23839 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
ancial | +1.098 |
culosis | +1.066 |
Klu | +0.910 |
reck | +0.906 |
ilege | +0.893 |
Neg logit contributions | |
asma | -1.314 |
Hermes | -1.140 |
alion | -1.082 |
yrus | -1.043 |
rodent | -1.034 |
Token |
|
Token ID | 198 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
asma | +3.778 |
Hermes | +3.133 |
alion | +2.867 |
rodent | +2.756 |
yrus | +2.735 |
Neg logit contributions | |
ancial | -4.926 |
culosis | -4.773 |
pload | -4.253 |
orkshire | -4.201 |
reck | -4.173 |
Token |
|
Token ID | 198 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
asma | +2.918 |
Hermes | +2.344 |
alion | +2.140 |
yrus | +2.011 |
rodent | +1.999 |
Neg logit contributions | |
ancial | -4.867 |
culosis | -4.758 |
orkshire | -4.186 |
pload | -4.183 |
Klu | -4.179 |
Token | Background |
Token ID | 21756 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
asma | +4.076 |
Hermes | +3.426 |
alion | +3.279 |
yrus | +3.170 |
rodent | +3.169 |
Neg logit contributions | |
ancial | -3.712 |
culosis | -3.597 |
Klu | -3.076 |
pload | -3.060 |
orkshire | -3.018 |
Token | Depression |
Token ID | 22483 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
asma | +8.810 |
Hermes | +7.514 |
rodent | +6.692 |
alion | +6.681 |
Cao | +6.665 |
Neg logit contributions | |
ancial | -8.889 |
culosis | -8.642 |
pload | -7.774 |
orkshire | -7.588 |
reck | -7.454 |
Token | presents |
Token ID | 10969 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
asma | +2.060 |
Hermes | +1.748 |
alion | +1.632 |
yrus | +1.582 |
rodent | +1.567 |
Neg logit contributions | |
ancial | -2.225 |
culosis | -2.148 |
Klu | -1.870 |
pload | -1.854 |
reck | -1.840 |
Token | a |
Token ID | 257 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
asma | +0.279 |
Hermes | +0.237 |
alion | +0.223 |
yrus | +0.215 |
rodent | +0.213 |
Neg logit contributions | |
ancial | -0.296 |
culosis | -0.287 |
Klu | -0.249 |
reck | -0.246 |
pload | -0.245 |
Token | significant |
Token ID | 2383 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
asma | +0.447 |
Hermes | +0.376 |
alion | +0.353 |
yrus | +0.338 |
rodent | +0.334 |
Neg logit contributions | |
ancial | -0.523 |
culosis | -0.508 |
Klu | -0.445 |
reck | -0.439 |
pload | -0.439 |
Token | burden |
Token ID | 10538 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
ancial | +0.835 |
culosis | +0.807 |
Klu | +0.688 |
reck | +0.674 |
ilege | +0.670 |
Neg logit contributions | |
asma | -1.051 |
Hermes | -0.912 |
alion | -0.872 |
yrus | -0.842 |
rodent | -0.827 |
Token | team |
Token ID | 1074 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
asma | +3.226 |
Hermes | +2.736 |
alion | +2.511 |
rodent | +2.465 |
yrus | +2.430 |
Neg logit contributions | |
ancial | -3.887 |
culosis | -3.803 |
reck | -3.276 |
ilege | -3.274 |
Klu | -3.265 |
Token | lead |
Token ID | 1085 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
asma | +0.969 |
Hermes | +0.819 |
alion | +0.771 |
yrus | +0.740 |
rodent | +0.729 |
Neg logit contributions | |
ancial | -1.080 |
culosis | -1.049 |
Klu | -0.917 |
reck | -0.904 |
pload | -0.903 |
Token | author |
Token ID | 1772 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
asma | +1.531 |
Hermes | +1.299 |
alion | +1.220 |
yrus | +1.171 |
rodent | +1.158 |
Neg logit contributions | |
ancial | -1.712 |
culosis | -1.665 |
Klu | -1.450 |
pload | -1.435 |
reck | -1.433 |
Token | Dr |
Token ID | 1583 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ancial | +0.544 |
culosis | +0.527 |
Klu | +0.456 |
reck | +0.447 |
pload | +0.445 |
Neg logit contributions | |
asma | -0.592 |
Hermes | -0.506 |
alion | -0.482 |
yrus | -0.465 |
rodent | -0.458 |
Token | A |
Token ID | 317 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
ancial | +0.938 |
culosis | +0.907 |
Klu | +0.783 |
reck | +0.768 |
pload | +0.764 |
Neg logit contributions | |
asma | -1.057 |
Hermes | -0.908 |
alion | -0.865 |
yrus | -0.835 |
rodent | -0.824 |
Token | uro |
Token ID | 1434 |
Feature activation | -9.27e+00 |
Pos logit contributions | |
ancial | +0.050 |
culosis | +0.049 |
Klu | +0.042 |
reck | +0.042 |
pload | +0.041 |
Neg logit contributions | |
asma | -0.050 |
Hermes | -0.043 |
alion | -0.040 |
yrus | -0.039 |
rodent | -0.038 |
Token | re |
Token ID | 260 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
asma | +7.530 |
Hermes | +6.625 |
alion | +6.222 |
yrus | +5.926 |
Cao | +5.895 |
Neg logit contributions | |
ancial | -7.368 |
culosis | -7.107 |
ilege | -6.008 |
orkshire | -5.983 |
Klu | -5.862 |
Token | Av |
Token ID | 5184 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
asma | +2.234 |
Hermes | +1.933 |
alion | +1.814 |
yrus | +1.746 |
rodent | +1.718 |
Neg logit contributions | |
ancial | -2.101 |
culosis | -2.031 |
Klu | -1.725 |
pload | -1.719 |
ilege | -1.718 |
Token | arg |
Token ID | 853 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
asma | +0.188 |
Hermes | +0.160 |
alion | +0.152 |
yrus | +0.147 |
rodent | +0.143 |
Neg logit contributions | |
ancial | -0.187 |
culosis | -0.181 |
Klu | -0.157 |
pload | -0.155 |
reck | -0.154 |
Token | ues |
Token ID | 947 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
asma | +1.007 |
Hermes | +0.844 |
alion | +0.795 |
yrus | +0.761 |
rodent | +0.748 |
Neg logit contributions | |
ancial | -1.193 |
culosis | -1.160 |
Klu | -1.020 |
reck | -1.004 |
pload | -1.004 |
Token | - |
Token ID | 12 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
asma | +1.165 |
Hermes | +0.989 |
alion | +0.935 |
yrus | +0.897 |
rodent | +0.884 |
Neg logit contributions | |
ancial | -1.237 |
culosis | -1.202 |
Klu | -1.045 |
reck | -1.030 |
pload | -1.029 |
Token | of |
Token ID | 286 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
asma | +1.259 |
Hermes | +1.075 |
alion | +1.017 |
yrus | +0.979 |
rodent | +0.965 |
Neg logit contributions | |
ancial | -1.249 |
culosis | -1.208 |
Klu | -1.044 |
reck | -1.025 |
pload | -1.025 |
Token | champions |
Token ID | 7827 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
asma | +0.395 |
Hermes | +0.338 |
alion | +0.319 |
yrus | +0.307 |
rodent | +0.303 |
Neg logit contributions | |
ancial | -0.394 |
culosis | -0.382 |
Klu | -0.331 |
reck | -0.326 |
pload | -0.326 |
Token | – |
Token ID | 784 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
asma | +1.438 |
Hermes | +1.228 |
alion | +1.152 |
yrus | +1.105 |
rodent | +1.099 |
Neg logit contributions | |
ancial | -1.529 |
culosis | -1.482 |
Klu | -1.275 |
pload | -1.268 |
reck | -1.266 |
Token | Betty |
Token ID | 29504 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
asma | +1.114 |
Hermes | +0.958 |
alion | +0.897 |
yrus | +0.865 |
rodent | +0.859 |
Neg logit contributions | |
ancial | -1.108 |
culosis | -1.074 |
Klu | -0.922 |
pload | -0.917 |
reck | -0.913 |
Token | C |
Token ID | 327 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
ancial | +1.277 |
culosis | +1.236 |
Klu | +1.062 |
reck | +1.045 |
pload | +1.042 |
Neg logit contributions | |
asma | -1.435 |
Hermes | -1.236 |
alion | -1.173 |
yrus | -1.131 |
rodent | -1.118 |
Token | uth |
Token ID | 1071 |
Feature activation | -9.22e+00 |
Pos logit contributions | |
asma | +3.274 |
Hermes | +2.780 |
alion | +2.633 |
yrus | +2.570 |
ods | +2.492 |
Neg logit contributions | |
ancial | -3.250 |
culosis | -3.184 |
Klu | -2.758 |
pload | -2.730 |
ilege | -2.662 |
Token | bert |
Token ID | 4835 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
asma | +8.041 |
Hermes | +6.832 |
alion | +6.612 |
ns | +6.181 |
yrus | +6.179 |
Neg logit contributions | |
ancial | -6.761 |
culosis | -6.572 |
Klu | -5.795 |
pload | -5.553 |
orkshire | -5.354 |
Token | , |
Token ID | 11 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
asma | +0.545 |
Hermes | +0.465 |
alion | +0.438 |
yrus | +0.421 |
rodent | +0.415 |
Neg logit contributions | |
ancial | -0.556 |
culosis | -0.538 |
Klu | -0.466 |
pload | -0.460 |
reck | -0.460 |
Token | Don |
Token ID | 2094 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
asma | +0.246 |
Hermes | +0.214 |
alion | +0.203 |
yrus | +0.196 |
rodent | +0.194 |
Neg logit contributions | |
ancial | -0.203 |
culosis | -0.196 |
Klu | -0.166 |
pload | -0.164 |
reck | -0.164 |
Token | Brad |
Token ID | 8114 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
asma | +0.386 |
Hermes | +0.330 |
alion | +0.310 |
yrus | +0.299 |
rodent | +0.295 |
Neg logit contributions | |
ancial | -0.393 |
culosis | -0.382 |
Klu | -0.330 |
pload | -0.326 |
reck | -0.326 |
Token | man |
Token ID | 805 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
asma | +1.192 |
Hermes | +1.028 |
alion | +0.965 |
yrus | +0.931 |
rodent | +0.923 |
Neg logit contributions | |
ancial | -1.068 |
culosis | -1.048 |
Klu | -0.894 |
ilege | -0.881 |
pload | -0.880 |
Token | The |
Token ID | 383 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ancial | +1.985 |
culosis | +1.927 |
Klu | +1.687 |
reck | +1.655 |
pload | +1.644 |
Neg logit contributions | |
asma | -1.921 |
Hermes | -1.610 |
alion | -1.537 |
yrus | -1.477 |
rodent | -1.455 |
Token | Hill |
Token ID | 3327 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
ancial | +0.151 |
culosis | +0.144 |
pload | +0.120 |
Klu | +0.119 |
reck | +0.118 |
Neg logit contributions | |
asma | -0.216 |
Hermes | -0.190 |
alion | -0.180 |
yrus | -0.174 |
rodent | -0.172 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ancial | +0.347 |
culosis | +0.335 |
Klu | +0.290 |
reck | +0.283 |
pload | +0.282 |
Neg logit contributions | |
asma | -0.412 |
Hermes | -0.356 |
alion | -0.343 |
yrus | -0.330 |
rodent | -0.325 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ancial | +1.095 |
culosis | +1.064 |
Klu | +0.935 |
reck | +0.922 |
pload | +0.920 |
Neg logit contributions | |
asma | -0.919 |
Hermes | -0.773 |
alion | -0.724 |
yrus | -0.691 |
rodent | -0.682 |
Token | K |
Token ID | 42 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ancial | +0.967 |
culosis | +0.938 |
Klu | +0.801 |
reck | +0.796 |
pload | +0.786 |
Neg logit contributions | |
asma | -1.158 |
Hermes | -1.005 |
alion | -0.954 |
yrus | -0.920 |
rodent | -0.911 |
Token | UAL |
Token ID | 25620 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
asma | +1.635 |
Hermes | +1.401 |
alion | +1.339 |
yrus | +1.288 |
rodent | +1.260 |
Neg logit contributions | |
ancial | -1.501 |
culosis | -1.461 |
Klu | -1.251 |
pload | -1.227 |
reck | -1.219 |
Token | A |
Token ID | 32 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
asma | +6.371 |
Hermes | +4.831 |
alion | +4.450 |
rodent | +4.364 |
yrus | +4.333 |
Neg logit contributions | |
ancial | -8.229 |
culosis | -8.086 |
orkshire | -6.960 |
Klu | -6.887 |
pload | -6.861 |
Token | L |
Token ID | 406 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
asma | +3.193 |
Hermes | +2.742 |
alion | +2.439 |
Cao | +2.430 |
rodent | +2.371 |
Neg logit contributions | |
ancial | -3.596 |
culosis | -3.427 |
orkshire | -3.020 |
ilege | -2.983 |
pload | -2.971 |
Token | UMP |
Token ID | 20476 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
asma | +2.875 |
Hermes | +2.463 |
alion | +2.360 |
yrus | +2.267 |
ods | +2.234 |
Neg logit contributions | |
ancial | -2.072 |
culosis | -1.947 |
orkshire | -1.700 |
pload | -1.687 |
Klu | -1.660 |
Token | UR |
Token ID | 4261 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
asma | +2.105 |
Hermes | +1.792 |
alion | +1.691 |
yrus | +1.628 |
rodent | +1.606 |
Neg logit contributions | |
ancial | -2.147 |
culosis | -2.084 |
Klu | -1.808 |
reck | -1.782 |
pload | -1.780 |
Token | -- |
Token ID | 1377 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
asma | +1.420 |
Hermes | +1.192 |
alion | +1.120 |
yrus | +1.071 |
rodent | +1.057 |
Neg logit contributions | |
ancial | -1.663 |
culosis | -1.613 |
Klu | -1.416 |
reck | -1.397 |
pload | -1.395 |
Token | Ste |
Token ID | 7447 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
asma | +3.060 |
Hermes | +2.667 |
alion | +2.476 |
yrus | +2.347 |
rodent | +2.332 |
Neg logit contributions | |
ancial | -2.953 |
culosis | -2.859 |
pload | -2.426 |
orkshire | -2.412 |
Klu | -2.409 |
Token | lla |
Token ID | 8466 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
asma | +1.887 |
Hermes | +1.233 |
alion | +1.148 |
yrus | +1.009 |
rodent | +0.851 |
Neg logit contributions | |
ancial | -6.287 |
culosis | -6.173 |
Klu | -5.665 |
pload | -5.570 |
orkshire | -5.526 |
Token | - |
Token ID | 12 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
asma | +1.381 |
Hermes | +1.176 |
alion | +1.104 |
yrus | +1.062 |
rodent | +1.046 |
Neg logit contributions | |
ancial | -1.468 |
culosis | -1.423 |
Klu | -1.234 |
reck | -1.221 |
pload | -1.217 |
Token | san |
Token ID | 12807 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
asma | +3.097 |
Hermes | +2.569 |
alion | +2.392 |
yrus | +2.287 |
rodent | +2.213 |
Neg logit contributions | |
ancial | -4.317 |
culosis | -4.215 |
Klu | -3.704 |
pload | -3.695 |
orkshire | -3.662 |
Token | collapsed |
Token ID | 14707 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
asma | +3.690 |
Hermes | +3.167 |
alion | +2.944 |
yrus | +2.834 |
rodent | +2.771 |
Neg logit contributions | |
ancial | -4.258 |
culosis | -4.126 |
Klu | -3.588 |
reck | -3.556 |
pload | -3.554 |
Token | ?」 |
Token ID | 42943 |
Feature activation | -8.71e+00 |
Pos logit contributions | |
asma | +0.469 |
Hermes | +0.401 |
alion | +0.377 |
yrus | +0.363 |
rodent | +0.358 |
Neg logit contributions | |
ancial | -0.486 |
culosis | -0.470 |
Klu | -0.408 |
reck | -0.402 |
pload | -0.402 |
Token |
|
Token ID | 198 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
asma | +5.354 |
Hermes | +4.528 |
alion | +3.965 |
yrus | +3.740 |
Cao | +3.680 |
Neg logit contributions | |
ancial | -8.750 |
culosis | -8.456 |
orkshire | -7.546 |
pload | -7.489 |
ilege | -7.484 |
Token |
|
Token ID | 198 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
asma | +1.550 |
Hermes | +1.268 |
alion | +1.178 |
yrus | +1.118 |
rodent | +1.098 |
Neg logit contributions | |
ancial | -2.302 |
culosis | -2.244 |
Klu | -1.993 |
reck | -1.968 |
pload | -1.967 |
Token | " |
Token ID | 1 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
asma | +1.694 |
Hermes | +1.420 |
alion | +1.337 |
yrus | +1.277 |
rodent | +1.240 |
Neg logit contributions | |
ancial | -2.033 |
culosis | -1.971 |
Klu | -1.721 |
pload | -1.701 |
orkshire | -1.689 |
Token | Yes |
Token ID | 5297 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
asma | +2.051 |
Hermes | +1.774 |
alion | +1.669 |
yrus | +1.585 |
rodent | +1.567 |
Neg logit contributions | |
ancial | -2.017 |
culosis | -1.951 |
Klu | -1.666 |
pload | -1.662 |
orkshire | -1.644 |
Token | . |
Token ID | 13 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
asma | +1.742 |
Hermes | +1.488 |
alion | +1.402 |
yrus | +1.347 |
rodent | +1.328 |
Neg logit contributions | |
ancial | -1.792 |
culosis | -1.738 |
Klu | -1.508 |
pload | -1.487 |
reck | -1.485 |
Token | Paul |
Token ID | 3362 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
asma | +0.598 |
Hermes | +0.513 |
alion | +0.487 |
yrus | +0.470 |
rodent | +0.464 |
Neg logit contributions | |
ancial | -0.542 |
culosis | -0.525 |
Klu | -0.450 |
pload | -0.444 |
reck | -0.442 |
Token | and |
Token ID | 290 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
ancial | +0.136 |
culosis | +0.132 |
Klu | +0.115 |
reck | +0.113 |
pload | +0.113 |
Neg logit contributions | |
asma | -0.127 |
Hermes | -0.108 |
alion | -0.102 |
yrus | -0.098 |
rodent | -0.097 |
Token | - |
Token ID | 532 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ancial | +0.586 |
culosis | +0.568 |
Klu | +0.491 |
reck | +0.483 |
pload | +0.482 |
Neg logit contributions | |
asma | -0.616 |
Hermes | -0.527 |
alion | -0.500 |
yrus | -0.481 |
rodent | -0.475 |
Token | by |
Token ID | 416 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
asma | +1.556 |
Hermes | +1.319 |
alion | +1.239 |
yrus | +1.197 |
rodent | +1.185 |
Neg logit contributions | |
ancial | -1.644 |
culosis | -1.598 |
Klu | -1.385 |
pload | -1.379 |
orkshire | -1.360 |
Token | my |
Token ID | 616 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
asma | +3.584 |
Hermes | +3.051 |
alion | +2.798 |
rodent | +2.750 |
yrus | +2.664 |
Neg logit contributions | |
ancial | -4.115 |
culosis | -3.978 |
pload | -3.446 |
orkshire | -3.412 |
reck | -3.406 |
Token | standards |
Token ID | 5423 |
Feature activation | -8.55e+00 |
Pos logit contributions | |
asma | +1.507 |
Hermes | +1.287 |
alion | +1.205 |
rodent | +1.159 |
yrus | +1.153 |
Neg logit contributions | |
ancial | -1.582 |
culosis | -1.539 |
Klu | -1.326 |
pload | -1.317 |
reck | -1.308 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
asma | +6.348 |
Hermes | +5.446 |
alion | +5.061 |
rodent | +4.881 |
yrus | +4.732 |
Neg logit contributions | |
ancial | -7.303 |
culosis | -7.133 |
pload | -6.196 |
Klu | -6.089 |
orkshire | -6.077 |
Token | as |
Token ID | 355 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
asma | +0.951 |
Hermes | +0.813 |
alion | +0.761 |
rodent | +0.732 |
yrus | +0.731 |
Neg logit contributions | |
ancial | -0.985 |
culosis | -0.954 |
Klu | -0.820 |
pload | -0.816 |
reck | -0.813 |
Token | I |
Token ID | 314 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ancial | +1.747 |
culosis | +1.701 |
Klu | +1.496 |
reck | +1.464 |
pload | +1.451 |
Neg logit contributions | |
asma | -1.747 |
Hermes | -1.487 |
alion | -1.422 |
yrus | -1.368 |
rodent | -1.328 |
Token | look |
Token ID | 804 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ancial | +1.258 |
culosis | +1.220 |
Klu | +1.061 |
reck | +1.046 |
pload | +1.042 |
Neg logit contributions | |
asma | -1.224 |
Hermes | -1.041 |
alion | -0.985 |
yrus | -0.946 |
rodent | -0.932 |
Token | at |
Token ID | 379 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
asma | +1.676 |
Hermes | +1.458 |
alion | +1.384 |
yrus | +1.328 |
rodent | +1.325 |
Neg logit contributions | |
ancial | -1.392 |
culosis | -1.358 |
Klu | -1.143 |
pload | -1.129 |
reck | -1.121 |
Token | take |
Token ID | 1011 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ancial | +0.603 |
culosis | +0.585 |
Klu | +0.507 |
reck | +0.499 |
pload | +0.498 |
Neg logit contributions | |
asma | -0.611 |
Hermes | -0.522 |
alion | -0.494 |
yrus | -0.475 |
rodent | -0.469 |
Token | effect |
Token ID | 1245 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
ancial | +0.911 |
culosis | +0.868 |
Klu | +0.687 |
reck | +0.668 |
pload | +0.665 |
Neg logit contributions | |
asma | -1.930 |
Hermes | -1.720 |
alion | -1.656 |
yrus | -1.612 |
rodent | -1.596 |
Token | in |
Token ID | 287 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
ancial | +3.218 |
culosis | +3.073 |
Klu | +2.683 |
reck | +2.666 |
pload | +2.632 |
Neg logit contributions | |
asma | -3.666 |
Hermes | -3.110 |
alion | -2.985 |
yrus | -2.865 |
rodent | -2.819 |
Token | lower |
Token ID | 2793 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ancial | +0.508 |
culosis | +0.493 |
Klu | +0.425 |
reck | +0.419 |
pload | +0.418 |
Neg logit contributions | |
asma | -0.537 |
Hermes | -0.460 |
alion | -0.436 |
yrus | -0.420 |
rodent | -0.415 |
Token | - |
Token ID | 12 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
asma | +1.336 |
Hermes | +1.151 |
alion | +1.088 |
yrus | +1.050 |
rodent | +1.040 |
Neg logit contributions | |
ancial | -1.245 |
culosis | -1.209 |
Klu | -1.038 |
reck | -1.026 |
pload | -1.024 |
Token | cost |
Token ID | 15805 |
Feature activation | -8.39e+00 |
Pos logit contributions | |
asma | +2.636 |
Hermes | +2.234 |
alion | +2.105 |
yrus | +2.050 |
rodent | +2.008 |
Neg logit contributions | |
ancial | -2.769 |
culosis | -2.704 |
Klu | -2.365 |
pload | -2.338 |
orkshire | -2.287 |
Token | parts |
Token ID | 3354 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
asma | +6.391 |
Hermes | +5.567 |
rodent | +5.069 |
alion | +4.992 |
yrus | +4.938 |
Neg logit contributions | |
culosis | -6.934 |
ancial | -6.885 |
pload | -6.024 |
ilege | -5.836 |
orkshire | -5.830 |
Token | of |
Token ID | 286 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
asma | +0.999 |
Hermes | +0.857 |
alion | +0.814 |
yrus | +0.785 |
rodent | +0.774 |
Neg logit contributions | |
ancial | -0.918 |
culosis | -0.888 |
Klu | -0.768 |
reck | -0.755 |
pload | -0.752 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
asma | +0.744 |
Hermes | +0.636 |
alion | +0.593 |
yrus | +0.570 |
rodent | +0.567 |
Neg logit contributions | |
ancial | -0.823 |
culosis | -0.806 |
Klu | -0.698 |
reck | -0.691 |
pload | -0.690 |
Token | country |
Token ID | 1499 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
asma | +0.880 |
Hermes | +0.753 |
alion | +0.706 |
yrus | +0.682 |
rodent | +0.676 |
Neg logit contributions | |
ancial | -0.918 |
culosis | -0.893 |
Klu | -0.771 |
pload | -0.763 |
reck | -0.762 |
Token | . |
Token ID | 13 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
asma | +1.696 |
Hermes | +1.456 |
alion | +1.373 |
yrus | +1.326 |
rodent | +1.308 |
Neg logit contributions | |
ancial | -1.653 |
culosis | -1.610 |
Klu | -1.394 |
pload | -1.366 |
reck | -1.365 |
Token | MD |
Token ID | 10670 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
asma | +0.419 |
Hermes | +0.362 |
alion | +0.344 |
yrus | +0.332 |
rodent | +0.328 |
Neg logit contributions | |
ancial | -0.355 |
culosis | -0.344 |
Klu | -0.294 |
reck | -0.289 |
pload | -0.288 |
Token | D |
Token ID | 35 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ancial | +1.771 |
culosis | +1.715 |
Klu | +1.447 |
reck | +1.422 |
ilege | +1.403 |
Neg logit contributions | |
asma | -2.447 |
Hermes | -2.140 |
alion | -2.047 |
yrus | -1.976 |
rodent | -1.936 |
Token | . |
Token ID | 13 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
ancial | +2.288 |
culosis | +2.223 |
Klu | +1.928 |
reck | +1.876 |
ilege | +1.860 |
Neg logit contributions | |
asma | -2.559 |
Hermes | -2.206 |
alion | -2.132 |
yrus | -2.015 |
rodent | -1.974 |
Token |
|
Token ID | 198 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
asma | +3.357 |
Hermes | +2.738 |
alion | +2.516 |
rodent | +2.366 |
yrus | +2.351 |
Neg logit contributions | |
ancial | -4.989 |
culosis | -4.860 |
pload | -4.319 |
orkshire | -4.287 |
reck | -4.284 |
Token |
|
Token ID | 198 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
asma | +2.816 |
Hermes | +2.260 |
alion | +2.061 |
yrus | +1.943 |
rodent | +1.925 |
Neg logit contributions | |
ancial | -4.676 |
culosis | -4.569 |
pload | -4.012 |
Klu | -4.012 |
orkshire | -4.007 |
Token | Methods |
Token ID | 46202 |
Feature activation | -8.38e+00 |
Pos logit contributions | |
asma | +3.736 |
Hermes | +2.902 |
alion | +2.809 |
yrus | +2.694 |
rodent | +2.681 |
Neg logit contributions | |
ancial | -5.054 |
culosis | -4.967 |
Klu | -4.387 |
pload | -4.368 |
orkshire | -4.295 |
Token | This |
Token ID | 770 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
asma | +6.497 |
Hermes | +5.412 |
alion | +4.987 |
rodent | +4.793 |
yrus | +4.779 |
Neg logit contributions | |
ancial | -7.148 |
culosis | -6.996 |
pload | -6.266 |
orkshire | -6.087 |
reck | -6.038 |
Token | is |
Token ID | 318 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
asma | +3.115 |
Hermes | +2.574 |
alion | +2.380 |
rodent | +2.306 |
yrus | +2.287 |
Neg logit contributions | |
ancial | -4.173 |
culosis | -4.109 |
pload | -3.605 |
Klu | -3.574 |
reck | -3.566 |
Token | a |
Token ID | 257 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
asma | +3.400 |
Hermes | +2.854 |
alion | +2.667 |
yrus | +2.584 |
rodent | +2.578 |
Neg logit contributions | |
ancial | -4.085 |
culosis | -4.002 |
pload | -3.482 |
reck | -3.463 |
ilege | -3.451 |
Token | non |
Token ID | 1729 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
asma | +3.256 |
Hermes | +2.696 |
rodent | +2.468 |
alion | +2.443 |
yrus | +2.375 |
Neg logit contributions | |
ancial | -4.409 |
culosis | -4.336 |
pload | -3.769 |
ilege | -3.761 |
reck | -3.738 |
Token | random |
Token ID | 25120 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
asma | +0.581 |
Hermes | +0.496 |
alion | +0.470 |
yrus | +0.452 |
rodent | +0.447 |
Neg logit contributions | |
ancial | -0.568 |
culosis | -0.551 |
Klu | -0.477 |
reck | -0.469 |
pload | -0.469 |
Token | et |
Token ID | 2123 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
asma | +2.230 |
Hermes | +1.875 |
alion | +1.711 |
rodent | +1.641 |
yrus | +1.640 |
Neg logit contributions | |
ancial | -2.790 |
culosis | -2.706 |
pload | -2.372 |
ilege | -2.358 |
Klu | -2.345 |
Token | al |
Token ID | 435 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
asma | +2.387 |
Hermes | +1.974 |
alion | +1.832 |
yrus | +1.744 |
rodent | +1.720 |
Neg logit contributions | |
ancial | -3.409 |
culosis | -3.315 |
Klu | -2.917 |
pload | -2.903 |
reck | -2.891 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
asma | +2.210 |
Hermes | +1.871 |
alion | +1.766 |
yrus | +1.694 |
rodent | +1.681 |
Neg logit contributions | |
ancial | -2.255 |
culosis | -2.197 |
Klu | -1.910 |
pload | -1.901 |
ilege | -1.881 |
Token | 2014 |
Token ID | 1946 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
asma | +1.950 |
Hermes | +1.678 |
alion | +1.565 |
yrus | +1.508 |
rodent | +1.503 |
Neg logit contributions | |
ancial | -1.949 |
culosis | -1.894 |
pload | -1.618 |
Klu | -1.618 |
ilege | -1.607 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
asma | +1.630 |
Hermes | +1.397 |
alion | +1.318 |
yrus | +1.274 |
rodent | +1.263 |
Neg logit contributions | |
ancial | -1.540 |
culosis | -1.494 |
Klu | -1.279 |
pload | -1.273 |
ilege | -1.264 |
Token | Tax |
Token ID | 9241 |
Feature activation | -8.36e+00 |
Pos logit contributions | |
asma | +1.811 |
Hermes | +1.556 |
alion | +1.445 |
yrus | +1.393 |
rodent | +1.385 |
Neg logit contributions | |
ancial | -1.875 |
culosis | -1.819 |
pload | -1.560 |
Klu | -1.558 |
ilege | -1.551 |
Token | onomy |
Token ID | 30565 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
asma | +5.644 |
Hermes | +4.510 |
yrus | +4.309 |
alion | +4.273 |
ods | +4.120 |
Neg logit contributions | |
ancial | -7.899 |
culosis | -7.581 |
Klu | -6.891 |
pload | -6.724 |
reck | -6.643 |
Token | of |
Token ID | 286 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
asma | +4.560 |
Hermes | +3.839 |
alion | +3.559 |
rodent | +3.507 |
yrus | +3.495 |
Neg logit contributions | |
ancial | -4.965 |
culosis | -4.839 |
pload | -4.216 |
Klu | -4.149 |
ilege | -4.085 |
Token | rock |
Token ID | 3881 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
asma | +1.450 |
Hermes | +1.242 |
alion | +1.150 |
yrus | +1.121 |
rodent | +1.116 |
Neg logit contributions | |
ancial | -1.548 |
culosis | -1.508 |
Klu | -1.298 |
pload | -1.293 |
reck | -1.285 |
Token | - |
Token ID | 12 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
ancial | +0.322 |
culosis | +0.312 |
Klu | +0.268 |
reck | +0.263 |
pload | +0.262 |
Neg logit contributions | |
asma | -0.372 |
Hermes | -0.321 |
alion | -0.306 |
yrus | -0.294 |
rodent | -0.290 |
Token | wall |
Token ID | 11930 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
asma | +0.940 |
Hermes | +0.817 |
alion | +0.780 |
yrus | +0.755 |
rodent | +0.746 |
Neg logit contributions | |
ancial | -0.715 |
culosis | -0.690 |
Klu | -0.585 |
reck | -0.572 |
pload | -0.572 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
asma | +0.704 |
Hermes | +0.578 |
alion | +0.540 |
yrus | +0.514 |
rodent | +0.504 |
Neg logit contributions | |
ancial | -1.003 |
culosis | -0.978 |
Klu | -0.872 |
reck | -0.860 |
pload | -0.857 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
asma | +0.987 |
Hermes | +0.854 |
alion | +0.813 |
yrus | +0.788 |
rodent | +0.776 |
Neg logit contributions | |
ancial | -0.795 |
culosis | -0.767 |
Klu | -0.655 |
pload | -0.639 |
reck | -0.636 |
Token | ) |
Token ID | 8 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
asma | +0.995 |
Hermes | +0.856 |
alion | +0.808 |
yrus | +0.780 |
rodent | +0.770 |
Neg logit contributions | |
ancial | -0.935 |
culosis | -0.906 |
Klu | -0.783 |
pload | -0.769 |
reck | -0.769 |
Token | Shrine |
Token ID | 30682 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
asma | +1.723 |
Hermes | +1.481 |
alion | +1.384 |
yrus | +1.337 |
rodent | +1.317 |
Neg logit contributions | |
ancial | -1.730 |
culosis | -1.680 |
Klu | -1.452 |
reck | -1.436 |
pload | -1.433 |
Token | for |
Token ID | 329 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
asma | +2.071 |
Hermes | +1.773 |
alion | +1.656 |
yrus | +1.607 |
rodent | +1.573 |
Neg logit contributions | |
ancial | -2.146 |
culosis | -2.083 |
Klu | -1.810 |
reck | -1.781 |
orkshire | -1.780 |
Token | Cup |
Token ID | 5454 |
Feature activation | -8.29e+00 |
Pos logit contributions | |
asma | +0.582 |
Hermes | +0.495 |
alion | +0.469 |
yrus | +0.451 |
rodent | +0.444 |
Neg logit contributions | |
ancial | -0.589 |
culosis | -0.572 |
Klu | -0.497 |
reck | -0.489 |
pload | -0.488 |
Token | id |
Token ID | 312 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
asma | +4.092 |
Hermes | +2.855 |
alion | +2.854 |
yrus | +2.673 |
ods | +2.546 |
Neg logit contributions | |
ancial | -9.315 |
culosis | -9.009 |
Klu | -8.330 |
orkshire | -8.161 |
Strike | -8.126 |
Token | : |
Token ID | 1058 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
asma | +0.752 |
Hermes | +0.638 |
alion | +0.602 |
yrus | +0.578 |
rodent | +0.570 |
Neg logit contributions | |
ancial | -0.800 |
culosis | -0.776 |
Klu | -0.676 |
reck | -0.666 |
pload | -0.665 |
Token | Called |
Token ID | 34099 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
asma | +2.851 |
Hermes | +2.434 |
alion | +2.270 |
yrus | +2.189 |
rodent | +2.137 |
Neg logit contributions | |
ancial | -3.090 |
culosis | -2.997 |
Klu | -2.601 |
reck | -2.571 |
ilege | -2.570 |
Token | as |
Token ID | 355 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
asma | +4.081 |
Hermes | +3.485 |
alion | +3.227 |
yrus | +3.143 |
rodent | +3.069 |
Neg logit contributions | |
ancial | -4.291 |
culosis | -4.152 |
Klu | -3.564 |
orkshire | -3.550 |
ilege | -3.546 |
Token | Man |
Token ID | 1869 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
asma | +2.571 |
Hermes | +2.190 |
alion | +2.050 |
yrus | +1.985 |
rodent | +1.943 |
Neg logit contributions | |
ancial | -2.729 |
culosis | -2.652 |
Klu | -2.290 |
reck | -2.266 |
ilege | -2.257 |
Token | i |
Token ID | 72 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
asma | +2.369 |
Hermes | +1.942 |
alion | +1.804 |
yrus | +1.718 |
rodent | +1.682 |
Neg logit contributions | |
ancial | -3.287 |
culosis | -3.181 |
Klu | -2.780 |
reck | -2.766 |
pload | -2.759 |
Token | i |
Token ID | 1312 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
asma | +2.043 |
Hermes | +1.712 |
alion | +1.590 |
yrus | +1.518 |
rodent | +1.494 |
Neg logit contributions | |
ancial | -2.584 |
culosis | -2.506 |
Klu | -2.177 |
reck | -2.165 |
pload | -2.162 |
Token | Kau |
Token ID | 28148 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
asma | +3.295 |
Hermes | +2.753 |
alion | +2.551 |
yrus | +2.457 |
rodent | +2.398 |
Neg logit contributions | |
ancial | -4.044 |
culosis | -3.897 |
Klu | -3.364 |
pload | -3.346 |
reck | -3.344 |
Token | a |
Token ID | 64 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
asma | +0.338 |
Hermes | +0.285 |
alion | +0.266 |
yrus | +0.255 |
rodent | +0.253 |
Neg logit contributions | |
ancial | -0.421 |
culosis | -0.410 |
Klu | -0.362 |
reck | -0.357 |
pload | -0.356 |
Token | � |
Token ID | 134 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
asma | +1.115 |
Hermes | +0.972 |
alion | +0.926 |
yrus | +0.897 |
rodent | +0.886 |
Neg logit contributions | |
ancial | -0.816 |
culosis | -0.785 |
Klu | -0.657 |
reck | -0.647 |
pload | -0.646 |
Token | � |
Token ID | 119 |
Feature activation | -8.23e+00 |
Pos logit contributions | |
asma | +2.256 |
Hermes | +1.788 |
alion | +1.629 |
yrus | +1.558 |
rodent | +1.507 |
Neg logit contributions | |
ancial | -3.701 |
culosis | -3.594 |
Klu | -3.206 |
orkshire | -3.190 |
pload | -3.177 |
Token | i |
Token ID | 72 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
asma | +3.999 |
Hermes | +2.757 |
alion | +2.647 |
yrus | +2.359 |
ods | +2.232 |
Neg logit contributions | |
ancial | -9.474 |
culosis | -9.215 |
Klu | -8.361 |
orkshire | -8.229 |
pload | -8.224 |
Token | , |
Token ID | 11 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
asma | +1.917 |
Hermes | +1.617 |
alion | +1.513 |
yrus | +1.451 |
rodent | +1.433 |
Neg logit contributions | |
ancial | -2.209 |
culosis | -2.141 |
Klu | -1.862 |
reck | -1.845 |
pload | -1.844 |
Token | ho |
Token ID | 8169 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
asma | +1.825 |
Hermes | +1.525 |
alion | +1.421 |
yrus | +1.356 |
rodent | +1.336 |
Neg logit contributions | |
ancial | -2.287 |
culosis | -2.221 |
Klu | -1.940 |
reck | -1.927 |
pload | -1.926 |
Token | � |
Token ID | 134 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
ancial | +0.088 |
culosis | +0.085 |
Klu | +0.073 |
reck | +0.071 |
pload | +0.071 |
Neg logit contributions | |
asma | -0.108 |
Hermes | -0.094 |
alion | -0.090 |
yrus | -0.086 |
rodent | -0.086 |
Token | � |
Token ID | 119 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
asma | +0.162 |
Hermes | +0.132 |
alion | +0.122 |
yrus | +0.116 |
rodent | +0.114 |
Neg logit contributions | |
ancial | -0.245 |
culosis | -0.239 |
Klu | -0.213 |
reck | -0.210 |
pload | -0.209 |
Token | , |
Token ID | 11 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
asma | +1.013 |
Hermes | +0.855 |
alion | +0.795 |
yrus | +0.767 |
rodent | +0.757 |
Neg logit contributions | |
ancial | -1.191 |
culosis | -1.158 |
Klu | -1.013 |
pload | -1.006 |
orkshire | -0.998 |
Token | 11 |
Token ID | 1367 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
asma | +2.048 |
Hermes | +1.766 |
alion | +1.627 |
yrus | +1.571 |
rodent | +1.569 |
Neg logit contributions | |
ancial | -2.201 |
culosis | -2.137 |
Klu | -1.829 |
ilege | -1.819 |
reck | -1.819 |
Token | : |
Token ID | 25 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ancial | +0.519 |
culosis | +0.505 |
Klu | +0.446 |
reck | +0.440 |
pload | +0.438 |
Neg logit contributions | |
asma | -0.428 |
Hermes | -0.357 |
alion | -0.337 |
yrus | -0.322 |
rodent | -0.316 |
Token | 15 |
Token ID | 1314 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ancial | +1.350 |
culosis | +1.301 |
Klu | +1.160 |
reck | +1.123 |
Strike | +1.103 |
Neg logit contributions | |
asma | -1.677 |
Hermes | -1.426 |
alion | -1.392 |
yrus | -1.356 |
rodent | -1.327 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
asma | +0.245 |
Hermes | +0.202 |
alion | +0.189 |
yrus | +0.179 |
rodent | +0.176 |
Neg logit contributions | |
ancial | -0.339 |
culosis | -0.330 |
Klu | -0.293 |
reck | -0.289 |
pload | -0.288 |
Token | . |
Token ID | 13 |
Feature activation | -8.18e+00 |
Pos logit contributions | |
asma | +1.011 |
Hermes | +0.870 |
alion | +0.827 |
yrus | +0.798 |
rodent | +0.788 |
Neg logit contributions | |
ancial | -0.901 |
culosis | -0.872 |
Klu | -0.751 |
reck | -0.739 |
pload | -0.736 |
Token | m |
Token ID | 76 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
asma | +4.883 |
Hermes | +3.871 |
alion | +3.586 |
ns | +3.404 |
ods | +3.349 |
Neg logit contributions | |
ancial | -8.506 |
culosis | -8.278 |
aution | -7.407 |
orkshire | -7.311 |
pload | -7.276 |
Token | .: |
Token ID | 11207 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
asma | +4.359 |
Hermes | +3.724 |
alion | +3.451 |
yrus | +3.294 |
ods | +3.250 |
Neg logit contributions | |
ancial | -4.840 |
culosis | -4.723 |
ilege | -4.094 |
pload | -4.034 |
orkshire | -4.015 |
Token | Notes |
Token ID | 11822 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ancial | +0.324 |
culosis | +0.315 |
Klu | +0.279 |
reck | +0.272 |
pload | +0.272 |
Neg logit contributions | |
asma | -0.280 |
Hermes | -0.233 |
alion | -0.223 |
yrus | -0.215 |
rodent | -0.211 |
Token | that |
Token ID | 326 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ancial | +0.238 |
culosis | +0.232 |
Klu | +0.201 |
reck | +0.198 |
pload | +0.198 |
Neg logit contributions | |
asma | -0.230 |
Hermes | -0.196 |
alion | -0.185 |
yrus | -0.178 |
rodent | -0.175 |
Token | Group |
Token ID | 4912 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
asma | +1.297 |
Hermes | +1.093 |
alion | +1.017 |
yrus | +0.977 |
rodent | +0.966 |
Neg logit contributions | |
ancial | -1.551 |
culosis | -1.511 |
Klu | -1.322 |
reck | -1.308 |
pload | -1.304 |
Token | cannot |
Token ID | 2314 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
asma | +1.488 |
Hermes | +1.259 |
alion | +1.192 |
yrus | +1.147 |
rodent | +1.125 |
Neg logit contributions | |
ancial | -1.578 |
culosis | -1.545 |
Klu | -1.335 |
reck | -1.329 |
orkshire | -1.320 |
Token | find |
Token ID | 1064 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
asma | +1.644 |
Hermes | +1.404 |
alion | +1.319 |
yrus | +1.279 |
rodent | +1.259 |
Neg logit contributions | |
ancial | -1.686 |
culosis | -1.646 |
Klu | -1.414 |
reck | -1.404 |
orkshire | -1.398 |
Token | the |
Token ID | 262 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
asma | +3.026 |
Hermes | +2.562 |
alion | +2.371 |
yrus | +2.340 |
rodent | +2.327 |
Neg logit contributions | |
ancial | -3.300 |
culosis | -3.264 |
reck | -2.814 |
orkshire | -2.771 |
pload | -2.771 |
Token | current |
Token ID | 1459 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
asma | +0.238 |
Hermes | +0.202 |
alion | +0.189 |
yrus | +0.183 |
rodent | +0.181 |
Neg logit contributions | |
ancial | -0.253 |
culosis | -0.246 |
Klu | -0.213 |
reck | -0.211 |
pload | -0.210 |
Token | wallpaper |
Token ID | 39328 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ancial | +0.170 |
culosis | +0.166 |
Klu | +0.146 |
reck | +0.144 |
pload | +0.143 |
Neg logit contributions | |
asma | -0.137 |
Hermes | -0.115 |
alion | -0.108 |
yrus | -0.103 |
rodent | -0.102 |
Token | $ |
Token ID | 720 |
Feature activation | -8.15e+00 |
Pos logit contributions | |
asma | +2.013 |
Hermes | +1.713 |
alion | +1.605 |
yrus | +1.562 |
rodent | +1.537 |
Neg logit contributions | |
ancial | -2.139 |
culosis | -2.118 |
Klu | -1.818 |
reck | -1.809 |
pload | -1.805 |
Token | ($ |
Token ID | 16763 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
asma | +6.788 |
Hermes | +5.514 |
alion | +5.353 |
yrus | +5.145 |
ods | +5.102 |
Neg logit contributions | |
ancial | -6.462 |
culosis | -6.279 |
Klu | -5.460 |
pload | -5.398 |
orkshire | -5.313 |
Token | w |
Token ID | 86 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
asma | +3.918 |
Hermes | +3.284 |
alion | +3.157 |
yrus | +3.045 |
rodent | +3.007 |
Neg logit contributions | |
ancial | -3.484 |
culosis | -3.368 |
Klu | -2.907 |
pload | -2.828 |
orkshire | -2.816 |
Token | path |
Token ID | 6978 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
asma | +0.801 |
Hermes | +0.665 |
alion | +0.624 |
yrus | +0.595 |
rodent | +0.585 |
Neg logit contributions | |
ancial | -1.033 |
culosis | -1.006 |
Klu | -0.889 |
reck | -0.873 |
pload | -0.873 |
Token | )" |
Token ID | 16725 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
ancial | +1.322 |
culosis | +1.271 |
Klu | +1.083 |
reck | +1.062 |
pload | +1.060 |
Neg logit contributions | |
asma | -1.639 |
Hermes | -1.417 |
alion | -1.354 |
yrus | -1.314 |
rodent | -1.293 |
Token | break |
Token ID | 2270 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
asma | +2.288 |
Hermes | +1.964 |
alion | +1.842 |
yrus | +1.765 |
rodent | +1.757 |
Neg logit contributions | |
ancial | -2.330 |
culosis | -2.265 |
Klu | -1.958 |
reck | -1.942 |
pload | -1.936 |
Token | Vim |
Token ID | 36645 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
ancial | +0.712 |
culosis | +0.694 |
Klu | +0.612 |
pload | +0.601 |
reck | +0.601 |
Neg logit contributions | |
asma | -0.598 |
Hermes | -0.499 |
alion | -0.476 |
yrus | -0.453 |
rodent | -0.442 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
asma | +2.417 |
Hermes | +2.056 |
alion | +1.908 |
yrus | +1.844 |
rodent | +1.827 |
Neg logit contributions | |
ancial | -2.633 |
culosis | -2.539 |
Klu | -2.203 |
reck | -2.180 |
orkshire | -2.176 |
Token | . |
Token ID | 13 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
asma | +1.331 |
Hermes | +1.142 |
alion | +1.077 |
yrus | +1.042 |
rodent | +1.030 |
Neg logit contributions | |
ancial | -1.262 |
culosis | -1.221 |
Klu | -1.052 |
reck | -1.038 |
pload | -1.033 |
Token | 0 |
Token ID | 15 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
asma | +4.329 |
Hermes | +3.711 |
alion | +3.476 |
yrus | +3.364 |
rodent | +3.306 |
Neg logit contributions | |
ancial | -4.124 |
culosis | -3.953 |
Klu | -3.397 |
reck | -3.353 |
orkshire | -3.351 |
Token | and |
Token ID | 290 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
asma | +1.547 |
Hermes | +1.317 |
alion | +1.231 |
yrus | +1.187 |
rodent | +1.175 |
Neg logit contributions | |
ancial | -1.691 |
culosis | -1.636 |
Klu | -1.424 |
reck | -1.409 |
pload | -1.403 |
Token | later |
Token ID | 1568 |
Feature activation | -8.07e+00 |
Pos logit contributions | |
asma | +2.034 |
Hermes | +1.707 |
alion | +1.576 |
yrus | +1.505 |
rodent | +1.499 |
Neg logit contributions | |
ancial | -2.649 |
culosis | -2.561 |
Klu | -2.248 |
reck | -2.232 |
pload | -2.222 |
Token | : |
Token ID | 25 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
asma | +5.639 |
Hermes | +4.797 |
rodent | +4.259 |
yrus | +4.256 |
alion | +4.233 |
Neg logit contributions | |
ancial | -7.517 |
culosis | -7.251 |
reck | -6.314 |
orkshire | -6.283 |
pload | -6.259 |
Token | /* |
Token ID | 11900 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
ancial | +0.161 |
culosis | +0.157 |
Klu | +0.141 |
pload | +0.139 |
reck | +0.139 |
Neg logit contributions | |
asma | -0.104 |
Hermes | -0.084 |
alion | -0.079 |
yrus | -0.074 |
rodent | -0.073 |
Token | vim |
Token ID | 43907 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
asma | +0.460 |
Hermes | +0.361 |
alion | +0.330 |
yrus | +0.310 |
rodent | +0.303 |
Neg logit contributions | |
ancial | -0.882 |
culosis | -0.862 |
Klu | -0.776 |
reck | -0.767 |
pload | -0.766 |
Token | 600 |
Token ID | 8054 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
asma | +1.943 |
Hermes | +1.607 |
alion | +1.504 |
yrus | +1.435 |
rodent | +1.415 |
Neg logit contributions | |
ancial | -2.547 |
culosis | -2.468 |
Klu | -2.186 |
reck | -2.152 |
pload | -2.145 |
Token | : |
Token ID | 25 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
ancial | +0.106 |
culosis | +0.104 |
Klu | +0.091 |
reck | +0.090 |
pload | +0.090 |
Neg logit contributions | |
asma | -0.091 |
Hermes | -0.077 |
alion | -0.072 |
yrus | -0.069 |
rodent | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
asma | +1.364 |
Hermes | +1.160 |
alion | +1.094 |
yrus | +1.056 |
rodent | +1.045 |
Neg logit contributions | |
ancial | -1.425 |
culosis | -1.392 |
Klu | -1.204 |
pload | -1.187 |
reck | -1.186 |
Token |
|
Token ID | 198 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
asma | +3.754 |
Hermes | +3.225 |
alion | +2.963 |
rodent | +2.863 |
yrus | +2.858 |
Neg logit contributions | |
ancial | -4.206 |
culosis | -4.078 |
pload | -3.521 |
orkshire | -3.506 |
ilege | -3.500 |
Token |
|
Token ID | 198 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
asma | +2.809 |
Hermes | +2.259 |
alion | +2.054 |
yrus | +1.931 |
rodent | +1.915 |
Neg logit contributions | |
ancial | -4.679 |
culosis | -4.570 |
Klu | -4.011 |
orkshire | -4.007 |
pload | -4.006 |
Token | Materials |
Token ID | 41657 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
asma | +4.699 |
Hermes | +3.935 |
alion | +3.790 |
yrus | +3.687 |
rodent | +3.671 |
Neg logit contributions | |
ancial | -4.405 |
culosis | -4.285 |
Klu | -3.683 |
pload | -3.599 |
orkshire | -3.566 |
Token | and |
Token ID | 290 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
asma | +5.459 |
Hermes | +4.554 |
alion | +4.164 |
rodent | +4.098 |
yrus | +4.096 |
Neg logit contributions | |
ancial | -6.021 |
culosis | -5.991 |
pload | -5.155 |
orkshire | -5.067 |
ilege | -5.063 |
Token | Methods |
Token ID | 25458 |
Feature activation | -8.06e+00 |
Pos logit contributions | |
asma | +1.523 |
Hermes | +1.256 |
alion | +1.173 |
yrus | +1.114 |
rodent | +1.102 |
Neg logit contributions | |
ancial | -2.085 |
culosis | -2.035 |
Klu | -1.797 |
reck | -1.775 |
pload | -1.772 |
Token | Experimental |
Token ID | 32286 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
asma | +6.296 |
Hermes | +5.304 |
rodent | +4.881 |
alion | +4.864 |
yrus | +4.784 |
Neg logit contributions | |
ancial | -6.782 |
culosis | -6.761 |
pload | -5.858 |
orkshire | -5.769 |
ilege | -5.718 |
Token | subjects |
Token ID | 7481 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
asma | +3.173 |
Hermes | +2.672 |
alion | +2.511 |
rodent | +2.460 |
yrus | +2.433 |
Neg logit contributions | |
ancial | -3.523 |
culosis | -3.425 |
Klu | -2.970 |
pload | -2.968 |
orkshire | -2.963 |
Token | Three |
Token ID | 7683 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
ancial | +0.590 |
culosis | +0.570 |
Klu | +0.497 |
reck | +0.489 |
pload | +0.482 |
Neg logit contributions | |
asma | -0.616 |
Hermes | -0.527 |
alion | -0.502 |
yrus | -0.480 |
rodent | -0.472 |
Token | female |
Token ID | 4048 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
asma | +3.212 |
Hermes | +2.642 |
alion | +2.402 |
rodent | +2.386 |
yrus | +2.352 |
Neg logit contributions | |
ancial | -4.748 |
culosis | -4.717 |
Klu | -4.103 |
pload | -4.085 |
ilege | -4.053 |
Token | r |
Token ID | 374 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
asma | +2.555 |
Hermes | +2.147 |
alion | +1.941 |
rodent | +1.924 |
yrus | +1.889 |
Neg logit contributions | |
ancial | -3.418 |
culosis | -3.358 |
Klu | -2.904 |
pload | -2.902 |
ilege | -2.897 |
Token |
|
Token ID | 198 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
asma | +0.908 |
Hermes | +0.766 |
alion | +0.715 |
yrus | +0.676 |
rodent | +0.669 |
Neg logit contributions | |
ancial | -1.102 |
culosis | -1.073 |
Klu | -0.932 |
reck | -0.931 |
pload | -0.928 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
asma | +1.396 |
Hermes | +1.143 |
alion | +1.064 |
yrus | +1.011 |
rodent | +0.993 |
Neg logit contributions | |
ancial | -2.047 |
culosis | -1.995 |
Klu | -1.775 |
reck | -1.752 |
pload | -1.749 |
Token | Kh |
Token ID | 33155 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
asma | +1.269 |
Hermes | +1.092 |
alion | +1.050 |
yrus | +1.009 |
rodent | +0.994 |
Neg logit contributions | |
ancial | -1.044 |
culosis | -1.009 |
Klu | -0.857 |
pload | -0.840 |
ilege | -0.836 |
Token | mel |
Token ID | 17694 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
asma | +2.616 |
Hermes | +2.143 |
alion | +2.068 |
yrus | +1.994 |
ods | +1.900 |
Neg logit contributions | |
ancial | -2.954 |
culosis | -2.901 |
Klu | -2.553 |
pload | -2.480 |
orkshire | -2.461 |
Token | ny |
Token ID | 3281 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
asma | +2.958 |
Hermes | +2.243 |
alion | +2.063 |
yrus | +1.976 |
ods | +1.875 |
Neg logit contributions | |
ancial | -5.712 |
culosis | -5.576 |
Klu | -5.047 |
pload | -4.986 |
reck | -4.983 |
Token | tsky |
Token ID | 30394 |
Feature activation | -8.06e+00 |
Pos logit contributions | |
asma | +1.051 |
Hermes | +0.894 |
alion | +0.854 |
yrus | +0.825 |
rodent | +0.810 |
Neg logit contributions | |
ancial | -0.934 |
culosis | -0.901 |
Klu | -0.780 |
reck | -0.764 |
pload | -0.763 |
Token | i |
Token ID | 72 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
asma | +3.448 |
Hermes | +2.382 |
alion | +2.169 |
yrus | +1.948 |
rodent | +1.779 |
Neg logit contributions | |
ancial | -9.664 |
culosis | -9.360 |
pload | -8.496 |
Klu | -8.496 |
reck | -8.401 |
Token | - |
Token ID | 12 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
asma | +0.349 |
Hermes | +0.296 |
alion | +0.279 |
yrus | +0.268 |
rodent | +0.264 |
Neg logit contributions | |
ancial | -0.380 |
culosis | -0.369 |
Klu | -0.322 |
reck | -0.318 |
pload | -0.317 |
Token | based |
Token ID | 3106 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
asma | +2.094 |
Hermes | +1.724 |
alion | +1.622 |
yrus | +1.555 |
rodent | +1.532 |
Neg logit contributions | |
ancial | -2.636 |
culosis | -2.567 |
Klu | -2.257 |
pload | -2.235 |
ilege | -2.214 |
Token | Anat |
Token ID | 28880 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
asma | +1.406 |
Hermes | +1.232 |
alion | +1.160 |
yrus | +1.120 |
rodent | +1.117 |
Neg logit contributions | |
ancial | -1.100 |
culosis | -1.060 |
ilege | -0.885 |
pload | -0.885 |
reck | -0.883 |
Token | ol |
Token ID | 349 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
asma | +2.912 |
Hermes | +2.439 |
alion | +2.373 |
yrus | +2.263 |
ods | +2.219 |
Neg logit contributions | |
ancial | -2.748 |
culosis | -2.676 |
Klu | -2.288 |
pload | -2.259 |
ilege | -2.255 |
Token | fight |
Token ID | 1907 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
asma | +0.577 |
Hermes | +0.495 |
alion | +0.465 |
yrus | +0.449 |
rodent | +0.446 |
Neg logit contributions | |
ancial | -0.562 |
culosis | -0.544 |
Klu | -0.470 |
reck | -0.463 |
pload | -0.463 |
Token | broke |
Token ID | 6265 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
asma | +0.539 |
Hermes | +0.461 |
alion | +0.434 |
yrus | +0.416 |
rodent | +0.414 |
Neg logit contributions | |
ancial | -0.582 |
culosis | -0.566 |
Klu | -0.489 |
ilege | -0.485 |
reck | -0.483 |
Token | out |
Token ID | 503 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
asma | +0.219 |
Hermes | +0.188 |
alion | +0.178 |
yrus | +0.171 |
rodent | +0.169 |
Neg logit contributions | |
ancial | -0.206 |
culosis | -0.199 |
Klu | -0.172 |
ilege | -0.168 |
pload | -0.168 |
Token | , |
Token ID | 11 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
asma | +0.313 |
Hermes | +0.269 |
alion | +0.253 |
yrus | +0.243 |
rodent | +0.241 |
Neg logit contributions | |
ancial | -0.318 |
culosis | -0.310 |
Klu | -0.267 |
ilege | -0.263 |
pload | -0.263 |
Token | and |
Token ID | 290 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
asma | +0.442 |
Hermes | +0.380 |
alion | +0.357 |
yrus | +0.344 |
rodent | +0.341 |
Neg logit contributions | |
ancial | -0.433 |
culosis | -0.421 |
Klu | -0.361 |
pload | -0.357 |
reck | -0.357 |
Token | Spl |
Token ID | 13341 |
Feature activation | -7.96e+00 |
Pos logit contributions | |
asma | +0.397 |
Hermes | +0.336 |
alion | +0.317 |
yrus | +0.304 |
rodent | +0.300 |
Neg logit contributions | |
ancial | -0.428 |
culosis | -0.416 |
Klu | -0.363 |
reck | -0.358 |
pload | -0.357 |
Token | inter |
Token ID | 3849 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
asma | +5.757 |
Hermes | +4.389 |
alion | +4.311 |
yrus | +4.252 |
opus | +4.121 |
Neg logit contributions | |
ancial | -7.317 |
culosis | -7.239 |
Klu | -6.329 |
orkshire | -6.184 |
pload | -6.174 |
Token | 's |
Token ID | 338 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
asma | +2.949 |
Hermes | +2.522 |
alion | +2.376 |
yrus | +2.292 |
rodent | +2.265 |
Neg logit contributions | |
ancial | -3.123 |
culosis | -3.014 |
Klu | -2.592 |
reck | -2.580 |
ilege | -2.578 |
Token | cage |
Token ID | 17186 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ancial | +0.163 |
culosis | +0.159 |
Klu | +0.140 |
reck | +0.137 |
pload | +0.137 |
Neg logit contributions | |
asma | -0.140 |
Hermes | -0.118 |
alion | -0.111 |
yrus | -0.106 |
rodent | -0.104 |
Token | was |
Token ID | 373 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ancial | +0.959 |
culosis | +0.931 |
Klu | +0.813 |
reck | +0.801 |
pload | +0.799 |
Neg logit contributions | |
asma | -0.900 |
Hermes | -0.763 |
alion | -0.721 |
yrus | -0.692 |
rodent | -0.680 |
Token | broken |
Token ID | 5445 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
ancial | +0.105 |
culosis | +0.102 |
Klu | +0.088 |
reck | +0.087 |
pload | +0.087 |
Neg logit contributions | |
asma | -0.107 |
Hermes | -0.092 |
alion | -0.087 |
yrus | -0.084 |
rodent | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
asma | +0.809 |
Hermes | +0.664 |
alion | +0.619 |
yrus | +0.588 |
rodent | +0.578 |
Neg logit contributions | |
ancial | -1.161 |
culosis | -1.132 |
Klu | -1.005 |
reck | -0.992 |
pload | -0.991 |
Token |
|
Token ID | 198 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
asma | +0.279 |
Hermes | +0.231 |
alion | +0.217 |
yrus | +0.208 |
rodent | +0.204 |
Neg logit contributions | |
ancial | -0.374 |
culosis | -0.365 |
Klu | -0.327 |
reck | -0.323 |
ilege | -0.319 |
Token | Ah |
Token ID | 10910 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
asma | +0.123 |
Hermes | +0.106 |
alion | +0.101 |
yrus | +0.097 |
rodent | +0.096 |
Neg logit contributions | |
ancial | -0.113 |
culosis | -0.109 |
Klu | -0.094 |
reck | -0.093 |
pload | -0.092 |
Token | , |
Token ID | 11 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
asma | +0.196 |
Hermes | +0.167 |
alion | +0.158 |
yrus | +0.152 |
rodent | +0.150 |
Neg logit contributions | |
ancial | -0.200 |
culosis | -0.194 |
Klu | -0.169 |
reck | -0.166 |
pload | -0.166 |
Token | it |
Token ID | 340 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
asma | +2.479 |
Hermes | +2.125 |
alion | +1.961 |
yrus | +1.886 |
rodent | +1.881 |
Neg logit contributions | |
ancial | -2.853 |
culosis | -2.788 |
Klu | -2.421 |
reck | -2.405 |
pload | -2.394 |
Token | looks |
Token ID | 3073 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
asma | +1.873 |
Hermes | +1.564 |
alion | +1.482 |
yrus | +1.423 |
rodent | +1.391 |
Neg logit contributions | |
ancial | -2.165 |
culosis | -2.104 |
Klu | -1.836 |
reck | -1.823 |
pload | -1.803 |
Token | like |
Token ID | 588 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
asma | +5.319 |
Hermes | +4.408 |
alion | +4.062 |
rodent | +3.883 |
goodbye | +3.781 |
Neg logit contributions | |
ancial | -7.584 |
culosis | -7.510 |
Klu | -6.424 |
orkshire | -6.405 |
pload | -6.394 |
Token | despite |
Token ID | 3805 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
asma | +3.316 |
Hermes | +2.831 |
alion | +2.622 |
yrus | +2.521 |
rodent | +2.498 |
Neg logit contributions | |
ancial | -3.911 |
culosis | -3.835 |
Klu | -3.312 |
reck | -3.301 |
orkshire | -3.273 |
Token | the |
Token ID | 262 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ancial | +0.300 |
culosis | +0.291 |
Klu | +0.256 |
reck | +0.252 |
ilege | +0.251 |
Neg logit contributions | |
asma | -0.272 |
Hermes | -0.229 |
alion | -0.216 |
yrus | -0.207 |
rodent | -0.204 |
Token | report |
Token ID | 989 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
asma | +0.498 |
Hermes | +0.425 |
alion | +0.403 |
yrus | +0.388 |
rodent | +0.382 |
Neg logit contributions | |
ancial | -0.485 |
culosis | -0.470 |
Klu | -0.407 |
reck | -0.401 |
pload | -0.400 |
Token | that |
Token ID | 326 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
asma | +1.287 |
Hermes | +1.096 |
alion | +1.038 |
yrus | +0.998 |
rodent | +0.984 |
Neg logit contributions | |
ancial | -1.323 |
culosis | -1.285 |
Klu | -1.116 |
reck | -1.099 |
pload | -1.097 |
Token | - |
Token ID | 12 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ancial | +2.120 |
culosis | +2.049 |
Klu | +1.806 |
ement | +1.751 |
pload | +1.747 |
Neg logit contributions | |
asma | -2.934 |
Hermes | -2.549 |
alion | -2.452 |
yrus | -2.362 |
rodent | -2.301 |
Token | line |
Token ID | 1370 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
asma | +1.190 |
Hermes | +0.994 |
alion | +0.938 |
yrus | +0.899 |
rodent | +0.884 |
Neg logit contributions | |
ancial | -1.417 |
culosis | -1.375 |
Klu | -1.211 |
pload | -1.188 |
reck | -1.184 |
Token | ? |
Token ID | 30 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
asma | +0.438 |
Hermes | +0.366 |
alion | +0.343 |
yrus | +0.328 |
rodent | +0.323 |
Neg logit contributions | |
ancial | -0.547 |
culosis | -0.533 |
Klu | -0.469 |
reck | -0.463 |
pload | -0.462 |
Token | in |
Token ID | 287 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
ancial | +0.920 |
culosis | +0.893 |
Klu | +0.782 |
reck | +0.770 |
pload | +0.770 |
Neg logit contributions | |
asma | -0.830 |
Hermes | -0.700 |
alion | -0.661 |
yrus | -0.633 |
rodent | -0.625 |
Token | what |
Token ID | 644 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
ancial | +0.617 |
culosis | +0.600 |
Klu | +0.522 |
reck | +0.514 |
pload | +0.512 |
Neg logit contributions | |
asma | -0.597 |
Hermes | -0.508 |
alion | -0.480 |
yrus | -0.461 |
rodent | -0.455 |
Token | context |
Token ID | 4732 |
Feature activation | -7.89e+00 |
Pos logit contributions | |
asma | +3.412 |
Hermes | +2.908 |
alion | +2.674 |
yrus | +2.582 |
rodent | +2.566 |
Neg logit contributions | |
ancial | -4.103 |
culosis | -4.057 |
reck | -3.461 |
Klu | -3.461 |
orkshire | -3.455 |
Token | are |
Token ID | 389 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
asma | +5.720 |
Hermes | +4.878 |
alion | +4.519 |
yrus | +4.390 |
rodent | +4.359 |
Neg logit contributions | |
ancial | -6.907 |
culosis | -6.844 |
Klu | -5.811 |
reck | -5.795 |
orkshire | -5.792 |
Token | blocks |
Token ID | 7021 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
asma | +3.544 |
Hermes | +3.049 |
alion | +2.797 |
yrus | +2.722 |
rodent | +2.707 |
Neg logit contributions | |
culosis | -3.785 |
ancial | -3.785 |
reck | -3.215 |
orkshire | -3.182 |
Klu | -3.178 |
Token | normally |
Token ID | 7685 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
asma | +0.345 |
Hermes | +0.291 |
alion | +0.274 |
yrus | +0.263 |
rodent | +0.259 |
Neg logit contributions | |
ancial | -0.395 |
culosis | -0.384 |
Klu | -0.336 |
reck | -0.332 |
pload | -0.331 |
Token | used |
Token ID | 973 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
asma | +1.193 |
Hermes | +1.000 |
alion | +0.933 |
yrus | +0.896 |
rodent | +0.885 |
Neg logit contributions | |
ancial | -1.460 |
culosis | -1.426 |
Klu | -1.246 |
reck | -1.234 |
pload | -1.227 |
Token | and |
Token ID | 290 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
asma | +0.151 |
Hermes | +0.129 |
alion | +0.121 |
yrus | +0.117 |
rodent | +0.115 |
Neg logit contributions | |
ancial | -0.158 |
culosis | -0.154 |
Klu | -0.134 |
reck | -0.132 |
pload | -0.131 |
Token | to |
Token ID | 284 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
asma | +0.416 |
Hermes | +0.355 |
alion | +0.335 |
yrus | +0.322 |
rodent | +0.318 |
Neg logit contributions | |
ancial | -0.429 |
culosis | -0.416 |
Klu | -0.362 |
reck | -0.356 |
pload | -0.356 |
Token | users |
Token ID | 2985 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
asma | +0.885 |
Hermes | +0.747 |
alion | +0.700 |
yrus | +0.670 |
rodent | +0.663 |
Neg logit contributions | |
ancial | -1.049 |
culosis | -1.020 |
Klu | -0.893 |
reck | -0.885 |
pload | -0.881 |
Token | by |
Token ID | 416 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
ancial | +0.110 |
culosis | +0.107 |
Klu | +0.093 |
reck | +0.091 |
pload | +0.091 |
Neg logit contributions | |
asma | -0.114 |
Hermes | -0.098 |
alion | -0.092 |
yrus | -0.089 |
rodent | -0.088 |
Token | router |
Token ID | 20264 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
asma | +1.664 |
Hermes | +1.420 |
alion | +1.314 |
yrus | +1.260 |
rodent | +1.256 |
Neg logit contributions | |
ancial | -2.025 |
culosis | -1.979 |
reck | -1.717 |
Klu | -1.709 |
pload | -1.705 |
Token | configuration |
Token ID | 8398 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
asma | +0.839 |
Hermes | +0.709 |
alion | +0.665 |
yrus | +0.638 |
rodent | +0.629 |
Neg logit contributions | |
ancial | -0.976 |
culosis | -0.949 |
Klu | -0.831 |
reck | -0.821 |
pload | -0.818 |
Token | tools |
Token ID | 4899 |
Feature activation | -7.87e+00 |
Pos logit contributions | |
asma | +1.340 |
Hermes | +1.136 |
alion | +1.070 |
yrus | +1.022 |
rodent | +1.009 |
Neg logit contributions | |
ancial | -1.529 |
culosis | -1.489 |
Klu | -1.297 |
reck | -1.283 |
pload | -1.282 |
Token | .[ |
Token ID | 3693 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
asma | +5.720 |
Hermes | +4.905 |
alion | +4.537 |
yrus | +4.298 |
rodent | +4.241 |
Neg logit contributions | |
ancial | -7.011 |
culosis | -6.838 |
orkshire | -5.911 |
ilege | -5.900 |
pload | -5.871 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
asma | +1.878 |
Hermes | +1.612 |
alion | +1.523 |
yrus | +1.468 |
rodent | +1.457 |
Neg logit contributions | |
ancial | -1.701 |
culosis | -1.647 |
Klu | -1.413 |
pload | -1.387 |
reck | -1.385 |
Token | ][ |
Token ID | 7131 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ancial | +0.089 |
culosis | +0.086 |
Klu | +0.074 |
reck | +0.073 |
pload | +0.072 |
Neg logit contributions | |
asma | -0.107 |
Hermes | -0.093 |
alion | -0.088 |
yrus | -0.085 |
rodent | -0.084 |
Token | 3 |
Token ID | 18 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
asma | +1.991 |
Hermes | +1.697 |
alion | +1.606 |
yrus | +1.549 |
rodent | +1.527 |
Neg logit contributions | |
ancial | -1.906 |
culosis | -1.853 |
Klu | -1.596 |
pload | -1.569 |
reck | -1.559 |
Token | ] |
Token ID | 60 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ancial | +1.180 |
culosis | +1.139 |
Klu | +0.972 |
reck | +0.957 |
pload | +0.953 |
Neg logit contributions | |
asma | -1.424 |
Hermes | -1.237 |
alion | -1.175 |
yrus | -1.140 |
rodent | -1.122 |
Token | Color |
Token ID | 10258 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
ancial | +1.321 |
culosis | +1.287 |
Klu | +1.133 |
reck | +1.119 |
ilege | +1.113 |
Neg logit contributions | |
asma | -1.087 |
Hermes | -0.912 |
alion | -0.856 |
yrus | -0.818 |
rodent | -0.806 |
Token | ] |
Token ID | 60 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ancial | +0.411 |
culosis | +0.397 |
Klu | +0.340 |
reck | +0.335 |
pload | +0.334 |
Neg logit contributions | |
asma | -0.477 |
Hermes | -0.412 |
alion | -0.392 |
yrus | -0.378 |
rodent | -0.373 |
Token | :: |
Token ID | 3712 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
ancial | +2.032 |
culosis | +1.970 |
Klu | +1.720 |
reck | +1.689 |
ilege | +1.689 |
Neg logit contributions | |
asma | -1.944 |
Hermes | -1.647 |
alion | -1.563 |
yrus | -1.505 |
rodent | -1.473 |
Token | From |
Token ID | 4863 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
ancial | +0.338 |
culosis | +0.326 |
Klu | +0.276 |
reck | +0.271 |
pload | +0.270 |
Neg logit contributions | |
asma | -0.454 |
Hermes | -0.397 |
alion | -0.378 |
yrus | -0.366 |
rodent | -0.362 |
Token | Ar |
Token ID | 3163 |
Feature activation | +6.82e+00 |
Pos logit contributions | |
ancial | +3.220 |
culosis | +3.108 |
Klu | +2.642 |
Strike | +2.589 |
ilege | +2.589 |
Neg logit contributions | |
asma | -4.285 |
Hermes | -3.758 |
alion | -3.586 |
yrus | -3.482 |
rodent | -3.431 |
Token | gb |
Token ID | 22296 |
Feature activation | +8.53e+00 |
Pos logit contributions | |
ancial | +3.482 |
culosis | +3.285 |
reck | +2.619 |
Klu | +2.577 |
ement | +2.563 |
Neg logit contributions | |
asma | -7.580 |
Hermes | -6.884 |
alion | -6.583 |
rodent | -6.443 |
yrus | -6.371 |
Token | ($ |
Token ID | 16763 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ancial | +6.057 |
culosis | +5.847 |
Klu | +4.986 |
ilege | +4.967 |
Strike | +4.959 |
Neg logit contributions | |
asma | -7.530 |
Hermes | -6.540 |
alion | -6.195 |
yrus | -6.065 |
rodent | -5.985 |
Token | BG |
Token ID | 40469 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
ancial | +0.974 |
culosis | +0.946 |
Klu | +0.804 |
reck | +0.792 |
ilege | +0.788 |
Neg logit contributions | |
asma | -1.208 |
Hermes | -1.058 |
alion | -1.003 |
yrus | -0.967 |
rodent | -0.958 |
Token | [ |
Token ID | 58 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ancial | +3.114 |
culosis | +3.021 |
Klu | +2.586 |
reck | +2.539 |
ilege | +2.519 |
Neg logit contributions | |
asma | -3.846 |
Hermes | -3.335 |
alion | -3.181 |
rodent | -3.071 |
yrus | -3.060 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ancial | +2.017 |
culosis | +1.970 |
Klu | +1.667 |
ilege | +1.644 |
reck | +1.643 |
Neg logit contributions | |
asma | -2.539 |
Hermes | -2.217 |
alion | -2.119 |
yrus | -2.035 |
rodent | -2.015 |
Token | ], |
Token ID | 4357 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ancial | +0.882 |
culosis | +0.855 |
Klu | +0.730 |
reck | +0.718 |
pload | +0.717 |
Neg logit contributions | |
asma | -1.066 |
Hermes | -0.921 |
alion | -0.877 |
yrus | -0.849 |
rodent | -0.839 |
Token | 7 |
Token ID | 22 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
asma | +0.934 |
Hermes | +0.808 |
alion | +0.770 |
yrus | +0.743 |
rodent | +0.734 |
Neg logit contributions | |
ancial | -0.770 |
culosis | -0.745 |
Klu | -0.636 |
pload | -0.623 |
reck | -0.623 |
Token | . |
Token ID | 13 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ancial | +0.289 |
culosis | +0.279 |
Klu | +0.242 |
reck | +0.238 |
pload | +0.236 |
Neg logit contributions | |
asma | -0.349 |
Hermes | -0.301 |
alion | -0.288 |
yrus | -0.279 |
rodent | -0.276 |
Token | While |
Token ID | 2893 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
ancial | +1.876 |
culosis | +1.806 |
Klu | +1.584 |
pload | +1.538 |
reck | +1.536 |
Neg logit contributions | |
asma | -2.140 |
Hermes | -1.818 |
alion | -1.746 |
yrus | -1.699 |
rodent | -1.662 |
Token | we |
Token ID | 356 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
ancial | +4.866 |
culosis | +4.675 |
Klu | +4.211 |
pload | +4.018 |
ilege | +3.997 |
Neg logit contributions | |
asma | -5.539 |
Hermes | -4.674 |
alion | -4.507 |
yrus | -4.341 |
ods | -4.221 |
Token | are |
Token ID | 389 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
ancial | +3.997 |
culosis | +3.756 |
reck | +3.212 |
Klu | +3.208 |
pload | +3.173 |
Neg logit contributions | |
asma | -5.115 |
Hermes | -4.498 |
alion | -4.223 |
yrus | -4.132 |
rodent | -4.023 |
Token | waiting |
Token ID | 4953 |
Feature activation | +8.53e+00 |
Pos logit contributions | |
ancial | +4.763 |
culosis | +4.550 |
Klu | +4.080 |
reck | +3.962 |
pload | +3.901 |
Neg logit contributions | |
asma | -5.512 |
Hermes | -4.733 |
alion | -4.503 |
yrus | -4.363 |
ods | -4.210 |
Token | for |
Token ID | 329 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
ancial | +5.866 |
culosis | +5.496 |
Klu | +4.838 |
pload | +4.686 |
ement | +4.686 |
Neg logit contributions | |
asma | -7.748 |
Hermes | -6.672 |
alion | -6.435 |
yrus | -6.208 |
rodent | -6.000 |
Token | the |
Token ID | 262 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
ancial | +3.792 |
culosis | +3.615 |
Klu | +3.258 |
ement | +3.103 |
pload | +3.086 |
Neg logit contributions | |
asma | -3.896 |
Hermes | -3.253 |
alion | -3.152 |
yrus | -3.061 |
ods | -2.906 |
Token | curry |
Token ID | 34611 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ancial | +3.737 |
culosis | +3.593 |
Klu | +3.273 |
reck | +3.153 |
pload | +3.150 |
Neg logit contributions | |
asma | -2.760 |
Hermes | -2.236 |
alion | -2.178 |
yrus | -2.057 |
ods | -1.940 |
Token | mix |
Token ID | 5022 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ancial | +0.105 |
culosis | +0.101 |
Klu | +0.085 |
reck | +0.084 |
pload | +0.083 |
Neg logit contributions | |
asma | -0.139 |
Hermes | -0.122 |
alion | -0.116 |
yrus | -0.112 |
rodent | -0.111 |
Token | to |
Token ID | 284 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
ancial | +2.124 |
culosis | +2.054 |
Klu | +1.786 |
reck | +1.748 |
pload | +1.744 |
Neg logit contributions | |
asma | -2.211 |
Hermes | -1.893 |
alion | -1.793 |
yrus | -1.724 |
rodent | -1.702 |
Token | can |
Token ID | 460 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ancial | +1.613 |
culosis | +1.567 |
Klu | +1.360 |
reck | +1.343 |
ilege | +1.332 |
Neg logit contributions | |
asma | -1.649 |
Hermes | -1.406 |
alion | -1.345 |
yrus | -1.283 |
rodent | -1.254 |
Token | go |
Token ID | 467 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ancial | +0.915 |
culosis | +0.891 |
Klu | +0.779 |
reck | +0.767 |
ilege | +0.766 |
Neg logit contributions | |
asma | -0.844 |
Hermes | -0.713 |
alion | -0.675 |
yrus | -0.645 |
rodent | -0.632 |
Token | into |
Token ID | 656 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
ancial | +0.214 |
culosis | +0.207 |
Klu | +0.179 |
reck | +0.177 |
pload | +0.177 |
Neg logit contributions | |
asma | -0.207 |
Hermes | -0.177 |
alion | -0.166 |
yrus | -0.160 |
rodent | -0.159 |
Token | the |
Token ID | 262 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
asma | +0.749 |
Hermes | +0.637 |
alion | +0.591 |
yrus | +0.571 |
rodent | +0.568 |
Neg logit contributions | |
ancial | -0.834 |
culosis | -0.807 |
Klu | -0.701 |
pload | -0.699 |
reck | -0.696 |
Token | women |
Token ID | 1466 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
ancial | +0.761 |
culosis | +0.741 |
Klu | +0.642 |
reck | +0.628 |
pload | +0.623 |
Neg logit contributions | |
asma | -0.834 |
Hermes | -0.714 |
alion | -0.683 |
yrus | -0.657 |
rodent | -0.644 |
Token | 's |
Token ID | 338 |
Feature activation | +7.98e+00 |
Pos logit contributions | |
ancial | +0.551 |
culosis | +0.533 |
Klu | +0.453 |
reck | +0.446 |
pload | +0.445 |
Neg logit contributions | |
asma | -0.677 |
Hermes | -0.586 |
alion | -0.558 |
yrus | -0.539 |
rodent | -0.533 |
Token | restroom |
Token ID | 40018 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ancial | +5.165 |
culosis | +5.040 |
Klu | +4.438 |
reck | +4.263 |
ement | +4.241 |
Neg logit contributions | |
asma | -7.422 |
Hermes | -6.407 |
alion | -6.389 |
yrus | -6.207 |
opus | -5.904 |
Token | , |
Token ID | 11 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
ancial | +2.235 |
culosis | +2.164 |
Klu | +1.885 |
reck | +1.855 |
ilege | +1.841 |
Neg logit contributions | |
asma | -2.456 |
Hermes | -2.091 |
alion | -1.996 |
yrus | -1.924 |
rodent | -1.874 |
Token | that |
Token ID | 326 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ancial | +0.076 |
culosis | +0.074 |
Klu | +0.064 |
reck | +0.063 |
pload | +0.063 |
Neg logit contributions | |
asma | -0.070 |
Hermes | -0.060 |
alion | -0.056 |
yrus | -0.054 |
rodent | -0.053 |
Token | 's |
Token ID | 338 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
ancial | +0.335 |
culosis | +0.324 |
Klu | +0.278 |
reck | +0.274 |
pload | +0.274 |
Neg logit contributions | |
asma | -0.372 |
Hermes | -0.320 |
alion | -0.304 |
yrus | -0.293 |
rodent | -0.290 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
asma | +0.620 |
Hermes | +0.525 |
alion | +0.491 |
yrus | +0.471 |
rodent | +0.470 |
Neg logit contributions | |
ancial | -0.717 |
culosis | -0.698 |
Klu | -0.603 |
pload | -0.602 |
reck | -0.598 |
Token | it |
Token ID | 340 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
ancial | +0.693 |
culosis | +0.674 |
Klu | +0.599 |
reck | +0.588 |
pload | +0.585 |
Neg logit contributions | |
asma | -0.559 |
Hermes | -0.463 |
alion | -0.438 |
yrus | -0.418 |
rodent | -0.409 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
ancial | +0.338 |
culosis | +0.328 |
Klu | +0.284 |
reck | +0.280 |
pload | +0.279 |
Neg logit contributions | |
asma | -0.350 |
Hermes | -0.300 |
alion | -0.284 |
yrus | -0.273 |
rodent | -0.270 |
Token | The |
Token ID | 383 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
asma | +0.320 |
Hermes | +0.272 |
alion | +0.256 |
yrus | +0.245 |
rodent | +0.242 |
Neg logit contributions | |
ancial | -0.347 |
culosis | -0.336 |
Klu | -0.292 |
reck | -0.289 |
pload | -0.289 |
Token | " |
Token ID | 366 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
ancial | +0.144 |
culosis | +0.140 |
Klu | +0.122 |
reck | +0.120 |
pload | +0.120 |
Neg logit contributions | |
asma | -0.141 |
Hermes | -0.120 |
alion | -0.113 |
yrus | -0.109 |
rodent | -0.107 |
Token | land |
Token ID | 1044 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
ancial | +0.614 |
culosis | +0.596 |
Klu | +0.512 |
reck | +0.506 |
pload | +0.502 |
Neg logit contributions | |
asma | -0.681 |
Hermes | -0.585 |
alion | -0.556 |
yrus | -0.535 |
rodent | -0.529 |
Token | of |
Token ID | 286 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
ancial | +0.530 |
culosis | +0.513 |
Klu | +0.442 |
reck | +0.435 |
pload | +0.434 |
Neg logit contributions | |
asma | -0.579 |
Hermes | -0.497 |
alion | -0.472 |
yrus | -0.455 |
rodent | -0.449 |
Token | the |
Token ID | 262 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
ancial | +5.915 |
culosis | +5.750 |
Klu | +5.329 |
reck | +5.061 |
ilege | +5.054 |
Neg logit contributions | |
asma | -6.000 |
alion | -4.940 |
Hermes | -4.839 |
yrus | -4.704 |
opus | -4.480 |
Token | free |
Token ID | 1479 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ancial | +3.410 |
culosis | +3.298 |
Klu | +2.970 |
reck | +2.846 |
pload | +2.806 |
Neg logit contributions | |
asma | -4.207 |
Hermes | -3.595 |
alion | -3.512 |
yrus | -3.345 |
rodent | -3.204 |
Token | " |
Token ID | 1 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
ancial | +1.618 |
culosis | +1.574 |
Klu | +1.384 |
reck | +1.360 |
ilege | +1.352 |
Neg logit contributions | |
asma | -1.479 |
Hermes | -1.251 |
alion | -1.182 |
yrus | -1.134 |
rodent | -1.110 |
Token | is |
Token ID | 318 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
asma | +0.699 |
Hermes | +0.594 |
alion | +0.558 |
yrus | +0.536 |
rodent | +0.530 |
Neg logit contributions | |
ancial | -0.767 |
culosis | -0.744 |
Klu | -0.646 |
reck | -0.639 |
pload | -0.639 |
Token | home |
Token ID | 1363 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ancial | +0.385 |
culosis | +0.374 |
Klu | +0.326 |
reck | +0.321 |
pload | +0.321 |
Neg logit contributions | |
asma | -0.352 |
Hermes | -0.298 |
alion | -0.281 |
yrus | -0.270 |
rodent | -0.266 |
Token | . |
Token ID | 13 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
ancial | +2.051 |
culosis | +1.970 |
Klu | +1.716 |
pload | +1.693 |
reck | +1.686 |
Neg logit contributions | |
asma | -2.238 |
Hermes | -1.913 |
alion | -1.823 |
yrus | -1.749 |
rodent | -1.736 |
Token | Instead |
Token ID | 5455 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
asma | +0.750 |
Hermes | +0.635 |
alion | +0.593 |
yrus | +0.570 |
rodent | +0.560 |
Neg logit contributions | |
ancial | -0.859 |
culosis | -0.833 |
Klu | -0.729 |
reck | -0.720 |
pload | -0.718 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
asma | +1.270 |
Hermes | +1.085 |
alion | +1.023 |
yrus | +0.986 |
rodent | +0.971 |
Neg logit contributions | |
ancial | -1.304 |
culosis | -1.267 |
Klu | -1.098 |
reck | -1.081 |
pload | -1.077 |
Token | use |
Token ID | 779 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
ancial | +0.171 |
culosis | +0.166 |
Klu | +0.144 |
pload | +0.142 |
reck | +0.142 |
Neg logit contributions | |
asma | -0.178 |
Hermes | -0.151 |
alion | -0.145 |
yrus | -0.138 |
rodent | -0.136 |
Token | the |
Token ID | 262 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
ancial | +0.438 |
culosis | +0.425 |
Klu | +0.374 |
reck | +0.368 |
pload | +0.368 |
Neg logit contributions | |
asma | -0.378 |
Hermes | -0.317 |
alion | -0.300 |
yrus | -0.286 |
rodent | -0.282 |
Token | ng |
Token ID | 23370 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
ancial | +0.551 |
culosis | +0.536 |
Klu | +0.473 |
reck | +0.467 |
pload | +0.466 |
Neg logit contributions | |
asma | -0.435 |
Hermes | -0.362 |
alion | -0.340 |
yrus | -0.325 |
rodent | -0.319 |
Token | - |
Token ID | 12 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
ancial | +5.350 |
culosis | +5.121 |
pload | +4.421 |
Klu | +4.358 |
ement | +4.324 |
Neg logit contributions | |
asma | -6.754 |
Hermes | -5.853 |
alion | -5.712 |
yrus | -5.372 |
rodent | -5.287 |
Token | bind |
Token ID | 21653 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
ancial | +2.210 |
culosis | +2.144 |
reck | +1.888 |
Klu | +1.884 |
pload | +1.878 |
Neg logit contributions | |
asma | -1.692 |
Hermes | -1.408 |
alion | -1.321 |
yrus | -1.252 |
rodent | -1.236 |
Token | directive |
Token ID | 22644 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
ancial | +3.043 |
culosis | +2.934 |
Klu | +2.549 |
ilege | +2.520 |
pload | +2.518 |
Neg logit contributions | |
asma | -3.038 |
Hermes | -2.574 |
alion | -2.453 |
yrus | -2.350 |
rodent | -2.318 |
Token | : |
Token ID | 25 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
ancial | +2.396 |
culosis | +2.304 |
Klu | +2.015 |
pload | +1.987 |
reck | +1.980 |
Neg logit contributions | |
asma | -2.476 |
Hermes | -2.100 |
alion | -2.008 |
yrus | -1.923 |
rodent | -1.894 |
Token |
|
Token ID | 198 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
ancial | +0.887 |
culosis | +0.859 |
Klu | +0.762 |
pload | +0.756 |
reck | +0.751 |
Neg logit contributions | |
asma | -0.671 |
Hermes | -0.551 |
alion | -0.520 |
yrus | -0.491 |
rodent | -0.486 |
Token | o |
Token ID | 78 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
asma | +2.850 |
Hermes | +2.374 |
alion | +2.274 |
yrus | +2.190 |
opus | +2.144 |
Neg logit contributions | |
ancial | -3.504 |
culosis | -3.383 |
Klu | -2.993 |
pload | -2.969 |
orkshire | -2.948 |
Token | vert |
Token ID | 1851 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
asma | +2.024 |
Hermes | +1.718 |
alion | +1.645 |
yrus | +1.577 |
rodent | +1.543 |
Neg logit contributions | |
ancial | -2.134 |
culosis | -2.078 |
Klu | -1.814 |
pload | -1.771 |
reck | -1.763 |
Token | ime |
Token ID | 524 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
ancial | +0.297 |
culosis | +0.291 |
Klu | +0.251 |
pload | +0.249 |
orkshire | +0.246 |
Neg logit contributions | |
asma | -0.294 |
Hermes | -0.249 |
alion | -0.237 |
yrus | -0.228 |
rodent | -0.225 |
Token | goal |
Token ID | 3061 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
asma | +0.407 |
Hermes | +0.341 |
alion | +0.322 |
yrus | +0.308 |
rodent | +0.304 |
Neg logit contributions | |
ancial | -0.484 |
culosis | -0.470 |
Klu | -0.412 |
pload | -0.406 |
reck | -0.406 |
Token | clin |
Token ID | 5327 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
ancial | +0.157 |
culosis | +0.152 |
Klu | +0.132 |
reck | +0.130 |
pload | +0.129 |
Neg logit contributions | |
asma | -0.161 |
Hermes | -0.138 |
alion | -0.131 |
yrus | -0.126 |
rodent | -0.124 |
Token | ched |
Token ID | 1740 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ancial | +0.803 |
culosis | +0.776 |
Klu | +0.667 |
ilege | +0.667 |
reck | +0.664 |
Neg logit contributions | |
asma | -0.815 |
Hermes | -0.705 |
alion | -0.655 |
rodent | -0.634 |
yrus | -0.630 |
Token | New |
Token ID | 968 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ancial | +1.107 |
culosis | +1.068 |
Klu | +0.937 |
reck | +0.919 |
pload | +0.915 |
Neg logit contributions | |
asma | -1.079 |
Hermes | -0.917 |
alion | -0.866 |
yrus | -0.833 |
rodent | -0.819 |
Token | Jersey |
Token ID | 8221 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ancial | +1.100 |
culosis | +1.044 |
Klu | +0.819 |
reck | +0.806 |
pload | +0.784 |
Neg logit contributions | |
asma | -2.438 |
Hermes | -2.180 |
alion | -2.082 |
yrus | -2.041 |
rodent | -2.025 |
Token | � |
Token ID | 447 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ancial | +1.299 |
culosis | +1.251 |
Klu | +1.081 |
reck | +1.062 |
pload | +1.058 |
Neg logit contributions | |
asma | -1.430 |
Hermes | -1.234 |
alion | -1.168 |
yrus | -1.128 |
rodent | -1.110 |
Token | � |
Token ID | 247 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ancial | +2.004 |
culosis | +1.946 |
Klu | +1.796 |
reck | +1.786 |
ilege | +1.772 |
Neg logit contributions | |
asma | -0.840 |
Hermes | -0.639 |
alion | -0.555 |
yrus | -0.520 |
rodent | -0.507 |
Token | s |
Token ID | 82 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
asma | +0.139 |
Hermes | +0.118 |
alion | +0.111 |
yrus | +0.107 |
rodent | +0.106 |
Neg logit contributions | |
ancial | -0.148 |
culosis | -0.145 |
Klu | -0.126 |
pload | -0.125 |
reck | -0.124 |
Token | were |
Token ID | 547 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
asma | +0.347 |
Hermes | +0.296 |
alion | +0.280 |
yrus | +0.269 |
rodent | +0.266 |
Neg logit contributions | |
ancial | -0.351 |
culosis | -0.341 |
Klu | -0.295 |
pload | -0.290 |
reck | -0.290 |
Token | ; |
Token ID | 26 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ancial | +1.755 |
culosis | +1.699 |
Klu | +1.477 |
reck | +1.453 |
pload | +1.446 |
Neg logit contributions | |
asma | -1.868 |
Hermes | -1.599 |
alion | -1.521 |
yrus | -1.462 |
rodent | -1.436 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ancial | +2.087 |
culosis | +2.023 |
Klu | +1.773 |
reck | +1.740 |
pload | +1.734 |
Neg logit contributions | |
asma | -2.032 |
Hermes | -1.725 |
alion | -1.635 |
yrus | -1.573 |
rodent | -1.543 |
Token | older |
Token ID | 4697 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ancial | +0.112 |
culosis | +0.109 |
Klu | +0.094 |
reck | +0.093 |
pload | +0.093 |
Neg logit contributions | |
asma | -0.108 |
Hermes | -0.092 |
alion | -0.087 |
yrus | -0.083 |
rodent | -0.082 |
Token | generation |
Token ID | 5270 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
asma | +0.972 |
Hermes | +0.824 |
alion | +0.773 |
yrus | +0.740 |
rodent | +0.740 |
Neg logit contributions | |
ancial | -1.083 |
culosis | -1.055 |
Klu | -0.911 |
reck | -0.904 |
pload | -0.904 |
Token | 's |
Token ID | 338 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
asma | +1.306 |
Hermes | +1.113 |
alion | +1.039 |
rodent | +1.001 |
yrus | +0.997 |
Neg logit contributions | |
ancial | -1.450 |
culosis | -1.408 |
Klu | -1.219 |
pload | -1.209 |
reck | -1.205 |
Token | rejection |
Token ID | 17927 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ancial | +1.963 |
culosis | +1.900 |
Klu | +1.664 |
reck | +1.639 |
ilege | +1.623 |
Neg logit contributions | |
asma | -1.947 |
Hermes | -1.655 |
alion | -1.575 |
yrus | -1.517 |
rodent | -1.471 |
Token | of |
Token ID | 286 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
ancial | +0.941 |
culosis | +0.912 |
Klu | +0.789 |
reck | +0.777 |
pload | +0.774 |
Neg logit contributions | |
asma | -0.985 |
Hermes | -0.843 |
alion | -0.798 |
yrus | -0.769 |
rodent | -0.758 |
Token | new |
Token ID | 649 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
ancial | +0.481 |
culosis | +0.467 |
Klu | +0.406 |
reck | +0.399 |
pload | +0.399 |
Neg logit contributions | |
asma | -0.469 |
Hermes | -0.399 |
alion | -0.378 |
yrus | -0.363 |
rodent | -0.358 |
Token | generation |
Token ID | 5270 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
ancial | +0.474 |
culosis | +0.460 |
Klu | +0.398 |
reck | +0.392 |
pload | +0.391 |
Neg logit contributions | |
asma | -0.481 |
Hermes | -0.411 |
alion | -0.389 |
yrus | -0.374 |
rodent | -0.369 |
Token | 's |
Token ID | 338 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
asma | +0.673 |
Hermes | +0.574 |
alion | +0.542 |
yrus | +0.520 |
rodent | +0.518 |
Neg logit contributions | |
ancial | -0.690 |
culosis | -0.669 |
Klu | -0.579 |
pload | -0.571 |
reck | -0.569 |
Token | comfortable |
Token ID | 6792 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
asma | +2.738 |
Hermes | +2.423 |
alion | +2.258 |
rodent | +2.207 |
yrus | +2.143 |
Neg logit contributions | |
ancial | -2.546 |
culosis | -2.468 |
Klu | -2.089 |
pload | -2.057 |
orkshire | -2.053 |
Token | . |
Token ID | 13 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
ancial | +0.216 |
culosis | +0.210 |
Klu | +0.181 |
reck | +0.178 |
pload | +0.178 |
Neg logit contributions | |
asma | -0.230 |
Hermes | -0.197 |
alion | -0.187 |
yrus | -0.180 |
rodent | -0.178 |
Token |
|
Token ID | 198 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
ancial | +0.423 |
culosis | +0.411 |
Klu | +0.362 |
reck | +0.355 |
pload | +0.355 |
Neg logit contributions | |
asma | -0.367 |
Hermes | -0.308 |
alion | -0.291 |
yrus | -0.280 |
rodent | -0.275 |
Token |
|
Token ID | 198 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
asma | +0.057 |
Hermes | +0.047 |
alion | +0.045 |
yrus | +0.043 |
rodent | +0.042 |
Neg logit contributions | |
ancial | -0.074 |
culosis | -0.072 |
Klu | -0.065 |
reck | -0.064 |
ilege | -0.063 |
Token | The |
Token ID | 464 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ancial | +0.435 |
culosis | +0.421 |
Klu | +0.360 |
reck | +0.354 |
pload | +0.353 |
Neg logit contributions | |
asma | -0.519 |
Hermes | -0.449 |
alion | -0.427 |
yrus | -0.413 |
rodent | -0.408 |
Token | shorts |
Token ID | 22078 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ancial | +0.868 |
culosis | +0.843 |
Klu | +0.738 |
reck | +0.724 |
pload | +0.721 |
Neg logit contributions | |
asma | -0.839 |
Hermes | -0.710 |
alion | -0.675 |
yrus | -0.648 |
rodent | -0.637 |
Token | are |
Token ID | 389 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ancial | +2.330 |
culosis | +2.261 |
Klu | +1.965 |
reck | +1.919 |
pload | +1.918 |
Neg logit contributions | |
asma | -2.540 |
Hermes | -2.171 |
alion | -2.074 |
yrus | -1.999 |
rodent | -1.960 |
Token | modeled |
Token ID | 29563 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
asma | +0.411 |
Hermes | +0.352 |
alion | +0.329 |
yrus | +0.315 |
rodent | +0.315 |
Neg logit contributions | |
ancial | -0.442 |
culosis | -0.430 |
Klu | -0.371 |
reck | -0.369 |
pload | -0.368 |
Token | on |
Token ID | 319 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
asma | +0.483 |
Hermes | +0.402 |
alion | +0.377 |
yrus | +0.361 |
rodent | +0.355 |
Neg logit contributions | |
ancial | -0.614 |
culosis | -0.597 |
Klu | -0.527 |
reck | -0.520 |
pload | -0.519 |
Token | the |
Token ID | 262 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ancial | +1.101 |
culosis | +1.066 |
Klu | +0.935 |
reck | +0.916 |
pload | +0.913 |
Neg logit contributions | |
asma | -1.056 |
Hermes | -0.891 |
alion | -0.850 |
yrus | -0.816 |
rodent | -0.800 |
Token | Body |
Token ID | 12290 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
ancial | +1.007 |
culosis | +0.976 |
Klu | +0.856 |
reck | +0.840 |
pload | +0.835 |
Neg logit contributions | |
asma | -0.965 |
Hermes | -0.814 |
alion | -0.777 |
yrus | -0.745 |
rodent | -0.731 |
Token | View |
Token ID | 7680 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
asma | +1.328 |
Hermes | +1.141 |
alion | +1.090 |
yrus | +1.049 |
rodent | +1.037 |
Neg logit contributions | |
ancial | -1.140 |
culosis | -1.096 |
Klu | -0.941 |
pload | -0.924 |
ilege | -0.917 |
Token | Images |
Token ID | 5382 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
asma | +0.993 |
Hermes | +0.808 |
alion | +0.753 |
yrus | +0.714 |
rodent | +0.701 |
Neg logit contributions | |
ancial | -1.499 |
culosis | -1.462 |
Klu | -1.304 |
reck | -1.285 |
pload | -1.283 |
Token | This |
Token ID | 770 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
asma | +1.748 |
Hermes | +1.485 |
alion | +1.373 |
yrus | +1.317 |
rodent | +1.308 |
Neg logit contributions | |
ancial | -1.999 |
culosis | -1.934 |
Klu | -1.689 |
pload | -1.678 |
ilege | -1.677 |
Token | aerial |
Token ID | 17789 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
asma | +0.240 |
Hermes | +0.202 |
alion | +0.191 |
yrus | +0.183 |
rodent | +0.180 |
Neg logit contributions | |
ancial | -0.269 |
culosis | -0.261 |
Klu | -0.228 |
reck | -0.225 |
pload | -0.225 |
Token | photograph |
Token ID | 8408 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
asma | +2.212 |
Hermes | +1.913 |
alion | +1.803 |
rodent | +1.748 |
yrus | +1.729 |
Neg logit contributions | |
ancial | -1.881 |
culosis | -1.804 |
Klu | -1.539 |
pload | -1.528 |
ilege | -1.514 |
Token | of |
Token ID | 286 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
asma | +0.606 |
Hermes | +0.512 |
alion | +0.480 |
yrus | +0.461 |
rodent | +0.456 |
Neg logit contributions | |
ancial | -0.701 |
culosis | -0.681 |
Klu | -0.593 |
pload | -0.586 |
reck | -0.585 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ancial | +1.074 |
culosis | +1.042 |
Klu | +0.912 |
reck | +0.897 |
pload | +0.890 |
Neg logit contributions | |
asma | -1.034 |
Hermes | -0.876 |
alion | -0.834 |
yrus | -0.799 |
rodent | -0.783 |
Token | Sund |
Token ID | 3309 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
asma | +0.089 |
Hermes | +0.077 |
alion | +0.073 |
yrus | +0.070 |
rodent | +0.070 |
Neg logit contributions | |
ancial | -0.081 |
culosis | -0.078 |
Klu | -0.067 |
pload | -0.066 |
reck | -0.066 |
Token | arb |
Token ID | 38039 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
asma | +2.588 |
Hermes | +2.304 |
alion | +2.227 |
yrus | +2.177 |
rodent | +2.142 |
Neg logit contributions | |
ancial | -1.090 |
culosis | -1.034 |
Klu | -0.805 |
pload | -0.776 |
reck | -0.767 |
Token | ans |
Token ID | 504 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
asma | +1.981 |
Hermes | +1.591 |
alion | +1.472 |
yrus | +1.392 |
rodent | +1.360 |
Neg logit contributions | |
ancial | -3.287 |
culosis | -3.208 |
Klu | -2.872 |
reck | -2.834 |
pload | -2.832 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
asma | +2.111 |
Hermes | +1.788 |
alion | +1.671 |
yrus | +1.604 |
rodent | +1.603 |
Neg logit contributions | |
ancial | -2.379 |
culosis | -2.297 |
Klu | -1.992 |
pload | -1.982 |
ilege | -1.980 |
Token | at |
Token ID | 379 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ancial | +1.224 |
culosis | +1.180 |
Klu | +0.991 |
reck | +0.970 |
pload | +0.962 |
Neg logit contributions | |
asma | -1.764 |
Hermes | -1.543 |
alion | -1.479 |
yrus | -1.432 |
rodent | -1.415 |
Token | I |
Token ID | 314 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ancial | +1.687 |
culosis | +1.628 |
Klu | +1.419 |
reck | +1.385 |
ilege | +1.371 |
Neg logit contributions | |
asma | -1.823 |
Hermes | -1.547 |
alion | -1.490 |
yrus | -1.431 |
rodent | -1.407 |
Token | HS |
Token ID | 7998 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ancial | +1.071 |
culosis | +1.036 |
Klu | +0.894 |
pload | +0.880 |
reck | +0.878 |
Neg logit contributions | |
asma | -1.119 |
Hermes | -0.959 |
alion | -0.904 |
yrus | -0.873 |
rodent | -0.859 |
Token | Global |
Token ID | 8060 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
asma | +1.849 |
Hermes | +1.624 |
alion | +1.478 |
yrus | +1.449 |
rodent | +1.430 |
Neg logit contributions | |
ancial | -1.642 |
culosis | -1.592 |
pload | -1.366 |
Klu | -1.355 |
ilege | -1.349 |
Token | Insight |
Token ID | 39917 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
asma | +0.913 |
Hermes | +0.799 |
alion | +0.747 |
yrus | +0.717 |
rodent | +0.712 |
Neg logit contributions | |
ancial | -0.717 |
culosis | -0.689 |
Klu | -0.592 |
pload | -0.592 |
reck | -0.586 |
Token | , |
Token ID | 11 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ancial | +0.085 |
culosis | +0.083 |
Klu | +0.072 |
pload | +0.071 |
reck | +0.071 |
Neg logit contributions | |
asma | -0.085 |
Hermes | -0.072 |
alion | -0.068 |
yrus | -0.065 |
rodent | -0.065 |
Token | said |
Token ID | 531 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ancial | +1.846 |
culosis | +1.785 |
Klu | +1.553 |
reck | +1.515 |
pload | +1.500 |
Neg logit contributions | |
asma | -2.082 |
Hermes | -1.780 |
alion | -1.718 |
yrus | -1.643 |
rodent | -1.621 |
Token | it |
Token ID | 340 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ancial | +1.227 |
culosis | +1.188 |
Klu | +1.047 |
reck | +1.029 |
pload | +1.027 |
Neg logit contributions | |
asma | -1.086 |
Hermes | -0.911 |
alion | -0.865 |
yrus | -0.828 |
rodent | -0.811 |
Token | was |
Token ID | 373 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
asma | +0.319 |
Hermes | +0.267 |
alion | +0.251 |
yrus | +0.240 |
rodent | +0.237 |
Neg logit contributions | |
ancial | -0.381 |
culosis | -0.370 |
Klu | -0.325 |
reck | -0.321 |
pload | -0.320 |
Token | no |
Token ID | 645 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ancial | +0.367 |
culosis | +0.357 |
Klu | +0.314 |
reck | +0.310 |
pload | +0.309 |
Neg logit contributions | |
asma | -0.302 |
Hermes | -0.253 |
alion | -0.238 |
yrus | -0.228 |
rodent | -0.224 |
Token | surprise |
Token ID | 5975 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
asma | +2.712 |
Hermes | +2.356 |
alion | +2.174 |
rodent | +2.127 |
yrus | +2.110 |
Neg logit contributions | |
ancial | -2.591 |
culosis | -2.507 |
Klu | -2.140 |
reck | -2.140 |
ilege | -2.123 |
Token | i |
Token ID | 1312 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
asma | +0.813 |
Hermes | +0.679 |
alion | +0.636 |
yrus | +0.608 |
rodent | +0.598 |
Neg logit contributions | |
ancial | -1.015 |
culosis | -0.987 |
Klu | -0.868 |
reck | -0.856 |
pload | -0.855 |
Token | n |
Token ID | 299 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
asma | +2.634 |
Hermes | +2.197 |
alion | +2.043 |
yrus | +1.953 |
rodent | +1.918 |
Neg logit contributions | |
ancial | -3.257 |
culosis | -3.147 |
Klu | -2.731 |
ilege | -2.712 |
reck | -2.708 |
Token | ā |
Token ID | 10235 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
asma | +1.766 |
Hermes | +1.464 |
alion | +1.387 |
yrus | +1.326 |
rodent | +1.288 |
Neg logit contributions | |
ancial | -2.058 |
culosis | -2.003 |
Klu | -1.755 |
pload | -1.728 |
reck | -1.723 |
Token | ke |
Token ID | 885 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
asma | +1.394 |
Hermes | +1.169 |
alion | +1.097 |
yrus | +1.050 |
rodent | +1.033 |
Neg logit contributions | |
ancial | -1.663 |
culosis | -1.615 |
Klu | -1.412 |
reck | -1.394 |
pload | -1.394 |
Token | iki |
Token ID | 5580 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
ancial | +0.422 |
culosis | +0.412 |
Klu | +0.368 |
reck | +0.361 |
pload | +0.360 |
Neg logit contributions | |
asma | -0.324 |
Hermes | -0.270 |
alion | -0.253 |
yrus | -0.242 |
rodent | -0.239 |
Token | ho |
Token ID | 8169 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
asma | +0.707 |
Hermes | +0.590 |
alion | +0.553 |
yrus | +0.529 |
rodent | +0.520 |
Neg logit contributions | |
ancial | -0.890 |
culosis | -0.866 |
Klu | -0.764 |
reck | -0.753 |
pload | -0.752 |
Token | � |
Token ID | 134 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
asma | +2.696 |
Hermes | +2.326 |
alion | +2.208 |
yrus | +2.136 |
rodent | +2.106 |
Neg logit contributions | |
ancial | -2.179 |
culosis | -2.097 |
Klu | -1.764 |
pload | -1.742 |
reck | -1.742 |
Token | � |
Token ID | 119 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
asma | +0.669 |
Hermes | +0.542 |
alion | +0.500 |
yrus | +0.476 |
rodent | +0.467 |
Neg logit contributions | |
ancial | -1.034 |
culosis | -1.008 |
Klu | -0.898 |
reck | -0.885 |
pload | -0.885 |
Token | op |
Token ID | 404 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
asma | +2.813 |
Hermes | +2.334 |
alion | +2.234 |
yrus | +2.137 |
ods | +2.078 |
Neg logit contributions | |
ancial | -3.064 |
culosis | -2.979 |
Klu | -2.585 |
pload | -2.538 |
reck | -2.526 |
Token | ā |
Token ID | 10235 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
asma | +3.837 |
Hermes | +3.224 |
alion | +3.105 |
yrus | +2.991 |
rodent | +2.895 |
Neg logit contributions | |
ancial | -3.495 |
culosis | -3.386 |
Klu | -2.907 |
pload | -2.875 |
orkshire | -2.836 |
Token | p |
Token ID | 79 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
asma | +1.319 |
Hermes | +1.113 |
alion | +1.051 |
yrus | +1.008 |
rodent | +0.992 |
Neg logit contributions | |
ancial | -1.452 |
culosis | -1.408 |
Klu | -1.228 |
reck | -1.209 |
pload | -1.208 |
Token | against |
Token ID | 1028 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
asma | +2.975 |
Hermes | +2.517 |
alion | +2.374 |
yrus | +2.246 |
rodent | +2.241 |
Neg logit contributions | |
ancial | -3.269 |
culosis | -3.172 |
pload | -2.759 |
Klu | -2.752 |
orkshire | -2.744 |
Token | the |
Token ID | 262 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
asma | +0.678 |
Hermes | +0.575 |
alion | +0.542 |
yrus | +0.518 |
rodent | +0.511 |
Neg logit contributions | |
ancial | -0.754 |
culosis | -0.733 |
Klu | -0.639 |
reck | -0.632 |
pload | -0.632 |
Token | coalition |
Token ID | 9906 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
asma | +0.103 |
Hermes | +0.087 |
alion | +0.082 |
yrus | +0.078 |
rodent | +0.077 |
Neg logit contributions | |
ancial | -0.118 |
culosis | -0.115 |
Klu | -0.101 |
reck | -0.099 |
pload | -0.099 |
Token | since |
Token ID | 1201 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
asma | +3.576 |
Hermes | +3.055 |
alion | +2.869 |
rodent | +2.725 |
yrus | +2.704 |
Neg logit contributions | |
ancial | -4.041 |
culosis | -3.941 |
pload | -3.433 |
Klu | -3.424 |
orkshire | -3.415 |
Token | it |
Token ID | 340 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
ancial | +0.621 |
culosis | +0.604 |
Klu | +0.525 |
reck | +0.517 |
pload | +0.517 |
Neg logit contributions | |
asma | -0.586 |
Hermes | -0.498 |
alion | -0.469 |
yrus | -0.450 |
rodent | -0.445 |
Token | began |
Token ID | 2540 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
ancial | +0.374 |
culosis | +0.362 |
Klu | +0.315 |
reck | +0.311 |
pload | +0.309 |
Neg logit contributions | |
asma | -0.372 |
Hermes | -0.318 |
alion | -0.301 |
yrus | -0.290 |
rodent | -0.285 |
Token | its |
Token ID | 663 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ancial | +0.036 |
culosis | +0.035 |
Klu | +0.030 |
pload | +0.030 |
reck | +0.030 |
Neg logit contributions | |
asma | -0.035 |
Hermes | -0.030 |
alion | -0.029 |
yrus | -0.027 |
rodent | -0.027 |
Token | campaign |
Token ID | 1923 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
asma | +2.177 |
Hermes | +1.873 |
alion | +1.760 |
rodent | +1.709 |
yrus | +1.689 |
Neg logit contributions | |
ancial | -2.022 |
culosis | -1.965 |
Klu | -1.687 |
pload | -1.675 |
ilege | -1.660 |
Token | against |
Token ID | 1028 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
asma | +0.923 |
Hermes | +0.794 |
alion | +0.754 |
yrus | +0.723 |
rodent | +0.718 |
Neg logit contributions | |
ancial | -0.874 |
culosis | -0.850 |
Klu | -0.729 |
pload | -0.720 |
ilege | -0.716 |
Token | Is |
Token ID | 1148 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
asma | +0.206 |
Hermes | +0.174 |
alion | +0.164 |
yrus | +0.157 |
rodent | +0.155 |
Neg logit contributions | |
ancial | -0.228 |
culosis | -0.221 |
Klu | -0.193 |
reck | -0.190 |
pload | -0.190 |
Token | il |
Token ID | 346 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
asma | +1.988 |
Hermes | +1.392 |
alion | +1.291 |
yrus | +1.181 |
ods | +1.097 |
Neg logit contributions | |
ancial | -5.142 |
culosis | -5.035 |
Klu | -4.582 |
pload | -4.527 |
orkshire | -4.516 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
asma | +0.578 |
Hermes | +0.492 |
alion | +0.461 |
yrus | +0.445 |
rodent | +0.439 |
Neg logit contributions | |
ancial | -0.630 |
culosis | -0.611 |
Klu | -0.529 |
reck | -0.526 |
pload | -0.525 |
Token | game |
Token ID | 983 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ancial | +1.812 |
culosis | +1.758 |
Klu | +1.552 |
reck | +1.517 |
pload | +1.506 |
Neg logit contributions | |
asma | -1.754 |
Hermes | -1.479 |
alion | -1.414 |
yrus | -1.345 |
rodent | -1.321 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
asma | +0.907 |
Hermes | +0.781 |
alion | +0.729 |
yrus | +0.707 |
rodent | +0.697 |
Neg logit contributions | |
ancial | -0.966 |
culosis | -0.939 |
Klu | -0.802 |
pload | -0.802 |
reck | -0.800 |
Token | they |
Token ID | 484 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
asma | +1.115 |
Hermes | +0.975 |
alion | +0.909 |
yrus | +0.887 |
rodent | +0.879 |
Neg logit contributions | |
ancial | -0.998 |
culosis | -0.970 |
Klu | -0.815 |
reck | -0.815 |
pload | -0.814 |
Token | gathered |
Token ID | 9272 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
asma | +1.133 |
Hermes | +0.960 |
alion | +0.905 |
yrus | +0.872 |
rodent | +0.862 |
Neg logit contributions | |
ancial | -1.210 |
culosis | -1.174 |
Klu | -1.020 |
reck | -1.006 |
pload | -1.004 |
Token | for |
Token ID | 329 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
asma | +1.011 |
Hermes | +0.870 |
alion | +0.812 |
yrus | +0.792 |
rodent | +0.791 |
Neg logit contributions | |
ancial | -0.968 |
culosis | -0.943 |
pload | -0.803 |
Klu | -0.799 |
ilege | -0.797 |
Token | dinner |
Token ID | 8073 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
ancial | +0.345 |
culosis | +0.335 |
Klu | +0.295 |
reck | +0.289 |
pload | +0.288 |
Neg logit contributions | |
asma | -0.308 |
Hermes | -0.259 |
alion | -0.246 |
yrus | -0.235 |
rodent | -0.230 |
Token | at |
Token ID | 379 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
asma | +0.828 |
Hermes | +0.712 |
alion | +0.673 |
yrus | +0.651 |
rodent | +0.644 |
Neg logit contributions | |
ancial | -0.787 |
culosis | -0.764 |
Klu | -0.655 |
pload | -0.648 |
reck | -0.645 |
Token | a |
Token ID | 257 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
asma | +1.590 |
Hermes | +1.381 |
alion | +1.280 |
yrus | +1.244 |
rodent | +1.234 |
Neg logit contributions | |
ancial | -1.595 |
culosis | -1.552 |
pload | -1.322 |
Klu | -1.320 |
reck | -1.317 |
Token | piano |
Token ID | 19132 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ancial | +0.201 |
culosis | +0.195 |
Klu | +0.172 |
reck | +0.169 |
pload | +0.169 |
Neg logit contributions | |
asma | -0.167 |
Hermes | -0.140 |
alion | -0.132 |
yrus | -0.126 |
rodent | -0.124 |
Token | bar |
Token ID | 2318 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ancial | +1.003 |
culosis | +0.972 |
Klu | +0.843 |
reck | +0.830 |
pload | +0.828 |
Neg logit contributions | |
asma | -1.022 |
Hermes | -0.873 |
alion | -0.827 |
yrus | -0.795 |
rodent | -0.785 |
Token | uneven |
Token ID | 30690 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
asma | +0.336 |
Hermes | +0.284 |
alion | +0.267 |
yrus | +0.256 |
rodent | +0.254 |
Neg logit contributions | |
ancial | -0.375 |
culosis | -0.364 |
Klu | -0.318 |
pload | -0.313 |
reck | -0.313 |
Token | debate |
Token ID | 4384 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ancial | +1.227 |
culosis | +1.190 |
Klu | +1.056 |
reck | +1.033 |
ilege | +1.025 |
Neg logit contributions | |
asma | -1.081 |
Hermes | -0.906 |
alion | -0.865 |
yrus | -0.823 |
rodent | -0.805 |
Token | . |
Token ID | 13 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
asma | +1.431 |
Hermes | +1.224 |
alion | +1.158 |
yrus | +1.115 |
rodent | +1.100 |
Neg logit contributions | |
ancial | -1.423 |
culosis | -1.383 |
Klu | -1.194 |
reck | -1.175 |
pload | -1.174 |
Token |
|
Token ID | 198 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
asma | +0.575 |
Hermes | +0.490 |
alion | +0.462 |
yrus | +0.443 |
rodent | +0.438 |
Neg logit contributions | |
ancial | -0.598 |
culosis | -0.580 |
Klu | -0.504 |
reck | -0.497 |
pload | -0.496 |
Token |
|
Token ID | 198 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
asma | +0.197 |
Hermes | +0.163 |
alion | +0.153 |
yrus | +0.147 |
rodent | +0.144 |
Neg logit contributions | |
ancial | -0.261 |
culosis | -0.254 |
Klu | -0.228 |
reck | -0.225 |
pload | -0.222 |
Token | P |
Token ID | 47 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
asma | +0.372 |
Hermes | +0.321 |
alion | +0.305 |
yrus | +0.295 |
rodent | +0.291 |
Neg logit contributions | |
ancial | -0.320 |
culosis | -0.310 |
Klu | -0.265 |
reck | -0.260 |
pload | -0.260 |
Token | ence |
Token ID | 594 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
asma | +0.479 |
Hermes | +0.420 |
alion | +0.406 |
yrus | +0.396 |
rodent | +0.386 |
Neg logit contributions | |
ancial | -0.285 |
culosis | -0.275 |
Klu | -0.226 |
pload | -0.217 |
ilege | -0.216 |
Token | did |
Token ID | 750 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
asma | +0.357 |
Hermes | +0.305 |
alion | +0.288 |
yrus | +0.278 |
rodent | +0.274 |
Neg logit contributions | |
ancial | -0.358 |
culosis | -0.347 |
Klu | -0.301 |
reck | -0.296 |
pload | -0.296 |
Token | well |
Token ID | 880 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ancial | +0.107 |
culosis | +0.104 |
Klu | +0.091 |
reck | +0.089 |
pload | +0.089 |
Neg logit contributions | |
asma | -0.102 |
Hermes | -0.086 |
alion | -0.082 |
yrus | -0.078 |
rodent | -0.077 |
Token | enough |
Token ID | 1576 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ancial | +2.092 |
culosis | +2.021 |
Klu | +1.772 |
reck | +1.730 |
pload | +1.710 |
Neg logit contributions | |
asma | -2.246 |
Hermes | -1.932 |
alion | -1.839 |
yrus | -1.757 |
rodent | -1.729 |
Token | for |
Token ID | 329 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
ancial | +0.935 |
culosis | +0.905 |
Klu | +0.787 |
reck | +0.774 |
pload | +0.768 |
Neg logit contributions | |
asma | -0.962 |
Hermes | -0.824 |
alion | -0.781 |
yrus | -0.749 |
rodent | -0.738 |
Token | the |
Token ID | 262 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
asma | +0.250 |
Hermes | +0.212 |
alion | +0.200 |
yrus | +0.192 |
rodent | +0.190 |
Neg logit contributions | |
ancial | -0.268 |
culosis | -0.260 |
Klu | -0.227 |
reck | -0.223 |
pload | -0.223 |
Token | outskirts |
Token ID | 30140 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
ancial | +0.464 |
culosis | +0.452 |
Klu | +0.400 |
reck | +0.394 |
pload | +0.393 |
Neg logit contributions | |
asma | -0.363 |
Hermes | -0.301 |
alion | -0.283 |
yrus | -0.270 |
rodent | -0.264 |
Token | of |
Token ID | 286 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
asma | +0.696 |
Hermes | +0.597 |
alion | +0.566 |
yrus | +0.545 |
rodent | +0.538 |
Neg logit contributions | |
ancial | -0.649 |
culosis | -0.628 |
Klu | -0.542 |
reck | -0.533 |
pload | -0.532 |
Token | Mumbai |
Token ID | 22917 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
asma | +0.711 |
Hermes | +0.612 |
alion | +0.575 |
yrus | +0.554 |
rodent | +0.550 |
Neg logit contributions | |
ancial | -0.687 |
culosis | -0.666 |
Klu | -0.572 |
reck | -0.568 |
pload | -0.565 |
Token | . |
Token ID | 13 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
asma | +1.630 |
Hermes | +1.399 |
alion | +1.322 |
yrus | +1.271 |
rodent | +1.261 |
Neg logit contributions | |
ancial | -1.626 |
culosis | -1.577 |
Klu | -1.363 |
reck | -1.344 |
pload | -1.340 |
Token |
|
Token ID | 198 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
asma | +0.595 |
Hermes | +0.515 |
alion | +0.487 |
yrus | +0.464 |
rodent | +0.461 |
Neg logit contributions | |
ancial | -0.564 |
culosis | -0.547 |
Klu | -0.469 |
reck | -0.464 |
pload | -0.462 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
asma | +0.471 |
Hermes | +0.387 |
alion | +0.363 |
yrus | +0.349 |
rodent | +0.341 |
Neg logit contributions | |
ancial | -0.653 |
culosis | -0.637 |
Klu | -0.569 |
reck | -0.561 |
pload | -0.557 |
Token | A |
Token ID | 32 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
asma | +0.948 |
Hermes | +0.814 |
alion | +0.776 |
yrus | +0.744 |
rodent | +0.736 |
Neg logit contributions | |
ancial | -0.877 |
culosis | -0.849 |
Klu | -0.729 |
pload | -0.716 |
reck | -0.712 |
Token | bench |
Token ID | 7624 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
asma | +2.311 |
Hermes | +1.959 |
alion | +1.852 |
yrus | +1.780 |
rodent | +1.762 |
Neg logit contributions | |
ancial | -2.436 |
culosis | -2.367 |
Klu | -2.037 |
pload | -2.021 |
reck | -2.017 |
Token | of |
Token ID | 286 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
asma | +1.242 |
Hermes | +1.042 |
alion | +0.982 |
yrus | +0.938 |
rodent | +0.925 |
Neg logit contributions | |
ancial | -1.468 |
culosis | -1.423 |
Klu | -1.246 |
reck | -1.231 |
pload | -1.230 |
Token | justices |
Token ID | 27818 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
ancial | +0.229 |
culosis | +0.221 |
Klu | +0.189 |
pload | +0.185 |
reck | +0.184 |
Neg logit contributions | |
asma | -0.286 |
Hermes | -0.247 |
alion | -0.237 |
yrus | -0.229 |
rodent | -0.226 |
Token | ]] |
Token ID | 11907 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ancial | +0.902 |
culosis | +0.871 |
Klu | +0.743 |
pload | +0.732 |
reck | +0.731 |
Neg logit contributions | |
asma | -1.116 |
Hermes | -0.965 |
alion | -0.921 |
yrus | -0.888 |
rodent | -0.877 |
Token | ] |
Token ID | 60 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
asma | +0.306 |
Hermes | +0.264 |
alion | +0.250 |
yrus | +0.241 |
rodent | +0.238 |
Neg logit contributions | |
ancial | -0.277 |
culosis | -0.268 |
Klu | -0.231 |
reck | -0.227 |
pload | -0.226 |
Token | = |
Token ID | 796 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
asma | +0.484 |
Hermes | +0.412 |
alion | +0.390 |
yrus | +0.375 |
rodent | +0.370 |
Neg logit contributions | |
ancial | -0.496 |
culosis | -0.482 |
Klu | -0.419 |
reck | -0.412 |
pload | -0.411 |
Token | " |
Token ID | 366 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
ancial | +2.007 |
culosis | +1.957 |
Klu | +1.725 |
pload | +1.701 |
ilege | +1.691 |
Neg logit contributions | |
asma | -1.794 |
Hermes | -1.489 |
alion | -1.422 |
yrus | -1.343 |
rodent | -1.322 |
Token | S |
Token ID | 50 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
asma | +0.364 |
Hermes | +0.315 |
alion | +0.300 |
yrus | +0.290 |
rodent | +0.287 |
Neg logit contributions | |
ancial | -0.293 |
culosis | -0.283 |
Klu | -0.241 |
reck | -0.237 |
pload | -0.236 |
Token | ", |
Token ID | 1600 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
asma | +1.303 |
Hermes | +1.103 |
alion | +1.041 |
yrus | +1.001 |
rodent | +0.983 |
Neg logit contributions | |
ancial | -1.418 |
culosis | -1.379 |
Klu | -1.206 |
reck | -1.185 |
pload | -1.183 |
Token | { |
Token ID | 1391 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
asma | +4.046 |
Hermes | +3.470 |
alion | +3.203 |
yrus | +3.128 |
rodent | +3.092 |
Neg logit contributions | |
ancial | -4.969 |
culosis | -4.811 |
Klu | -4.197 |
reck | -4.171 |
orkshire | -4.145 |
Token | i |
Token ID | 72 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
ancial | +1.679 |
culosis | +1.629 |
Klu | +1.405 |
reck | +1.402 |
ilege | +1.389 |
Neg logit contributions | |
asma | -1.766 |
Hermes | -1.506 |
alion | -1.436 |
yrus | -1.371 |
rodent | -1.358 |
Token | , |
Token ID | 11 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
asma | +2.128 |
Hermes | +1.825 |
alion | +1.714 |
yrus | +1.657 |
rodent | +1.630 |
Neg logit contributions | |
ancial | -2.150 |
culosis | -2.097 |
Klu | -1.822 |
reck | -1.784 |
pload | -1.781 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
asma | +1.988 |
Hermes | +1.685 |
alion | +1.575 |
yrus | +1.518 |
rodent | +1.492 |
Neg logit contributions | |
ancial | -2.320 |
culosis | -2.251 |
Klu | -1.976 |
reck | -1.944 |
pload | -1.936 |
Token | , |
Token ID | 11 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
asma | +1.736 |
Hermes | +1.516 |
alion | +1.447 |
yrus | +1.399 |
rodent | +1.384 |
Neg logit contributions | |
ancial | -1.305 |
culosis | -1.265 |
Klu | -1.071 |
reck | -1.045 |
pload | -1.043 |
Token | S |
Token ID | 50 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
asma | +1.042 |
Hermes | +0.901 |
alion | +0.855 |
yrus | +0.822 |
rodent | +0.811 |
Neg logit contributions | |
ancial | -0.887 |
culosis | -0.864 |
Klu | -0.732 |
reck | -0.723 |
pload | -0.722 |
Token | ). |
Token ID | 737 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ancial | +2.191 |
culosis | +2.112 |
Klu | +1.798 |
reck | +1.757 |
pload | +1.749 |
Neg logit contributions | |
asma | -2.821 |
Hermes | -2.441 |
alion | -2.343 |
yrus | -2.262 |
rodent | -2.246 |
Token | Since |
Token ID | 4619 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
asma | +0.955 |
Hermes | +0.800 |
alion | +0.749 |
yrus | +0.716 |
rodent | +0.706 |
Neg logit contributions | |
ancial | -1.170 |
culosis | -1.138 |
Klu | -1.000 |
reck | -0.988 |
pload | -0.987 |
Token | dinosaurs |
Token ID | 27199 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
asma | +0.142 |
Hermes | +0.120 |
alion | +0.113 |
yrus | +0.109 |
rodent | +0.108 |
Neg logit contributions | |
ancial | -0.149 |
culosis | -0.145 |
Klu | -0.126 |
reck | -0.124 |
pload | -0.124 |
Token | are |
Token ID | 389 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
asma | +1.634 |
Hermes | +1.396 |
alion | +1.314 |
rodent | +1.269 |
yrus | +1.267 |
Neg logit contributions | |
ancial | -1.656 |
culosis | -1.606 |
Klu | -1.388 |
pload | -1.377 |
reck | -1.369 |
Token | thought |
Token ID | 1807 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
asma | +1.353 |
Hermes | +1.147 |
alion | +1.059 |
rodent | +1.024 |
yrus | +1.021 |
Neg logit contributions | |
ancial | -1.625 |
culosis | -1.591 |
Klu | -1.378 |
pload | -1.368 |
ilege | -1.366 |
Token | to |
Token ID | 284 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
asma | +4.052 |
Hermes | +3.433 |
alion | +3.205 |
rodent | +3.094 |
yrus | +3.086 |
Neg logit contributions | |
ancial | -4.702 |
culosis | -4.561 |
Klu | -4.004 |
pload | -3.961 |
orkshire | -3.961 |
Token | be |
Token ID | 307 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
asma | +1.737 |
Hermes | +1.459 |
alion | +1.369 |
yrus | +1.316 |
rodent | +1.306 |
Neg logit contributions | |
ancial | -2.045 |
culosis | -1.990 |
Klu | -1.750 |
reck | -1.722 |
pload | -1.718 |
Token | over |
Token ID | 625 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
asma | +2.187 |
Hermes | +1.874 |
alion | +1.712 |
rodent | +1.686 |
yrus | +1.663 |
Neg logit contributions | |
ancial | -2.561 |
culosis | -2.520 |
Klu | -2.162 |
ilege | -2.149 |
pload | -2.146 |
Token | 65 |
Token ID | 6135 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
asma | +0.700 |
Hermes | +0.599 |
alion | +0.566 |
yrus | +0.547 |
rodent | +0.539 |
Neg logit contributions | |
ancial | -0.695 |
culosis | -0.676 |
Klu | -0.584 |
reck | -0.574 |
pload | -0.574 |
Token | million |
Token ID | 1510 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
asma | +1.041 |
Hermes | +0.875 |
alion | +0.822 |
yrus | +0.788 |
rodent | +0.777 |
Neg logit contributions | |
ancial | -1.225 |
culosis | -1.192 |
Klu | -1.045 |
reck | -1.031 |
pload | -1.030 |
Token | private |
Token ID | 2839 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
asma | +0.050 |
Hermes | +0.042 |
alion | +0.039 |
yrus | +0.038 |
rodent | +0.037 |
Neg logit contributions | |
ancial | -0.059 |
culosis | -0.057 |
Klu | -0.050 |
reck | -0.050 |
pload | -0.049 |
Token | property |
Token ID | 3119 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
ancial | +1.553 |
culosis | +1.490 |
Klu | +1.248 |
reck | +1.217 |
ilege | +1.198 |
Neg logit contributions | |
asma | -2.490 |
Hermes | -2.175 |
alion | -2.106 |
yrus | -2.032 |
rodent | -1.998 |
Token | worth |
Token ID | 2861 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
ancial | +0.415 |
culosis | +0.403 |
Klu | +0.350 |
reck | +0.345 |
pload | +0.343 |
Neg logit contributions | |
asma | -0.409 |
Hermes | -0.348 |
alion | -0.329 |
yrus | -0.317 |
rodent | -0.312 |
Token | more |
Token ID | 517 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
asma | +0.590 |
Hermes | +0.496 |
alion | +0.464 |
yrus | +0.445 |
rodent | +0.438 |
Neg logit contributions | |
ancial | -0.712 |
culosis | -0.694 |
Klu | -0.609 |
reck | -0.601 |
pload | -0.600 |
Token | than |
Token ID | 621 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
asma | +1.062 |
Hermes | +0.881 |
alion | +0.824 |
yrus | +0.787 |
rodent | +0.774 |
Neg logit contributions | |
ancial | -1.399 |
culosis | -1.362 |
Klu | -1.204 |
reck | -1.188 |
pload | -1.187 |
Token | Rs |
Token ID | 12820 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
asma | +0.722 |
Hermes | +0.603 |
alion | +0.565 |
yrus | +0.540 |
rodent | +0.531 |
Neg logit contributions | |
ancial | -0.907 |
culosis | -0.883 |
Klu | -0.778 |
reck | -0.768 |
pload | -0.766 |
Token | 20 |
Token ID | 1160 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
asma | +4.010 |
Hermes | +3.479 |
alion | +3.226 |
yrus | +3.078 |
rodent | +3.039 |
Neg logit contributions | |
ancial | -4.261 |
culosis | -4.199 |
pload | -3.539 |
Klu | -3.529 |
orkshire | -3.517 |
Token | , |
Token ID | 11 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
asma | +1.706 |
Hermes | +1.453 |
alion | +1.368 |
yrus | +1.310 |
rodent | +1.294 |
Neg logit contributions | |
ancial | -1.865 |
culosis | -1.816 |
Klu | -1.580 |
pload | -1.563 |
reck | -1.562 |
Token | 000 |
Token ID | 830 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ancial | +1.031 |
culosis | +1.000 |
Klu | +0.871 |
pload | +0.856 |
reck | +0.856 |
Neg logit contributions | |
asma | -0.999 |
Hermes | -0.847 |
alion | -0.799 |
yrus | -0.772 |
rodent | -0.760 |
Token | crore |
Token ID | 22306 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
asma | +0.787 |
Hermes | +0.656 |
alion | +0.615 |
yrus | +0.587 |
rodent | +0.578 |
Neg logit contributions | |
ancial | -0.999 |
culosis | -0.972 |
Klu | -0.858 |
reck | -0.846 |
pload | -0.845 |
Token | has |
Token ID | 468 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
asma | +2.572 |
Hermes | +2.170 |
alion | +2.044 |
yrus | +1.948 |
rodent | +1.933 |
Neg logit contributions | |
ancial | -3.063 |
culosis | -2.966 |
Klu | -2.624 |
pload | -2.597 |
ilege | -2.585 |
Token | was |
Token ID | 373 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
asma | +2.702 |
Hermes | +2.310 |
alion | +2.166 |
yrus | +2.082 |
rodent | +2.056 |
Neg logit contributions | |
ancial | -2.915 |
culosis | -2.812 |
Klu | -2.423 |
reck | -2.406 |
ilege | -2.406 |
Token | a |
Token ID | 257 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
ancial | +1.187 |
culosis | +1.156 |
Klu | +1.016 |
reck | +0.995 |
pload | +0.995 |
Neg logit contributions | |
asma | -1.169 |
Hermes | -0.983 |
alion | -0.940 |
yrus | -0.898 |
rodent | -0.883 |
Token | boy |
Token ID | 2933 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
ancial | +0.301 |
culosis | +0.292 |
Klu | +0.256 |
reck | +0.252 |
pload | +0.252 |
Neg logit contributions | |
asma | -0.272 |
Hermes | -0.229 |
alion | -0.217 |
yrus | -0.208 |
rodent | -0.204 |
Token | who |
Token ID | 508 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
asma | +0.496 |
Hermes | +0.423 |
alion | +0.400 |
yrus | +0.384 |
rodent | +0.380 |
Neg logit contributions | |
ancial | -0.507 |
culosis | -0.491 |
Klu | -0.427 |
reck | -0.421 |
pload | -0.420 |
Token | was |
Token ID | 373 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
asma | +0.522 |
Hermes | +0.441 |
alion | +0.417 |
yrus | +0.400 |
rodent | +0.394 |
Neg logit contributions | |
ancial | -0.568 |
culosis | -0.552 |
Klu | -0.484 |
reck | -0.475 |
pload | -0.475 |
Token | looking |
Token ID | 2045 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
asma | +0.485 |
Hermes | +0.410 |
alion | +0.387 |
yrus | +0.371 |
rodent | +0.365 |
Neg logit contributions | |
ancial | -0.537 |
culosis | -0.522 |
Klu | -0.456 |
reck | -0.450 |
pload | -0.449 |
Token | for |
Token ID | 329 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
asma | +4.508 |
Hermes | +3.932 |
alion | +3.685 |
rodent | +3.517 |
goodbye | +3.480 |
Neg logit contributions | |
ancial | -4.851 |
culosis | -4.738 |
Klu | -4.010 |
pload | -4.003 |
orkshire | -3.980 |
Token | his |
Token ID | 465 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
asma | +0.603 |
Hermes | +0.512 |
alion | +0.485 |
yrus | +0.466 |
rodent | +0.459 |
Neg logit contributions | |
ancial | -0.623 |
culosis | -0.605 |
Klu | -0.527 |
reck | -0.518 |
pload | -0.517 |
Token | mother |
Token ID | 2802 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
asma | +1.456 |
Hermes | +1.207 |
alion | +1.123 |
yrus | +1.069 |
rodent | +1.059 |
Neg logit contributions | |
ancial | -1.971 |
culosis | -1.916 |
Klu | -1.688 |
reck | -1.674 |
pload | -1.673 |
Token | from |
Token ID | 422 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ancial | +0.684 |
culosis | +0.663 |
Klu | +0.573 |
reck | +0.564 |
pload | +0.562 |
Neg logit contributions | |
asma | -0.728 |
Hermes | -0.623 |
alion | -0.592 |
yrus | -0.569 |
rodent | -0.562 |
Token | the |
Token ID | 262 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
ancial | +0.261 |
culosis | +0.253 |
Klu | +0.220 |
reck | +0.217 |
pload | +0.216 |
Neg logit contributions | |
asma | -0.254 |
Hermes | -0.216 |
alion | -0.204 |
yrus | -0.196 |
rodent | -0.193 |
Token | House |
Token ID | 2097 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
ancial | +1.097 |
culosis | +1.064 |
Klu | +0.929 |
reck | +0.907 |
ilege | +0.904 |
Neg logit contributions | |
asma | -1.120 |
Hermes | -0.953 |
alion | -0.908 |
yrus | -0.874 |
rodent | -0.855 |
Token | Republicans |
Token ID | 4734 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ancial | +0.379 |
culosis | +0.368 |
Klu | +0.317 |
pload | +0.312 |
reck | +0.312 |
Neg logit contributions | |
asma | -0.395 |
Hermes | -0.339 |
alion | -0.321 |
yrus | -0.309 |
rodent | -0.307 |
Token | , |
Token ID | 11 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
asma | +0.281 |
Hermes | +0.241 |
alion | +0.228 |
yrus | +0.219 |
rodent | +0.216 |
Neg logit contributions | |
ancial | -0.274 |
culosis | -0.266 |
Klu | -0.230 |
reck | -0.227 |
pload | -0.226 |
Token | has |
Token ID | 468 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ancial | +1.648 |
culosis | +1.606 |
Klu | +1.409 |
reck | +1.378 |
pload | +1.367 |
Neg logit contributions | |
asma | -1.592 |
Hermes | -1.343 |
alion | -1.291 |
yrus | -1.230 |
rodent | -1.205 |
Token | emptied |
Token ID | 46705 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
asma | +0.187 |
Hermes | +0.157 |
alion | +0.147 |
yrus | +0.141 |
rodent | +0.139 |
Neg logit contributions | |
ancial | -0.226 |
culosis | -0.220 |
Klu | -0.194 |
reck | -0.191 |
pload | -0.191 |
Token | $ |
Token ID | 720 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
asma | +0.888 |
Hermes | +0.753 |
alion | +0.708 |
yrus | +0.680 |
rodent | +0.671 |
Neg logit contributions | |
ancial | -0.989 |
culosis | -0.962 |
Klu | -0.839 |
reck | -0.828 |
pload | -0.826 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
asma | +4.217 |
Hermes | +3.576 |
alion | +3.390 |
yrus | +3.229 |
ods | +3.163 |
Neg logit contributions | |
ancial | -4.316 |
culosis | -4.231 |
Klu | -3.614 |
pload | -3.560 |
orkshire | -3.552 |
Token | million |
Token ID | 1510 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
asma | +2.515 |
Hermes | +2.115 |
alion | +2.008 |
yrus | +1.916 |
rodent | +1.886 |
Neg logit contributions | |
ancial | -2.946 |
culosis | -2.881 |
Klu | -2.530 |
pload | -2.471 |
ilege | -2.470 |
Token | into |
Token ID | 656 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
asma | +1.808 |
Hermes | +1.540 |
alion | +1.449 |
yrus | +1.390 |
rodent | +1.378 |
Neg logit contributions | |
ancial | -1.910 |
culosis | -1.860 |
Klu | -1.611 |
reck | -1.591 |
pload | -1.589 |
Token | the |
Token ID | 262 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
asma | +1.761 |
Hermes | +1.515 |
alion | +1.412 |
yrus | +1.352 |
rodent | +1.349 |
Neg logit contributions | |
ancial | -1.959 |
culosis | -1.904 |
Klu | -1.650 |
ilege | -1.636 |
reck | -1.633 |
Token | race |
Token ID | 3234 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ancial | +0.252 |
culosis | +0.245 |
Klu | +0.214 |
reck | +0.211 |
pload | +0.210 |
Neg logit contributions | |
asma | -0.230 |
Hermes | -0.194 |
alion | -0.184 |
yrus | -0.176 |
rodent | -0.173 |