Token | Hide |
Token ID | 10415 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
forging | +0.641 |
orsi | +0.637 |
ratulations | +0.636 |
remember | +0.632 |
iferation | +0.612 |
Neg logit contributions | |
Behavioral | -0.195 |
Pandora | -0.161 |
ディ | -0.147 |
^^ | -0.130 |
Pesh | -0.129 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Behavioral | +1.406 |
Pandora | +1.239 |
Bronze | +1.002 |
Stephenson | +0.987 |
ディ | +0.983 |
Neg logit contributions | |
ratulations | -4.170 |
forging | -4.126 |
orsi | -4.074 |
merce | -4.060 |
remember | -3.946 |
Token | 5 |
Token ID | 642 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
Behavioral | +1.078 |
Pandora | +0.970 |
ディ | +0.866 |
Bronze | +0.855 |
^^ | +0.846 |
Neg logit contributions | |
ratulations | -1.829 |
forging | -1.820 |
orsi | -1.812 |
merce | -1.755 |
remember | -1.753 |
Token | of |
Token ID | 286 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Behavioral | +0.549 |
Pandora | +0.501 |
ディ | +0.462 |
^^ | +0.459 |
Bronze | +0.447 |
Neg logit contributions | |
ratulations | -0.860 |
forging | -0.830 |
orsi | -0.830 |
merce | -0.821 |
remember | -0.789 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Behavioral | +0.650 |
Pandora | +0.558 |
ディ | +0.500 |
Pesh | +0.494 |
Bronze | +0.488 |
Neg logit contributions | |
ratulations | -1.479 |
orsi | -1.455 |
forging | -1.451 |
remember | -1.421 |
merce | -1.412 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
forging | +0.248 |
ratulations | +0.247 |
orsi | +0.245 |
remember | +0.239 |
merce | +0.237 |
Neg logit contributions | |
Behavioral | -0.137 |
Pandora | -0.122 |
Pesh | -0.109 |
ディ | -0.108 |
Bronze | -0.107 |
Token | : |
Token ID | 25 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Behavioral | +5.031 |
Pandora | +4.606 |
^^ | +4.419 |
Bronze | +4.296 |
ディ | +4.204 |
Neg logit contributions | |
ratulations | -6.636 |
merce | -6.431 |
forging | -6.047 |
orsi | -5.977 |
iferation | -5.701 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Behavioral | +1.152 |
Pandora | +1.050 |
ディ | +0.976 |
Pesh | +0.972 |
Possible | +0.965 |
Neg logit contributions | |
ratulations | -1.244 |
forging | -1.219 |
orsi | -1.211 |
merce | -1.181 |
remember | -1.176 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Behavioral | +0.809 |
Pandora | +0.740 |
ディ | +0.701 |
Stephenson | +0.691 |
Pesh | +0.690 |
Neg logit contributions | |
ratulations | -0.736 |
forging | -0.727 |
orsi | -0.724 |
remember | -0.716 |
merce | -0.696 |
Token | 's |
Token ID | 338 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Behavioral | +0.866 |
Pandora | +0.785 |
ディ | +0.708 |
^^ | +0.702 |
Bronze | +0.698 |
Neg logit contributions | |
ratulations | -1.334 |
orsi | -1.307 |
forging | -1.296 |
remember | -1.293 |
merce | -1.273 |
Token | political |
Token ID | 1964 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Behavioral | +1.017 |
Pandora | +0.927 |
ディ | +0.860 |
Pesh | +0.848 |
^^ | +0.847 |
Neg logit contributions | |
ratulations | -1.113 |
orsi | -1.098 |
remember | -1.081 |
forging | -1.079 |
sbm | -1.037 |
Token | Hide |
Token ID | 10415 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
Behavioral | +0.001 |
Pandora | +0.001 |
ディ | +0.001 |
^^ | +0.001 |
Pesh | +0.001 |
Neg logit contributions | |
forging | -0.004 |
ratulations | -0.004 |
orsi | -0.004 |
remember | -0.004 |
iferation | -0.004 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Behavioral | +1.662 |
Pandora | +1.461 |
Bronze | +1.179 |
ディ | +1.161 |
Stephenson | +1.159 |
Neg logit contributions | |
ratulations | -4.849 |
forging | -4.811 |
orsi | -4.758 |
merce | -4.724 |
remember | -4.595 |
Token | 7 |
Token ID | 767 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Behavioral | +1.639 |
Pandora | +1.510 |
^^ | +1.388 |
ディ | +1.383 |
Stephenson | +1.365 |
Neg logit contributions | |
ratulations | -1.891 |
forging | -1.863 |
orsi | -1.862 |
merce | -1.816 |
remember | -1.779 |
Token | of |
Token ID | 286 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Behavioral | +0.238 |
Pandora | +0.218 |
ディ | +0.201 |
^^ | +0.199 |
Bronze | +0.194 |
Neg logit contributions | |
ratulations | -0.354 |
forging | -0.345 |
orsi | -0.344 |
merce | -0.337 |
remember | -0.331 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Behavioral | +0.664 |
Pandora | +0.576 |
ディ | +0.521 |
Pesh | +0.508 |
Stephenson | +0.503 |
Neg logit contributions | |
ratulations | -1.492 |
orsi | -1.475 |
forging | -1.466 |
remember | -1.433 |
merce | -1.432 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
Behavioral | +0.096 |
Pandora | +0.086 |
Pesh | +0.077 |
ディ | +0.076 |
Bronze | +0.076 |
Neg logit contributions | |
forging | -0.177 |
ratulations | -0.177 |
orsi | -0.176 |
merce | -0.171 |
remember | -0.170 |
Token | : |
Token ID | 25 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Behavioral | +4.850 |
Pandora | +4.478 |
^^ | +4.313 |
Bronze | +4.154 |
ディ | +4.073 |
Neg logit contributions | |
ratulations | -6.464 |
merce | -6.323 |
forging | -5.927 |
orsi | -5.886 |
iferation | -5.627 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Behavioral | +0.823 |
Pandora | +0.752 |
ディ | +0.707 |
Pesh | +0.696 |
Possible | +0.690 |
Neg logit contributions | |
ratulations | -0.880 |
forging | -0.868 |
orsi | -0.860 |
remember | -0.836 |
merce | -0.834 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Behavioral | +1.105 |
Pandora | +1.012 |
ディ | +0.961 |
^^ | +0.943 |
Pesh | +0.941 |
Neg logit contributions | |
ratulations | -1.013 |
forging | -1.013 |
orsi | -0.993 |
remember | -0.981 |
merce | -0.962 |
Token | 's |
Token ID | 338 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Behavioral | +0.990 |
Pandora | +0.894 |
ディ | +0.816 |
^^ | +0.812 |
Bronze | +0.801 |
Neg logit contributions | |
ratulations | -1.575 |
orsi | -1.535 |
forging | -1.532 |
remember | -1.505 |
merce | -1.502 |
Token | political |
Token ID | 1964 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
Behavioral | +0.723 |
Pandora | +0.659 |
ディ | +0.616 |
^^ | +0.607 |
Pesh | +0.606 |
Neg logit contributions | |
ratulations | -0.784 |
orsi | -0.773 |
forging | -0.765 |
remember | -0.764 |
iferation | -0.732 |
Token | Hide |
Token ID | 10415 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
forging | +0.922 |
orsi | +0.915 |
ratulations | +0.912 |
remember | +0.910 |
iferation | +0.879 |
Neg logit contributions | |
Behavioral | -0.277 |
Pandora | -0.228 |
ディ | -0.209 |
^^ | -0.185 |
Pesh | -0.183 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Behavioral | +1.283 |
Pandora | +1.124 |
ディ | +0.920 |
Bronze | +0.913 |
^^ | +0.899 |
Neg logit contributions | |
ratulations | -3.534 |
forging | -3.514 |
orsi | -3.462 |
merce | -3.441 |
remember | -3.358 |
Token | 12 |
Token ID | 1105 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Behavioral | +1.066 |
Pandora | +0.953 |
ディ | +0.886 |
^^ | +0.870 |
Pesh | +0.845 |
Neg logit contributions | |
ratulations | -1.656 |
forging | -1.622 |
orsi | -1.610 |
merce | -1.596 |
iferation | -1.555 |
Token | of |
Token ID | 286 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
Behavioral | +0.952 |
Pandora | +0.875 |
^^ | +0.804 |
ディ | +0.802 |
Bronze | +0.784 |
Neg logit contributions | |
ratulations | -1.557 |
orsi | -1.505 |
forging | -1.504 |
merce | -1.503 |
iferation | -1.435 |
Token | 15 |
Token ID | 1315 |
Feature activation | -7.81e-02 |
Pos logit contributions | |
Behavioral | +0.371 |
Pandora | +0.325 |
ディ | +0.297 |
Pesh | +0.285 |
^^ | +0.283 |
Neg logit contributions | |
ratulations | -0.810 |
orsi | -0.803 |
forging | -0.799 |
remember | -0.783 |
merce | -0.776 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
forging | +0.076 |
ratulations | +0.076 |
orsi | +0.076 |
remember | +0.074 |
merce | +0.073 |
Neg logit contributions | |
Behavioral | -0.043 |
Pandora | -0.038 |
ディ | -0.034 |
Pesh | -0.034 |
^^ | -0.034 |
Token | : |
Token ID | 25 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Behavioral | +4.785 |
Pandora | +4.447 |
^^ | +4.292 |
Bronze | +4.145 |
ディ | +4.016 |
Neg logit contributions | |
ratulations | -6.398 |
merce | -6.295 |
forging | -5.870 |
orsi | -5.845 |
iferation | -5.610 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Behavioral | +0.752 |
Pandora | +0.687 |
ディ | +0.647 |
Pesh | +0.636 |
Bronze | +0.631 |
Neg logit contributions | |
ratulations | -0.801 |
forging | -0.793 |
orsi | -0.785 |
remember | -0.763 |
merce | -0.759 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Behavioral | +0.823 |
Pandora | +0.756 |
ディ | +0.718 |
^^ | +0.705 |
Stephenson | +0.702 |
Neg logit contributions | |
forging | -0.747 |
ratulations | -0.746 |
orsi | -0.733 |
remember | -0.724 |
merce | -0.707 |
Token | 's |
Token ID | 338 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Behavioral | +0.984 |
Pandora | +0.892 |
ディ | +0.811 |
^^ | +0.808 |
Bronze | +0.798 |
Neg logit contributions | |
ratulations | -1.591 |
orsi | -1.553 |
forging | -1.542 |
merce | -1.524 |
remember | -1.521 |
Token | political |
Token ID | 1964 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
Behavioral | +0.935 |
Pandora | +0.851 |
ディ | +0.786 |
^^ | +0.783 |
Pesh | +0.782 |
Neg logit contributions | |
ratulations | -1.057 |
orsi | -1.038 |
remember | -1.025 |
forging | -1.021 |
iferation | -0.986 |
Token | Hide |
Token ID | 10415 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
forging | +1.616 |
orsi | +1.603 |
ratulations | +1.599 |
remember | +1.591 |
iferation | +1.534 |
Neg logit contributions | |
Behavioral | -0.688 |
Pandora | -0.595 |
ディ | -0.555 |
^^ | -0.511 |
Pesh | -0.507 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Behavioral | +1.484 |
Pandora | +1.293 |
Bronze | +1.057 |
ディ | +1.056 |
^^ | +1.033 |
Neg logit contributions | |
ratulations | -4.258 |
forging | -4.226 |
orsi | -4.179 |
merce | -4.156 |
remember | -4.037 |
Token | 9 |
Token ID | 860 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Behavioral | +1.399 |
Pandora | +1.304 |
Bronze | +1.200 |
^^ | +1.190 |
Stephenson | +1.184 |
Neg logit contributions | |
ratulations | -1.478 |
forging | -1.459 |
orsi | -1.443 |
merce | -1.415 |
remember | -1.395 |
Token | of |
Token ID | 286 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Behavioral | +0.225 |
Pandora | +0.205 |
ディ | +0.191 |
^^ | +0.189 |
Bronze | +0.184 |
Neg logit contributions | |
ratulations | -0.335 |
forging | -0.326 |
orsi | -0.325 |
merce | -0.319 |
remember | -0.312 |
Token | 15 |
Token ID | 1315 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
Behavioral | +0.676 |
Pandora | +0.590 |
ディ | +0.530 |
Pesh | +0.516 |
Stephenson | +0.511 |
Neg logit contributions | |
ratulations | -1.560 |
orsi | -1.542 |
forging | -1.529 |
merce | -1.501 |
remember | -1.493 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
forging | +0.079 |
ratulations | +0.079 |
orsi | +0.079 |
remember | +0.076 |
merce | +0.076 |
Neg logit contributions | |
Behavioral | -0.044 |
Pandora | -0.040 |
Pesh | -0.035 |
ディ | -0.035 |
Bronze | -0.035 |
Token | : |
Token ID | 25 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Behavioral | +4.783 |
Pandora | +4.435 |
^^ | +4.276 |
Bronze | +4.127 |
ディ | +4.026 |
Neg logit contributions | |
ratulations | -6.349 |
merce | -6.219 |
forging | -5.820 |
orsi | -5.798 |
iferation | -5.541 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Behavioral | +0.751 |
Pandora | +0.687 |
ディ | +0.646 |
Pesh | +0.635 |
Bronze | +0.629 |
Neg logit contributions | |
ratulations | -0.796 |
forging | -0.787 |
orsi | -0.780 |
remember | -0.758 |
merce | -0.755 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Behavioral | +1.139 |
Pandora | +1.046 |
ディ | +0.992 |
^^ | +0.973 |
Stephenson | +0.972 |
Neg logit contributions | |
ratulations | -1.047 |
forging | -1.047 |
orsi | -1.027 |
remember | -1.015 |
merce | -0.996 |
Token | 's |
Token ID | 338 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Behavioral | +1.033 |
Pandora | +0.937 |
ディ | +0.848 |
^^ | +0.844 |
Bronze | +0.840 |
Neg logit contributions | |
ratulations | -1.662 |
orsi | -1.620 |
forging | -1.614 |
remember | -1.590 |
merce | -1.589 |
Token | political |
Token ID | 1964 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Behavioral | +0.865 |
Pandora | +0.789 |
ディ | +0.733 |
Pesh | +0.725 |
^^ | +0.725 |
Neg logit contributions | |
ratulations | -0.958 |
orsi | -0.943 |
remember | -0.931 |
forging | -0.931 |
iferation | -0.894 |
Token | Hide |
Token ID | 10415 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
forging | +0.567 |
orsi | +0.563 |
ratulations | +0.562 |
remember | +0.559 |
iferation | +0.540 |
Neg logit contributions | |
Behavioral | -0.191 |
Pandora | -0.160 |
ディ | -0.147 |
^^ | -0.132 |
Pesh | -0.131 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Behavioral | +1.706 |
Pandora | +1.480 |
Bronze | +1.208 |
Possible | +1.176 |
ディ | +1.175 |
Neg logit contributions | |
ratulations | -4.951 |
forging | -4.907 |
merce | -4.849 |
orsi | -4.843 |
remember | -4.678 |
Token | 14 |
Token ID | 1478 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Behavioral | +1.278 |
Pandora | +1.134 |
ディ | +1.047 |
^^ | +1.042 |
Stephenson | +1.036 |
Neg logit contributions | |
ratulations | -1.971 |
forging | -1.914 |
orsi | -1.901 |
merce | -1.883 |
remember | -1.847 |
Token | of |
Token ID | 286 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
Behavioral | +1.104 |
Pandora | +1.011 |
^^ | +0.933 |
ディ | +0.918 |
Bronze | +0.906 |
Neg logit contributions | |
ratulations | -1.792 |
forging | -1.737 |
orsi | -1.735 |
merce | -1.731 |
iferation | -1.658 |
Token | 15 |
Token ID | 1315 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
Behavioral | +0.380 |
Pandora | +0.333 |
ディ | +0.305 |
Pesh | +0.293 |
^^ | +0.291 |
Neg logit contributions | |
ratulations | -0.814 |
orsi | -0.807 |
forging | -0.804 |
remember | -0.786 |
merce | -0.779 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
Behavioral | +0.326 |
Pandora | +0.292 |
Pesh | +0.260 |
ディ | +0.257 |
Bronze | +0.256 |
Neg logit contributions | |
forging | -0.598 |
ratulations | -0.598 |
orsi | -0.594 |
merce | -0.578 |
remember | -0.575 |
Token | : |
Token ID | 25 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
Behavioral | +4.759 |
Pandora | +4.413 |
^^ | +4.253 |
Bronze | +4.112 |
ディ | +3.987 |
Neg logit contributions | |
ratulations | -6.285 |
merce | -6.189 |
forging | -5.770 |
orsi | -5.744 |
iferation | -5.511 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Behavioral | +0.712 |
Pandora | +0.651 |
ディ | +0.612 |
Pesh | +0.602 |
Bronze | +0.598 |
Neg logit contributions | |
ratulations | -0.753 |
forging | -0.746 |
orsi | -0.738 |
remember | -0.719 |
merce | -0.713 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Behavioral | +0.948 |
Pandora | +0.871 |
ディ | +0.825 |
^^ | +0.812 |
Stephenson | +0.809 |
Neg logit contributions | |
forging | -0.865 |
ratulations | -0.863 |
orsi | -0.846 |
remember | -0.837 |
merce | -0.819 |
Token | 's |
Token ID | 338 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Behavioral | +0.971 |
Pandora | +0.879 |
^^ | +0.800 |
ディ | +0.797 |
Bronze | +0.788 |
Neg logit contributions | |
ratulations | -1.586 |
orsi | -1.539 |
forging | -1.535 |
merce | -1.515 |
remember | -1.505 |
Token | political |
Token ID | 1964 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Behavioral | +0.774 |
Pandora | +0.704 |
ディ | +0.653 |
^^ | +0.649 |
Pesh | +0.648 |
Neg logit contributions | |
ratulations | -0.859 |
orsi | -0.844 |
remember | -0.835 |
forging | -0.832 |
iferation | -0.802 |
Token | Hide |
Token ID | 10415 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
forging | +0.737 |
orsi | +0.731 |
ratulations | +0.729 |
remember | +0.727 |
iferation | +0.702 |
Neg logit contributions | |
Behavioral | -0.230 |
Pandora | -0.191 |
ディ | -0.174 |
^^ | -0.156 |
Pesh | -0.154 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Behavioral | +1.598 |
Pandora | +1.395 |
Bronze | +1.138 |
ディ | +1.122 |
Stephenson | +1.108 |
Neg logit contributions | |
ratulations | -4.588 |
forging | -4.556 |
orsi | -4.505 |
merce | -4.475 |
remember | -4.352 |
Token | 8 |
Token ID | 807 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Behavioral | +1.563 |
Pandora | +1.399 |
^^ | +1.289 |
Possible | +1.285 |
Pesh | +1.276 |
Neg logit contributions | |
ratulations | -1.930 |
forging | -1.844 |
merce | -1.840 |
orsi | -1.833 |
remember | -1.745 |
Token | of |
Token ID | 286 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Behavioral | +0.162 |
Pandora | +0.148 |
ディ | +0.137 |
^^ | +0.136 |
Bronze | +0.133 |
Neg logit contributions | |
ratulations | -0.241 |
forging | -0.236 |
orsi | -0.235 |
merce | -0.230 |
remember | -0.225 |
Token | 15 |
Token ID | 1315 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
Behavioral | +0.621 |
Pandora | +0.541 |
ディ | +0.488 |
Pesh | +0.474 |
Stephenson | +0.469 |
Neg logit contributions | |
ratulations | -1.400 |
orsi | -1.384 |
forging | -1.375 |
merce | -1.345 |
remember | -1.344 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.08e+00 |
Pos logit contributions | |
Behavioral | +0.052 |
Pandora | +0.046 |
Pesh | +0.041 |
ディ | +0.041 |
Bronze | +0.041 |
Neg logit contributions | |
forging | -0.094 |
ratulations | -0.094 |
orsi | -0.093 |
merce | -0.090 |
remember | -0.090 |
Token | : |
Token ID | 25 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
Behavioral | +4.781 |
Pandora | +4.417 |
^^ | +4.248 |
Bronze | +4.107 |
ディ | +4.017 |
Neg logit contributions | |
ratulations | -6.252 |
merce | -6.119 |
forging | -5.742 |
orsi | -5.707 |
iferation | -5.458 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Behavioral | +0.707 |
Pandora | +0.646 |
ディ | +0.609 |
Pesh | +0.598 |
Bronze | +0.592 |
Neg logit contributions | |
ratulations | -0.749 |
forging | -0.740 |
orsi | -0.734 |
remember | -0.714 |
merce | -0.710 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Behavioral | +1.023 |
Pandora | +0.939 |
ディ | +0.892 |
^^ | +0.874 |
Stephenson | +0.872 |
Neg logit contributions | |
forging | -0.934 |
ratulations | -0.934 |
orsi | -0.916 |
remember | -0.905 |
merce | -0.886 |
Token | 's |
Token ID | 338 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Behavioral | +1.009 |
Pandora | +0.914 |
ディ | +0.831 |
^^ | +0.826 |
Bronze | +0.818 |
Neg logit contributions | |
ratulations | -1.616 |
orsi | -1.575 |
forging | -1.570 |
remember | -1.546 |
merce | -1.545 |
Token | political |
Token ID | 1964 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Behavioral | +0.856 |
Pandora | +0.780 |
ディ | +0.726 |
^^ | +0.718 |
Pesh | +0.717 |
Neg logit contributions | |
ratulations | -0.946 |
orsi | -0.931 |
remember | -0.919 |
forging | -0.919 |
iferation | -0.882 |
Token | Hide |
Token ID | 10415 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
forging | +1.102 |
orsi | +1.092 |
ratulations | +1.089 |
remember | +1.085 |
iferation | +1.045 |
Neg logit contributions | |
Behavioral | -0.460 |
Pandora | -0.397 |
ディ | -0.371 |
^^ | -0.340 |
Pesh | -0.337 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Behavioral | +1.444 |
Pandora | +1.258 |
Bronze | +1.031 |
ディ | +1.025 |
^^ | +1.008 |
Neg logit contributions | |
ratulations | -4.063 |
forging | -4.039 |
orsi | -3.984 |
merce | -3.965 |
remember | -3.853 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Behavioral | +0.977 |
Pandora | +0.910 |
ディ | +0.814 |
^^ | +0.812 |
Possible | +0.809 |
Neg logit contributions | |
ratulations | -1.271 |
forging | -1.234 |
orsi | -1.230 |
merce | -1.208 |
remember | -1.193 |
Token | of |
Token ID | 286 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Behavioral | +0.675 |
Pandora | +0.617 |
ディ | +0.568 |
^^ | +0.567 |
Bronze | +0.551 |
Neg logit contributions | |
ratulations | -1.073 |
forging | -1.039 |
orsi | -1.038 |
merce | -1.031 |
remember | -0.990 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Behavioral | +0.555 |
Pandora | +0.485 |
ディ | +0.440 |
Pesh | +0.424 |
^^ | +0.422 |
Neg logit contributions | |
ratulations | -1.236 |
orsi | -1.223 |
forging | -1.216 |
remember | -1.189 |
merce | -1.188 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
Behavioral | +0.093 |
Pandora | +0.084 |
Pesh | +0.074 |
ディ | +0.074 |
Bronze | +0.073 |
Neg logit contributions | |
forging | -0.168 |
ratulations | -0.167 |
orsi | -0.166 |
merce | -0.162 |
remember | -0.161 |
Token | : |
Token ID | 25 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Behavioral | +4.710 |
Pandora | +4.379 |
^^ | +4.222 |
Bronze | +4.076 |
ディ | +3.968 |
Neg logit contributions | |
ratulations | -6.246 |
merce | -6.136 |
forging | -5.729 |
orsi | -5.711 |
iferation | -5.462 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Behavioral | +0.753 |
Pandora | +0.689 |
ディ | +0.648 |
Pesh | +0.637 |
Bronze | +0.632 |
Neg logit contributions | |
ratulations | -0.800 |
forging | -0.792 |
orsi | -0.784 |
remember | -0.762 |
merce | -0.759 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Behavioral | +0.928 |
Pandora | +0.853 |
ディ | +0.810 |
^^ | +0.795 |
Stephenson | +0.793 |
Neg logit contributions | |
forging | -0.844 |
ratulations | -0.842 |
orsi | -0.828 |
remember | -0.818 |
merce | -0.800 |
Token | 's |
Token ID | 338 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Behavioral | +1.089 |
Pandora | +0.986 |
^^ | +0.893 |
ディ | +0.892 |
Bronze | +0.885 |
Neg logit contributions | |
ratulations | -1.783 |
orsi | -1.733 |
forging | -1.729 |
merce | -1.708 |
remember | -1.697 |
Token | political |
Token ID | 1964 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
Behavioral | +0.883 |
Pandora | +0.803 |
ディ | +0.746 |
^^ | +0.740 |
Pesh | +0.739 |
Neg logit contributions | |
ratulations | -0.983 |
orsi | -0.966 |
remember | -0.955 |
forging | -0.953 |
iferation | -0.917 |
Token | Hide |
Token ID | 10415 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
forging | +0.600 |
orsi | +0.595 |
ratulations | +0.594 |
remember | +0.591 |
iferation | +0.572 |
Neg logit contributions | |
Behavioral | -0.185 |
Pandora | -0.153 |
ディ | -0.139 |
^^ | -0.124 |
Pesh | -0.123 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Behavioral | +1.576 |
Pandora | +1.376 |
Bronze | +1.114 |
ディ | +1.097 |
Stephenson | +1.090 |
Neg logit contributions | |
ratulations | -4.631 |
forging | -4.607 |
orsi | -4.541 |
merce | -4.533 |
remember | -4.393 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Behavioral | +1.380 |
Pandora | +1.277 |
Bronze | +1.166 |
^^ | +1.164 |
ディ | +1.151 |
Neg logit contributions | |
ratulations | -1.634 |
forging | -1.576 |
merce | -1.545 |
orsi | -1.537 |
iferation | -1.495 |
Token | of |
Token ID | 286 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
Behavioral | +0.651 |
Pandora | +0.595 |
ディ | +0.552 |
^^ | +0.547 |
Bronze | +0.532 |
Neg logit contributions | |
ratulations | -1.024 |
forging | -0.992 |
orsi | -0.992 |
merce | -0.981 |
remember | -0.946 |
Token | 15 |
Token ID | 1315 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
Behavioral | +0.447 |
Pandora | +0.388 |
ディ | +0.354 |
Pesh | +0.343 |
^^ | +0.339 |
Neg logit contributions | |
ratulations | -0.983 |
orsi | -0.974 |
forging | -0.970 |
remember | -0.950 |
merce | -0.941 |
Token | Photos |
Token ID | 9434 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
forging | +0.473 |
ratulations | +0.472 |
orsi | +0.469 |
remember | +0.456 |
merce | +0.454 |
Neg logit contributions | |
Behavioral | -0.262 |
Pandora | -0.235 |
Pesh | -0.210 |
ディ | -0.209 |
Bronze | -0.206 |
Token | : |
Token ID | 25 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Behavioral | +4.707 |
Pandora | +4.357 |
^^ | +4.193 |
Bronze | +4.038 |
ディ | +3.979 |
Neg logit contributions | |
ratulations | -6.266 |
merce | -6.116 |
forging | -5.738 |
orsi | -5.702 |
iferation | -5.438 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Behavioral | +0.905 |
Pandora | +0.824 |
ディ | +0.775 |
Pesh | +0.764 |
Possible | +0.758 |
Neg logit contributions | |
ratulations | -0.973 |
forging | -0.959 |
orsi | -0.950 |
remember | -0.923 |
merce | -0.923 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Behavioral | +1.127 |
Pandora | +1.030 |
ディ | +0.980 |
^^ | +0.960 |
Pesh | +0.960 |
Neg logit contributions | |
ratulations | -1.033 |
forging | -1.031 |
orsi | -1.014 |
remember | -1.000 |
merce | -0.979 |
Token | 's |
Token ID | 338 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Behavioral | +1.030 |
Pandora | +0.930 |
ディ | +0.847 |
^^ | +0.844 |
Bronze | +0.833 |
Neg logit contributions | |
ratulations | -1.643 |
orsi | -1.603 |
forging | -1.598 |
remember | -1.571 |
merce | -1.569 |
Token | political |
Token ID | 1964 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
Behavioral | +0.923 |
Pandora | +0.840 |
ディ | +0.783 |
Pesh | +0.774 |
^^ | +0.773 |
Neg logit contributions | |
ratulations | -1.023 |
orsi | -1.006 |
remember | -0.994 |
forging | -0.994 |
iferation | -0.954 |
Token | Hide |
Token ID | 10415 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
forging | +0.305 |
orsi | +0.302 |
ratulations | +0.302 |
remember | +0.300 |
iferation | +0.291 |
Neg logit contributions | |
Behavioral | -0.092 |
Pandora | -0.076 |
ディ | -0.069 |
^^ | -0.061 |
Pesh | -0.060 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Behavioral | +1.713 |
Pandora | +1.486 |
Bronze | +1.206 |
^^ | +1.179 |
ディ | +1.179 |
Neg logit contributions | |
ratulations | -5.058 |
forging | -5.015 |
merce | -4.967 |
orsi | -4.942 |
remember | -4.772 |
Token | 13 |
Token ID | 1511 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Behavioral | +1.384 |
Pandora | +1.254 |
ディ | +1.179 |
^^ | +1.159 |
Bronze | +1.135 |
Neg logit contributions | |
forging | -1.978 |
ratulations | -1.974 |
orsi | -1.954 |
remember | -1.906 |
merce | -1.897 |
Token | of |
Token ID | 286 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Behavioral | +0.654 |
Pandora | +0.599 |
^^ | +0.552 |
ディ | +0.549 |
Bronze | +0.537 |
Neg logit contributions | |
ratulations | -1.025 |
orsi | -0.996 |
forging | -0.996 |
merce | -0.985 |
remember | -0.947 |
Token | 15 |
Token ID | 1315 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Behavioral | +0.523 |
Pandora | +0.458 |
ディ | +0.417 |
Pesh | +0.403 |
^^ | +0.399 |
Neg logit contributions | |
ratulations | -1.145 |
orsi | -1.135 |
forging | -1.130 |
remember | -1.104 |
merce | -1.097 |
Token | Photos |
Token ID | 9434 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
Behavioral | +0.167 |
Pandora | +0.149 |
Pesh | +0.133 |
ディ | +0.132 |
Bronze | +0.131 |
Neg logit contributions | |
forging | -0.300 |
ratulations | -0.299 |
orsi | -0.297 |
remember | -0.289 |
merce | -0.288 |
Token | : |
Token ID | 25 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Behavioral | +4.698 |
Pandora | +4.359 |
^^ | +4.197 |
Bronze | +4.066 |
ディ | +3.943 |
Neg logit contributions | |
ratulations | -6.169 |
merce | -6.071 |
forging | -5.669 |
orsi | -5.643 |
iferation | -5.407 |
Token | Carly |
Token ID | 35982 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
Behavioral | +0.745 |
Pandora | +0.682 |
ディ | +0.639 |
Pesh | +0.630 |
Bronze | +0.626 |
Neg logit contributions | |
ratulations | -0.789 |
forging | -0.781 |
orsi | -0.772 |
remember | -0.752 |
merce | -0.746 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Behavioral | +0.758 |
Pandora | +0.697 |
ディ | +0.661 |
^^ | +0.650 |
Stephenson | +0.647 |
Neg logit contributions | |
forging | -0.687 |
ratulations | -0.685 |
orsi | -0.673 |
remember | -0.665 |
merce | -0.649 |
Token | 's |
Token ID | 338 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Behavioral | +0.902 |
Pandora | +0.817 |
ディ | +0.741 |
^^ | +0.741 |
Bronze | +0.733 |
Neg logit contributions | |
ratulations | -1.463 |
orsi | -1.423 |
forging | -1.417 |
merce | -1.399 |
remember | -1.393 |
Token | political |
Token ID | 1964 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Behavioral | +0.860 |
Pandora | +0.782 |
ディ | +0.722 |
^^ | +0.720 |
Pesh | +0.719 |
Neg logit contributions | |
ratulations | -0.969 |
orsi | -0.951 |
remember | -0.941 |
forging | -0.937 |
iferation | -0.904 |
Token | Hide |
Token ID | 10415 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
forging | +0.638 |
orsi | +0.633 |
ratulations | +0.631 |
remember | +0.629 |
iferation | +0.607 |
Neg logit contributions | |
Behavioral | -0.233 |
Pandora | -0.197 |
ディ | -0.183 |
^^ | -0.166 |
Pesh | -0.164 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Behavioral | +1.442 |
Pandora | +1.258 |
Bronze | +1.026 |
ディ | +1.019 |
^^ | +1.006 |
Neg logit contributions | |
ratulations | -4.092 |
forging | -4.065 |
orsi | -4.009 |
merce | -3.995 |
remember | -3.888 |
Token | 11 |
Token ID | 1367 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
Behavioral | +1.238 |
Pandora | +1.150 |
Bronze | +1.038 |
^^ | +1.028 |
ディ | +1.009 |
Neg logit contributions | |
ratulations | -1.720 |
forging | -1.698 |
merce | -1.673 |
orsi | -1.671 |
remember | -1.636 |
Token | of |
Token ID | 286 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Behavioral | +0.337 |
Pandora | +0.308 |
ディ | +0.284 |
^^ | +0.283 |
Bronze | +0.276 |
Neg logit contributions | |
ratulations | -0.521 |
orsi | -0.506 |
forging | -0.505 |
merce | -0.498 |
remember | -0.482 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
Behavioral | +0.536 |
Pandora | +0.469 |
ディ | +0.425 |
Pesh | +0.410 |
^^ | +0.408 |
Neg logit contributions | |
ratulations | -1.197 |
orsi | -1.184 |
forging | -1.177 |
merce | -1.150 |
remember | -1.149 |
Token | Photos |
Token ID | 9434 |
Feature activation | +6.95e+00 |
Pos logit contributions | |
Behavioral | +0.023 |
Pandora | +0.020 |
Pesh | +0.018 |
ディ | +0.018 |
^^ | +0.018 |
Neg logit contributions | |
forging | -0.041 |
ratulations | -0.041 |
orsi | -0.040 |
remember | -0.039 |
merce | -0.039 |
Token | : |
Token ID | 25 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Behavioral | +4.665 |
Pandora | +4.341 |
^^ | +4.177 |
Bronze | +4.033 |
ディ | +3.923 |
Neg logit contributions | |
ratulations | -6.146 |
merce | -6.038 |
forging | -5.647 |
orsi | -5.621 |
iferation | -5.383 |
Token | Carly |
Token ID | 35982 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Behavioral | +0.808 |
Pandora | +0.739 |
ディ | +0.695 |
Pesh | +0.683 |
Bronze | +0.678 |
Neg logit contributions | |
ratulations | -0.865 |
forging | -0.855 |
orsi | -0.847 |
remember | -0.823 |
merce | -0.820 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Behavioral | +0.935 |
Pandora | +0.859 |
ディ | +0.816 |
^^ | +0.801 |
Stephenson | +0.798 |
Neg logit contributions | |
forging | -0.853 |
ratulations | -0.852 |
orsi | -0.836 |
remember | -0.826 |
merce | -0.809 |
Token | 's |
Token ID | 338 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Behavioral | +0.875 |
Pandora | +0.793 |
ディ | +0.721 |
^^ | +0.718 |
Bronze | +0.711 |
Neg logit contributions | |
ratulations | -1.405 |
orsi | -1.367 |
forging | -1.364 |
merce | -1.342 |
remember | -1.339 |
Token | political |
Token ID | 1964 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
Behavioral | +0.923 |
Pandora | +0.840 |
ディ | +0.777 |
^^ | +0.773 |
Pesh | +0.772 |
Neg logit contributions | |
ratulations | -1.040 |
orsi | -1.022 |
remember | -1.009 |
forging | -1.005 |
iferation | -0.970 |
Token | Hide |
Token ID | 10415 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
forging | +1.426 |
orsi | +1.411 |
remember | +1.403 |
ratulations | +1.401 |
iferation | +1.335 |
Neg logit contributions | |
Behavioral | -1.092 |
Pandora | -0.990 |
ディ | -0.954 |
^^ | -0.899 |
Pesh | -0.893 |
Token | Caption |
Token ID | 11260 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Behavioral | +1.126 |
Pandora | +0.986 |
ディ | +0.924 |
^^ | +0.858 |
Pesh | +0.853 |
Neg logit contributions | |
forging | -2.341 |
orsi | -2.322 |
ratulations | -2.318 |
remember | -2.303 |
iferation | -2.216 |
Token | 4 |
Token ID | 604 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Behavioral | +0.235 |
Pandora | +0.213 |
ディ | +0.200 |
^^ | +0.192 |
Pesh | +0.191 |
Neg logit contributions | |
forging | -0.304 |
ratulations | -0.304 |
orsi | -0.301 |
remember | -0.296 |
iferation | -0.286 |
Token | of |
Token ID | 286 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Behavioral | +0.137 |
Pandora | +0.123 |
ディ | +0.115 |
^^ | +0.112 |
Pesh | +0.112 |
Neg logit contributions | |
ratulations | -0.190 |
forging | -0.187 |
orsi | -0.185 |
remember | -0.180 |
merce | -0.179 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Behavioral | +0.723 |
Pandora | +0.665 |
ディ | +0.616 |
Pesh | +0.599 |
Bronze | +0.597 |
Neg logit contributions | |
ratulations | -0.928 |
forging | -0.912 |
orsi | -0.912 |
merce | -0.889 |
remember | -0.888 |
Token | Photos |
Token ID | 9434 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
forging | +0.201 |
orsi | +0.199 |
ratulations | +0.199 |
remember | +0.197 |
iferation | +0.189 |
Neg logit contributions | |
Behavioral | -0.132 |
Pandora | -0.118 |
ディ | -0.112 |
^^ | -0.106 |
Pesh | -0.106 |
Token | : |
Token ID | 25 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Behavioral | +4.949 |
Pandora | +4.507 |
Bronze | +4.203 |
^^ | +4.179 |
Possible | +4.172 |
Neg logit contributions | |
ratulations | -5.226 |
merce | -4.992 |
forging | -4.845 |
orsi | -4.805 |
iferation | -4.602 |
Token | Carly |
Token ID | 35982 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
Behavioral | +1.184 |
Pandora | +1.075 |
ディ | +1.008 |
Pesh | +0.974 |
^^ | +0.963 |
Neg logit contributions | |
forging | -1.500 |
ratulations | -1.495 |
orsi | -1.488 |
remember | -1.464 |
iferation | -1.408 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
Behavioral | +0.768 |
Pandora | +0.712 |
ディ | +0.683 |
Pesh | +0.659 |
^^ | +0.657 |
Neg logit contributions | |
forging | -0.615 |
orsi | -0.608 |
ratulations | -0.608 |
remember | -0.605 |
iferation | -0.570 |
Token | 's |
Token ID | 338 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Behavioral | +0.696 |
Pandora | +0.639 |
ディ | +0.605 |
Pesh | +0.581 |
^^ | +0.581 |
Neg logit contributions | |
forging | -0.756 |
orsi | -0.755 |
ratulations | -0.753 |
remember | -0.748 |
iferation | -0.715 |
Token | political |
Token ID | 1964 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Behavioral | +1.566 |
Pandora | +1.454 |
ディ | +1.375 |
Pesh | +1.339 |
Bronze | +1.330 |
Neg logit contributions | |
ratulations | -1.318 |
orsi | -1.317 |
forging | -1.306 |
remember | -1.295 |
sbm | -1.230 |
Token | 13 |
Token ID | 1511 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Behavioral | +1.521 |
Pandora | +1.379 |
ディ | +1.254 |
^^ | +1.252 |
Bronze | +1.241 |
Neg logit contributions | |
ratulations | -2.126 |
orsi | -2.095 |
forging | -2.094 |
merce | -2.039 |
remember | -2.028 |
Token | , |
Token ID | 11 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Behavioral | +1.010 |
Pandora | +0.922 |
ディ | +0.855 |
^^ | +0.839 |
Bronze | +0.813 |
Neg logit contributions | |
ratulations | -1.606 |
forging | -1.592 |
orsi | -1.587 |
merce | -1.545 |
remember | -1.528 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Behavioral | +1.547 |
Pandora | +1.391 |
ディ | +1.297 |
^^ | +1.256 |
Pesh | +1.239 |
Neg logit contributions | |
forging | -2.421 |
ratulations | -2.388 |
orsi | -2.387 |
remember | -2.358 |
iferation | -2.292 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Behavioral | +0.998 |
Pandora | +0.898 |
^^ | +0.808 |
ディ | +0.790 |
Pesh | +0.779 |
Neg logit contributions | |
ratulations | -1.844 |
forging | -1.820 |
orsi | -1.801 |
merce | -1.779 |
iferation | -1.740 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Behavioral | +0.689 |
Pandora | +0.618 |
^^ | +0.564 |
Bronze | +0.540 |
ディ | +0.538 |
Neg logit contributions | |
ratulations | -1.348 |
forging | -1.325 |
orsi | -1.317 |
merce | -1.298 |
iferation | -1.269 |
Token | Subject |
Token ID | 19776 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
Behavioral | +0.638 |
Pandora | +0.564 |
^^ | +0.534 |
ディ | +0.488 |
IRD | +0.448 |
Neg logit contributions | |
ratulations | -1.868 |
forging | -1.856 |
orsi | -1.842 |
merce | -1.775 |
deadlines | -1.756 |
Token | : |
Token ID | 25 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Behavioral | +4.458 |
Pandora | +4.195 |
^^ | +3.965 |
Possible | +3.815 |
Bronze | +3.805 |
Neg logit contributions | |
ratulations | -5.191 |
forging | -4.930 |
orsi | -4.884 |
merce | -4.860 |
iferation | -4.718 |
Token | boys |
Token ID | 6510 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Behavioral | +2.326 |
Pandora | +2.123 |
ディ | +1.950 |
^^ | +1.933 |
Pesh | +1.907 |
Neg logit contributions | |
orsi | -2.861 |
forging | -2.858 |
ratulations | -2.843 |
remember | -2.790 |
iferation | -2.718 |
Token | beware |
Token ID | 40600 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Behavioral | +0.161 |
Pandora | +0.147 |
ディ | +0.140 |
^^ | +0.135 |
Pesh | +0.133 |
Neg logit contributions | |
forging | -0.184 |
orsi | -0.182 |
ratulations | -0.182 |
remember | -0.179 |
iferation | -0.173 |
Token | This |
Token ID | 770 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
Behavioral | +0.224 |
Pandora | +0.204 |
ディ | +0.193 |
^^ | +0.188 |
Pesh | +0.185 |
Neg logit contributions | |
forging | -0.264 |
orsi | -0.262 |
ratulations | -0.261 |
remember | -0.258 |
iferation | -0.248 |
Token | film |
Token ID | 2646 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Behavioral | +0.376 |
Pandora | +0.344 |
ディ | +0.328 |
^^ | +0.316 |
Pesh | +0.313 |
Neg logit contributions | |
forging | -0.421 |
orsi | -0.417 |
ratulations | -0.416 |
remember | -0.412 |
iferation | -0.393 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Behavioral | +1.079 |
Pandora | +0.975 |
ディ | +0.902 |
^^ | +0.889 |
Pesh | +0.880 |
Neg logit contributions | |
ratulations | -1.491 |
orsi | -1.479 |
forging | -1.476 |
remember | -1.430 |
merce | -1.417 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Behavioral | +0.691 |
Pandora | +0.626 |
^^ | +0.579 |
ディ | +0.577 |
Bronze | +0.560 |
Neg logit contributions | |
ratulations | -1.132 |
forging | -1.116 |
orsi | -1.114 |
merce | -1.088 |
remember | -1.058 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Behavioral | +1.098 |
Pandora | +0.974 |
ディ | +0.873 |
Bronze | +0.869 |
Pesh | +0.866 |
Neg logit contributions | |
ratulations | -1.655 |
orsi | -1.650 |
forging | -1.647 |
remember | -1.608 |
merce | -1.590 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Behavioral | +0.585 |
Pandora | +0.527 |
ディ | +0.481 |
^^ | +0.478 |
Bronze | +0.461 |
Neg logit contributions | |
ratulations | -1.037 |
forging | -1.028 |
orsi | -1.020 |
merce | -0.998 |
iferation | -0.983 |
Token |
|
Token ID | 198 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Behavioral | +0.710 |
Pandora | +0.635 |
^^ | +0.583 |
ディ | +0.562 |
Bronze | +0.557 |
Neg logit contributions | |
ratulations | -1.383 |
forging | -1.359 |
orsi | -1.353 |
merce | -1.331 |
iferation | -1.302 |
Token | Subject |
Token ID | 19776 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
Behavioral | +0.652 |
Pandora | +0.573 |
^^ | +0.548 |
ディ | +0.537 |
IRD | +0.488 |
Neg logit contributions | |
ratulations | -1.823 |
forging | -1.807 |
orsi | -1.783 |
merce | -1.751 |
iferation | -1.707 |
Token | : |
Token ID | 25 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Behavioral | +4.032 |
Pandora | +3.770 |
^^ | +3.650 |
ディ | +3.498 |
Possible | +3.436 |
Neg logit contributions | |
ratulations | -4.955 |
forging | -4.716 |
merce | -4.702 |
orsi | -4.683 |
iferation | -4.419 |
Token | User |
Token ID | 11787 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Behavioral | +2.060 |
Pandora | +1.889 |
ディ | +1.743 |
^^ | +1.716 |
Pesh | +1.698 |
Neg logit contributions | |
orsi | -2.492 |
forging | -2.492 |
ratulations | -2.474 |
remember | -2.431 |
iferation | -2.367 |
Token | reviews |
Token ID | 8088 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
forging | +0.844 |
orsi | +0.834 |
ratulations | +0.832 |
remember | +0.827 |
iferation | +0.786 |
Neg logit contributions | |
Behavioral | -0.739 |
Pandora | -0.675 |
ディ | -0.650 |
^^ | -0.617 |
Pesh | -0.616 |
Token | are |
Token ID | 389 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
forging | +0.126 |
orsi | +0.125 |
ratulations | +0.124 |
remember | +0.123 |
iferation | +0.118 |
Neg logit contributions | |
Behavioral | -0.104 |
Pandora | -0.095 |
ディ | -0.091 |
^^ | -0.087 |
Pesh | -0.086 |
Token | a |
Token ID | 257 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Behavioral | +0.516 |
Pandora | +0.471 |
ディ | +0.447 |
^^ | +0.429 |
Pesh | +0.426 |
Neg logit contributions | |
forging | -0.622 |
orsi | -0.618 |
ratulations | -0.616 |
remember | -0.610 |
iferation | -0.584 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Behavioral | +1.555 |
Pandora | +1.417 |
ディ | +1.289 |
^^ | +1.288 |
Bronze | +1.278 |
Neg logit contributions | |
ratulations | -2.186 |
orsi | -2.157 |
forging | -2.150 |
merce | -2.091 |
iferation | -2.070 |
Token | , |
Token ID | 11 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Behavioral | +0.931 |
Pandora | +0.851 |
^^ | +0.783 |
ディ | +0.777 |
Bronze | +0.756 |
Neg logit contributions | |
ratulations | -1.597 |
forging | -1.571 |
orsi | -1.569 |
merce | -1.551 |
iferation | -1.493 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Behavioral | +1.618 |
Pandora | +1.467 |
ディ | +1.399 |
^^ | +1.330 |
Pesh | +1.324 |
Neg logit contributions | |
forging | -2.087 |
orsi | -2.067 |
ratulations | -2.060 |
remember | -2.047 |
iferation | -1.953 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Behavioral | +0.878 |
Pandora | +0.791 |
^^ | +0.718 |
ディ | +0.715 |
Bronze | +0.687 |
Neg logit contributions | |
ratulations | -1.614 |
forging | -1.602 |
orsi | -1.585 |
merce | -1.562 |
iferation | -1.531 |
Token |
|
Token ID | 198 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Behavioral | +0.913 |
Pandora | +0.816 |
^^ | +0.751 |
ディ | +0.716 |
Bronze | +0.715 |
Neg logit contributions | |
ratulations | -1.836 |
forging | -1.800 |
orsi | -1.794 |
merce | -1.772 |
iferation | -1.728 |
Token | Subject |
Token ID | 19776 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
Behavioral | +0.758 |
Pandora | +0.675 |
^^ | +0.649 |
ディ | +0.624 |
IRD | +0.558 |
Neg logit contributions | |
ratulations | -2.291 |
forging | -2.272 |
orsi | -2.244 |
merce | -2.212 |
iferation | -2.149 |
Token | : |
Token ID | 25 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
Behavioral | +3.997 |
Pandora | +3.742 |
^^ | +3.596 |
ディ | +3.475 |
Possible | +3.417 |
Neg logit contributions | |
ratulations | -4.908 |
forging | -4.675 |
merce | -4.656 |
orsi | -4.628 |
iferation | -4.380 |
Token | Que |
Token ID | 4670 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
Behavioral | +2.068 |
Pandora | +1.894 |
ディ | +1.749 |
^^ | +1.723 |
Pesh | +1.703 |
Neg logit contributions | |
orsi | -2.528 |
forging | -2.527 |
ratulations | -2.507 |
remember | -2.466 |
iferation | -2.398 |
Token | er |
Token ID | 263 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
forging | +0.292 |
orsi | +0.288 |
ratulations | +0.287 |
remember | +0.285 |
iferation | +0.267 |
Neg logit contributions | |
Behavioral | -0.395 |
Pandora | -0.367 |
ディ | -0.356 |
Pesh | -0.341 |
^^ | -0.340 |
Token | magnet |
Token ID | 19972 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Behavioral | +0.305 |
Pandora | +0.278 |
ディ | +0.264 |
^^ | +0.254 |
Pesh | +0.252 |
Neg logit contributions | |
forging | -0.363 |
orsi | -0.360 |
ratulations | -0.359 |
remember | -0.355 |
iferation | -0.340 |
Token | ? |
Token ID | 30 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
forging | +1.400 |
orsi | +1.381 |
ratulations | +1.381 |
remember | +1.375 |
iferation | +1.307 |
Neg logit contributions | |
Behavioral | -1.185 |
Pandora | -1.077 |
ディ | -1.044 |
Pesh | -0.981 |
^^ | -0.981 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Behavioral | +0.634 |
Pandora | +0.578 |
ディ | +0.535 |
^^ | +0.527 |
Pesh | +0.519 |
Neg logit contributions | |
ratulations | -0.837 |
forging | -0.831 |
orsi | -0.827 |
remember | -0.803 |
merce | -0.795 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Behavioral | +0.684 |
Pandora | +0.622 |
ディ | +0.578 |
^^ | +0.575 |
Bronze | +0.555 |
Neg logit contributions | |
ratulations | -1.117 |
orsi | -1.101 |
forging | -1.101 |
merce | -1.074 |
remember | -1.045 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
Behavioral | +1.121 |
Pandora | +1.017 |
ディ | +0.971 |
^^ | +0.924 |
Pesh | +0.919 |
Neg logit contributions | |
forging | -1.423 |
orsi | -1.409 |
ratulations | -1.405 |
remember | -1.395 |
iferation | -1.333 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Behavioral | +0.438 |
Pandora | +0.397 |
ディ | +0.360 |
^^ | +0.359 |
Bronze | +0.345 |
Neg logit contributions | |
ratulations | -0.775 |
forging | -0.770 |
orsi | -0.763 |
merce | -0.744 |
remember | -0.734 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Behavioral | +0.644 |
Pandora | +0.577 |
^^ | +0.528 |
ディ | +0.509 |
Bronze | +0.506 |
Neg logit contributions | |
ratulations | -1.254 |
forging | -1.232 |
orsi | -1.227 |
merce | -1.204 |
iferation | -1.182 |
Token | Subject |
Token ID | 19776 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
Behavioral | +0.547 |
Pandora | +0.486 |
^^ | +0.474 |
ディ | +0.449 |
IRD | +0.396 |
Neg logit contributions | |
ratulations | -1.737 |
forging | -1.714 |
orsi | -1.699 |
merce | -1.663 |
iferation | -1.625 |
Token | : |
Token ID | 25 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
Behavioral | +4.036 |
Pandora | +3.773 |
^^ | +3.626 |
ディ | +3.488 |
Possible | +3.446 |
Neg logit contributions | |
ratulations | -4.857 |
forging | -4.631 |
merce | -4.588 |
orsi | -4.580 |
iferation | -4.344 |
Token | R |
Token ID | 371 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Behavioral | +2.133 |
Pandora | +1.945 |
ディ | +1.802 |
^^ | +1.776 |
Pesh | +1.755 |
Neg logit contributions | |
orsi | -2.573 |
forging | -2.571 |
ratulations | -2.551 |
remember | -2.513 |
iferation | -2.442 |
Token | iff |
Token ID | 733 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
Behavioral | +0.243 |
Pandora | +0.225 |
ディ | +0.216 |
^^ | +0.209 |
Pesh | +0.207 |
Neg logit contributions | |
forging | -0.216 |
orsi | -0.213 |
ratulations | -0.212 |
remember | -0.210 |
iferation | -0.199 |
Token | Tra |
Token ID | 15721 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Behavioral | +0.601 |
Pandora | +0.552 |
ディ | +0.528 |
^^ | +0.511 |
Pesh | +0.505 |
Neg logit contributions | |
forging | -0.587 |
ratulations | -0.580 |
orsi | -0.580 |
remember | -0.575 |
iferation | -0.548 |
Token | x |
Token ID | 87 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Behavioral | +0.245 |
Pandora | +0.220 |
ディ | +0.209 |
^^ | +0.196 |
Pesh | +0.195 |
Neg logit contributions | |
forging | -0.385 |
orsi | -0.381 |
ratulations | -0.380 |
remember | -0.378 |
iferation | -0.362 |
Token | 5 |
Token ID | 642 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Behavioral | +1.454 |
Pandora | +1.321 |
ディ | +1.206 |
^^ | +1.196 |
Bronze | +1.189 |
Neg logit contributions | |
ratulations | -2.041 |
orsi | -2.015 |
forging | -2.009 |
merce | -1.945 |
remember | -1.944 |
Token | , |
Token ID | 11 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Behavioral | +1.313 |
Pandora | +1.190 |
^^ | +1.102 |
ディ | +1.085 |
Bronze | +1.065 |
Neg logit contributions | |
ratulations | -2.263 |
orsi | -2.226 |
forging | -2.223 |
merce | -2.194 |
iferation | -2.105 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Behavioral | +1.361 |
Pandora | +1.237 |
ディ | +1.188 |
^^ | +1.125 |
Pesh | +1.121 |
Neg logit contributions | |
forging | -1.718 |
orsi | -1.698 |
ratulations | -1.696 |
remember | -1.684 |
iferation | -1.609 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Behavioral | +0.789 |
Pandora | +0.709 |
^^ | +0.643 |
ディ | +0.640 |
Bronze | +0.622 |
Neg logit contributions | |
ratulations | -1.432 |
forging | -1.414 |
orsi | -1.408 |
merce | -1.379 |
iferation | -1.354 |
Token |
|
Token ID | 198 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Behavioral | +0.906 |
Pandora | +0.807 |
^^ | +0.744 |
ディ | +0.711 |
Bronze | +0.710 |
Neg logit contributions | |
ratulations | -1.819 |
forging | -1.784 |
orsi | -1.777 |
merce | -1.754 |
iferation | -1.711 |
Token | Subject |
Token ID | 19776 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
Behavioral | +0.768 |
Pandora | +0.672 |
^^ | +0.650 |
ディ | +0.628 |
IRD | +0.574 |
Neg logit contributions | |
ratulations | -2.208 |
forging | -2.186 |
orsi | -2.155 |
merce | -2.127 |
iferation | -2.069 |
Token | : |
Token ID | 25 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
Behavioral | +3.938 |
Pandora | +3.679 |
^^ | +3.583 |
ディ | +3.445 |
Bronze | +3.364 |
Neg logit contributions | |
ratulations | -4.834 |
merce | -4.596 |
forging | -4.595 |
orsi | -4.567 |
iferation | -4.307 |
Token | Que |
Token ID | 4670 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
Behavioral | +2.025 |
Pandora | +1.853 |
ディ | +1.710 |
^^ | +1.684 |
Pesh | +1.663 |
Neg logit contributions | |
orsi | -2.464 |
forging | -2.460 |
ratulations | -2.442 |
remember | -2.402 |
iferation | -2.340 |
Token | ers |
Token ID | 364 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
forging | +0.555 |
orsi | +0.546 |
ratulations | +0.543 |
remember | +0.539 |
iferation | +0.506 |
Neg logit contributions | |
Behavioral | -0.813 |
Pandora | -0.759 |
ディ | -0.740 |
Pesh | -0.708 |
^^ | -0.702 |
Token | are |
Token ID | 389 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Behavioral | +0.280 |
Pandora | +0.255 |
ディ | +0.242 |
^^ | +0.234 |
Pesh | +0.231 |
Neg logit contributions | |
forging | -0.328 |
orsi | -0.325 |
ratulations | -0.325 |
remember | -0.320 |
iferation | -0.307 |
Token | Here |
Token ID | 3423 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Behavioral | +0.227 |
Pandora | +0.207 |
ディ | +0.196 |
^^ | +0.189 |
Pesh | +0.187 |
Neg logit contributions | |
forging | -0.266 |
orsi | -0.264 |
ratulations | -0.264 |
remember | -0.261 |
iferation | -0.250 |
Token | predatory |
Token ID | 35341 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Behavioral | +0.061 |
Pandora | +0.056 |
ディ | +0.053 |
^^ | +0.051 |
Pesh | +0.051 |
Neg logit contributions | |
forging | -0.074 |
orsi | -0.073 |
ratulations | -0.073 |
remember | -0.072 |
iferation | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
forging | +1.294 |
orsi | +1.272 |
ratulations | +1.267 |
remember | +1.260 |
deadlines | +1.200 |
Neg logit contributions | |
Behavioral | -1.168 |
Pandora | -1.062 |
ディ | -1.032 |
Pesh | -0.974 |
^^ | -0.973 |
Token | � |
Token ID | 564 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Behavioral | +0.637 |
Pandora | +0.579 |
ディ | +0.547 |
^^ | +0.526 |
Pesh | +0.521 |
Neg logit contributions | |
forging | -0.836 |
ratulations | -0.835 |
orsi | -0.833 |
remember | -0.822 |
iferation | -0.794 |
Token | � |
Token ID | 250 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
Behavioral | +0.292 |
Pandora | +0.267 |
ディ | +0.257 |
^^ | +0.244 |
Pesh | +0.244 |
Neg logit contributions | |
forging | -0.312 |
orsi | -0.309 |
ratulations | -0.308 |
remember | -0.306 |
iferation | -0.290 |
Token | c |
Token ID | 66 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
forging | +0.377 |
orsi | +0.372 |
ratulations | +0.372 |
remember | +0.366 |
iferation | +0.349 |
Neg logit contributions | |
Behavioral | -0.428 |
Pandora | -0.396 |
ディ | -0.382 |
^^ | -0.367 |
Pesh | -0.365 |
Token | ou |
Token ID | 280 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
forging | +0.126 |
orsi | +0.125 |
ratulations | +0.124 |
remember | +0.123 |
iferation | +0.116 |
Neg logit contributions | |
Behavioral | -0.149 |
Pandora | -0.138 |
ディ | -0.133 |
^^ | -0.128 |
Pesh | -0.128 |
Token | gar |
Token ID | 4563 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
Behavioral | +4.522 |
Pandora | +4.252 |
ディ | +4.037 |
^^ | +3.991 |
Stephenson | +3.894 |
Neg logit contributions | |
forging | -3.539 |
orsi | -3.445 |
remember | -3.432 |
ratulations | -3.418 |
iferation | -3.290 |
Token | � |
Token ID | 447 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
forging | +0.530 |
orsi | +0.524 |
ratulations | +0.522 |
remember | +0.519 |
iferation | +0.492 |
Neg logit contributions | |
Behavioral | -0.461 |
Pandora | -0.419 |
ディ | -0.403 |
Pesh | -0.382 |
^^ | -0.382 |
Token | � |
Token ID | 251 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
forging | +0.285 |
orsi | +0.282 |
ratulations | +0.281 |
remember | +0.279 |
iferation | +0.267 |
Neg logit contributions | |
Behavioral | -0.241 |
Pandora | -0.220 |
ディ | -0.211 |
Pesh | -0.201 |
^^ | -0.200 |
Token | type |
Token ID | 2099 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
forging | +0.541 |
orsi | +0.534 |
ratulations | +0.532 |
remember | +0.529 |
iferation | +0.504 |
Neg logit contributions | |
Behavioral | -0.471 |
Pandora | -0.430 |
ディ | -0.413 |
^^ | -0.393 |
Pesh | -0.391 |
Token | of |
Token ID | 286 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
Behavioral | +0.093 |
Pandora | +0.085 |
ディ | +0.081 |
^^ | +0.078 |
Pesh | +0.077 |
Neg logit contributions | |
forging | -0.106 |
orsi | -0.105 |
ratulations | -0.104 |
remember | -0.103 |
iferation | -0.099 |
Token | angs |
Token ID | 27725 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Behavioral | +0.803 |
Pandora | +0.746 |
ディ | +0.713 |
^^ | +0.694 |
Pesh | +0.684 |
Neg logit contributions | |
forging | -0.742 |
orsi | -0.730 |
ratulations | -0.728 |
remember | -0.722 |
deadlines | -0.683 |
Token | of |
Token ID | 286 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
forging | +0.117 |
orsi | +0.116 |
ratulations | +0.116 |
remember | +0.115 |
iferation | +0.110 |
Neg logit contributions | |
Behavioral | -0.099 |
Pandora | -0.091 |
ディ | -0.087 |
^^ | -0.083 |
Pesh | -0.082 |
Token | dis |
Token ID | 595 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Behavioral | +0.062 |
Pandora | +0.057 |
ディ | +0.054 |
^^ | +0.052 |
Pesh | +0.052 |
Neg logit contributions | |
orsi | -0.068 |
forging | -0.068 |
ratulations | -0.068 |
remember | -0.067 |
iferation | -0.064 |
Token | pri |
Token ID | 3448 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
Behavioral | +1.728 |
Pandora | +1.608 |
ディ | +1.554 |
^^ | +1.508 |
Pesh | +1.481 |
Neg logit contributions | |
forging | -1.477 |
orsi | -1.460 |
ratulations | -1.447 |
remember | -1.397 |
iferation | -1.356 |
Token | z |
Token ID | 89 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Behavioral | +0.737 |
Pandora | +0.677 |
ディ | +0.651 |
^^ | +0.641 |
Pesh | +0.626 |
Neg logit contributions | |
forging | -0.739 |
orsi | -0.720 |
ratulations | -0.716 |
remember | -0.711 |
sbm | -0.682 |
Token | 'd |
Token ID | 1549 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Behavioral | +1.211 |
Pandora | +1.129 |
ディ | +1.077 |
^^ | +1.063 |
Pesh | +1.045 |
Neg logit contributions | |
forging | -1.054 |
orsi | -1.045 |
ratulations | -1.035 |
remember | -1.023 |
sbm | -0.977 |
Token | love |
Token ID | 1842 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Behavioral | +3.981 |
Pandora | +3.811 |
Bronze | +3.480 |
^^ | +3.465 |
Pesh | +3.430 |
Neg logit contributions | |
orsi | -3.992 |
ratulations | -3.931 |
remember | -3.845 |
forging | -3.783 |
sbm | -3.760 |
Token | , |
Token ID | 11 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Behavioral | +0.808 |
Pandora | +0.749 |
ディ | +0.697 |
^^ | +0.679 |
Pesh | +0.664 |
Neg logit contributions | |
ratulations | -1.034 |
orsi | -1.027 |
forging | -1.021 |
remember | -1.009 |
sbm | -0.974 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Behavioral | +1.859 |
Pandora | +1.700 |
ディ | +1.614 |
^^ | +1.545 |
Pesh | +1.533 |
Neg logit contributions | |
forging | -2.282 |
orsi | -2.275 |
ratulations | -2.274 |
remember | -2.244 |
iferation | -2.148 |
Token | law |
Token ID | 1099 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
Behavioral | +1.628 |
Pandora | +1.520 |
ディ | +1.423 |
^^ | +1.385 |
Pesh | +1.382 |
Neg logit contributions | |
orsi | -1.674 |
ratulations | -1.670 |
forging | -1.657 |
remember | -1.647 |
sbm | -1.574 |
Token | 's |
Token ID | 338 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Behavioral | +0.525 |
Pandora | +0.481 |
ディ | +0.458 |
^^ | +0.438 |
Pesh | +0.435 |
Neg logit contributions | |
forging | -0.627 |
orsi | -0.623 |
ratulations | -0.621 |
remember | -0.616 |
iferation | -0.589 |
Token | 9 |
Token ID | 860 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Behavioral | +1.249 |
Pandora | +1.133 |
ディ | +1.041 |
^^ | +1.033 |
Bronze | +1.022 |
Neg logit contributions | |
ratulations | -1.714 |
forging | -1.695 |
orsi | -1.692 |
remember | -1.633 |
merce | -1.632 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ratulations | +0.116 |
forging | +0.115 |
orsi | +0.115 |
merce | +0.111 |
remember | +0.110 |
Neg logit contributions | |
Behavioral | -0.076 |
Pandora | -0.069 |
ディ | -0.065 |
^^ | -0.064 |
Bronze | -0.062 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Behavioral | +1.362 |
Pandora | +1.235 |
ディ | +1.173 |
^^ | +1.118 |
Pesh | +1.111 |
Neg logit contributions | |
forging | -1.791 |
orsi | -1.774 |
ratulations | -1.767 |
remember | -1.756 |
iferation | -1.678 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Behavioral | +0.659 |
Pandora | +0.594 |
^^ | +0.540 |
ディ | +0.539 |
Bronze | +0.518 |
Neg logit contributions | |
ratulations | -1.182 |
forging | -1.174 |
orsi | -1.164 |
merce | -1.141 |
iferation | -1.123 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Behavioral | +0.812 |
Pandora | +0.725 |
^^ | +0.667 |
ディ | +0.639 |
Bronze | +0.637 |
Neg logit contributions | |
ratulations | -1.606 |
forging | -1.576 |
orsi | -1.571 |
merce | -1.548 |
iferation | -1.513 |
Token | Subject |
Token ID | 19776 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Behavioral | +0.659 |
Pandora | +0.583 |
^^ | +0.569 |
ディ | +0.545 |
IRD | +0.483 |
Neg logit contributions | |
ratulations | -2.034 |
forging | -2.019 |
orsi | -1.993 |
merce | -1.961 |
iferation | -1.912 |
Token | : |
Token ID | 25 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Behavioral | +3.795 |
Pandora | +3.556 |
^^ | +3.425 |
ディ | +3.305 |
Possible | +3.246 |
Neg logit contributions | |
ratulations | -4.529 |
forging | -4.334 |
merce | -4.287 |
orsi | -4.282 |
iferation | -4.052 |
Token | R |
Token ID | 371 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Behavioral | +2.021 |
Pandora | +1.849 |
ディ | +1.712 |
^^ | +1.684 |
Pesh | +1.663 |
Neg logit contributions | |
forging | -2.471 |
orsi | -2.470 |
ratulations | -2.451 |
remember | -2.414 |
iferation | -2.345 |
Token | ipe |
Token ID | 3757 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
forging | +0.091 |
orsi | +0.090 |
ratulations | +0.090 |
remember | +0.089 |
iferation | +0.084 |
Neg logit contributions | |
Behavioral | -0.117 |
Pandora | -0.109 |
ディ | -0.105 |
^^ | -0.101 |
Pesh | -0.101 |
Token | for |
Token ID | 329 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Behavioral | +0.506 |
Pandora | +0.462 |
ディ | +0.438 |
^^ | +0.422 |
Pesh | +0.418 |
Neg logit contributions | |
forging | -0.601 |
orsi | -0.597 |
ratulations | -0.592 |
remember | -0.587 |
iferation | -0.562 |
Token | M |
Token ID | 337 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Behavioral | +0.264 |
Pandora | +0.242 |
ディ | +0.230 |
^^ | +0.220 |
Pesh | +0.219 |
Neg logit contributions | |
forging | -0.303 |
orsi | -0.301 |
ratulations | -0.300 |
remember | -0.297 |
iferation | -0.285 |
Token | what |
Token ID | 644 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Behavioral | +0.389 |
Pandora | +0.357 |
ディ | +0.338 |
^^ | +0.322 |
Pesh | +0.322 |
Neg logit contributions | |
forging | -0.461 |
ratulations | -0.460 |
orsi | -0.460 |
remember | -0.453 |
iferation | -0.436 |
Token | happens |
Token ID | 4325 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
Behavioral | +0.986 |
Pandora | +0.906 |
ディ | +0.840 |
Stephenson | +0.811 |
^^ | +0.811 |
Neg logit contributions | |
forging | -1.222 |
ratulations | -1.220 |
orsi | -1.219 |
remember | -1.203 |
iferation | -1.166 |
Token | when |
Token ID | 618 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Behavioral | +0.416 |
Pandora | +0.378 |
ディ | +0.349 |
^^ | +0.335 |
Pesh | +0.332 |
Neg logit contributions | |
ratulations | -0.679 |
forging | -0.677 |
orsi | -0.675 |
remember | -0.668 |
iferation | -0.646 |
Token | the |
Token ID | 262 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
forging | +0.207 |
orsi | +0.206 |
ratulations | +0.206 |
remember | +0.204 |
iferation | +0.196 |
Neg logit contributions | |
Behavioral | -0.181 |
Pandora | -0.166 |
ディ | -0.157 |
^^ | -0.151 |
Pesh | -0.151 |
Token | First |
Token ID | 3274 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Behavioral | +0.337 |
Pandora | +0.311 |
ディ | +0.293 |
Pesh | +0.286 |
^^ | +0.284 |
Neg logit contributions | |
orsi | -0.325 |
ratulations | -0.325 |
forging | -0.325 |
remember | -0.320 |
iferation | -0.308 |
Token | Family |
Token ID | 7884 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
Behavioral | +1.297 |
Pandora | +1.163 |
ディ | +1.113 |
^^ | +1.060 |
Pesh | +1.057 |
Neg logit contributions | |
forging | -1.630 |
orsi | -1.622 |
ratulations | -1.616 |
remember | -1.595 |
iferation | -1.537 |
Token | opens |
Token ID | 9808 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
Behavioral | +3.659 |
Pandora | +3.374 |
Bronze | +3.036 |
Pesh | +3.017 |
^^ | +3.001 |
Neg logit contributions | |
ratulations | -4.269 |
orsi | -4.216 |
remember | -4.173 |
forging | -4.141 |
iferation | -4.107 |
Token | the |
Token ID | 262 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
Behavioral | +0.596 |
Pandora | +0.555 |
ディ | +0.508 |
Pesh | +0.494 |
^^ | +0.493 |
Neg logit contributions | |
orsi | -0.729 |
ratulations | -0.728 |
forging | -0.726 |
remember | -0.718 |
iferation | -0.695 |
Token | White |
Token ID | 2635 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Behavioral | +0.606 |
Pandora | +0.565 |
ディ | +0.527 |
^^ | +0.512 |
Pesh | +0.512 |
Neg logit contributions | |
orsi | -0.591 |
forging | -0.590 |
ratulations | -0.589 |
remember | -0.581 |
iferation | -0.555 |
Token | House |
Token ID | 2097 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Behavioral | +0.396 |
Pandora | +0.361 |
ディ | +0.344 |
^^ | +0.330 |
Pesh | +0.329 |
Neg logit contributions | |
forging | -0.460 |
orsi | -0.455 |
ratulations | -0.454 |
remember | -0.450 |
iferation | -0.430 |
Token | for |
Token ID | 329 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
forging | +1.012 |
orsi | +1.001 |
ratulations | +0.998 |
remember | +0.992 |
iferation | +0.945 |
Neg logit contributions | |
Behavioral | -0.873 |
Pandora | -0.797 |
ディ | -0.764 |
^^ | -0.728 |
Pesh | -0.724 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ratulations | +0.727 |
forging | +0.722 |
orsi | +0.716 |
remember | +0.682 |
merce | +0.678 |
Neg logit contributions | |
Behavioral | -0.715 |
Pandora | -0.658 |
^^ | -0.632 |
ディ | -0.627 |
Bronze | -0.600 |
Token | : |
Token ID | 25 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
ratulations | +1.049 |
forging | +1.036 |
orsi | +1.030 |
remember | +0.983 |
merce | +0.972 |
Neg logit contributions | |
Behavioral | -1.361 |
Pandora | -1.273 |
ディ | -1.217 |
^^ | -1.197 |
Bronze | -1.175 |
Token | 47 |
Token ID | 2857 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
forging | +0.069 |
remember | +0.068 |
ratulations | +0.068 |
orsi | +0.068 |
sbm | +0.065 |
Neg logit contributions | |
Behavioral | -0.044 |
Pandora | -0.039 |
ディ | -0.037 |
Pesh | -0.035 |
Bronze | -0.035 |
Token | ] |
Token ID | 60 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
forging | +2.310 |
ratulations | +2.300 |
orsi | +2.292 |
remember | +2.253 |
iferation | +2.186 |
Neg logit contributions | |
Behavioral | -1.140 |
Pandora | -1.004 |
ディ | -0.933 |
^^ | -0.886 |
Pesh | -0.868 |
Token | < |
Token ID | 1279 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
forging | +0.741 |
ratulations | +0.732 |
remember | +0.726 |
orsi | +0.726 |
iferation | +0.696 |
Neg logit contributions | |
Behavioral | -0.458 |
Pandora | -0.410 |
ディ | -0.398 |
^^ | -0.363 |
Pesh | -0.363 |
Token | min |
Token ID | 1084 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
forging | +1.562 |
orsi | +1.546 |
ratulations | +1.541 |
remember | +1.537 |
iferation | +1.446 |
Neg logit contributions | |
Behavioral | -1.760 |
Pandora | -1.623 |
ディ | -1.560 |
Pesh | -1.495 |
^^ | -1.494 |
Token | ion |
Token ID | 295 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
remember | +5.189 |
forging | +5.155 |
orsi | +5.152 |
ratulations | +5.133 |
onew | +4.991 |
Neg logit contributions | |
Behavioral | -3.897 |
Pandora | -3.418 |
ディ | -3.286 |
Pesh | -3.171 |
Stephenson | -3.058 |
Token | 13 |
Token ID | 1485 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Behavioral | +0.022 |
Pandora | +0.020 |
ディ | +0.019 |
^^ | +0.019 |
Stephenson | +0.018 |
Neg logit contributions | |
forging | -0.032 |
ratulations | -0.032 |
orsi | -0.031 |
remember | -0.031 |
iferation | -0.030 |
Token | 37 |
Token ID | 2718 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
forging | +1.676 |
ratulations | +1.671 |
orsi | +1.656 |
remember | +1.614 |
iferation | +1.589 |
Neg logit contributions | |
Behavioral | -1.223 |
Pandora | -1.109 |
ディ | -1.052 |
^^ | -1.026 |
IRD | -0.982 |
Token | > |
Token ID | 29 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
forging | +1.750 |
ratulations | +1.743 |
orsi | +1.730 |
remember | +1.675 |
iferation | +1.633 |
Neg logit contributions | |
Behavioral | -1.495 |
Pandora | -1.370 |
ディ | -1.320 |
^^ | -1.284 |
Pesh | -1.242 |
Token | lol |
Token ID | 19462 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Behavioral | +0.912 |
Pandora | +0.838 |
ディ | +0.785 |
^^ | +0.772 |
Pesh | +0.763 |
Neg logit contributions | |
orsi | -1.085 |
forging | -1.081 |
ratulations | -1.074 |
remember | -1.058 |
iferation | -1.028 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Behavioral | +1.064 |
Pandora | +0.969 |
ディ | +0.921 |
^^ | +0.899 |
Pesh | +0.891 |
Neg logit contributions | |
forging | -1.172 |
ratulations | -1.171 |
orsi | -1.165 |
remember | -1.148 |
iferation | -1.109 |
Token | ; |
Token ID | 26 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
forging | +1.115 |
orsi | +1.098 |
ratulations | +1.095 |
remember | +1.094 |
iferation | +1.045 |
Neg logit contributions | |
Behavioral | -0.817 |
Pandora | -0.742 |
ディ | -0.715 |
Pesh | -0.669 |
^^ | -0.662 |
Token | } |
Token ID | 1782 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Behavioral | +0.486 |
Pandora | +0.445 |
ディ | +0.423 |
^^ | +0.408 |
Pesh | +0.404 |
Neg logit contributions | |
forging | -0.535 |
orsi | -0.531 |
ratulations | -0.530 |
remember | -0.525 |
iferation | -0.502 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Behavioral | +0.250 |
Pandora | +0.225 |
ディ | +0.214 |
^^ | +0.202 |
Pesh | +0.201 |
Neg logit contributions | |
forging | -0.374 |
orsi | -0.370 |
ratulations | -0.370 |
remember | -0.367 |
iferation | -0.352 |
Token | 2 |
Token ID | 362 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
forging | +1.535 |
orsi | +1.513 |
ratulations | +1.508 |
remember | +1.506 |
iferation | +1.439 |
Neg logit contributions | |
Behavioral | -0.963 |
Pandora | -0.862 |
ディ | -0.827 |
Pesh | -0.770 |
^^ | -0.767 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
forging | +3.424 |
ratulations | +3.392 |
orsi | +3.364 |
remember | +3.359 |
deadlines | +3.181 |
Neg logit contributions | |
Behavioral | -2.391 |
Pandora | -2.148 |
ディ | -2.099 |
Pesh | -1.955 |
IRD | -1.929 |
Token | void |
Token ID | 7951 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
forging | +4.539 |
remember | +4.402 |
ratulations | +4.373 |
orsi | +4.321 |
onew | +4.110 |
Neg logit contributions | |
Behavioral | -3.815 |
ディ | -3.459 |
Pandora | -3.449 |
IRD | -3.288 |
Pesh | -3.221 |
Token | vert |
Token ID | 9421 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
forging | +2.469 |
orsi | +2.439 |
ratulations | +2.431 |
remember | +2.418 |
iferation | +2.292 |
Neg logit contributions | |
Behavioral | -2.085 |
Pandora | -1.894 |
ディ | -1.825 |
^^ | -1.724 |
Pesh | -1.721 |
Token | ( |
Token ID | 357 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
forging | +1.363 |
ratulations | +1.353 |
orsi | +1.348 |
remember | +1.328 |
iferation | +1.282 |
Neg logit contributions | |
Behavioral | -1.087 |
Pandora | -0.990 |
ディ | -0.938 |
^^ | -0.900 |
Pesh | -0.895 |
Token | in |
Token ID | 287 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Behavioral | +0.725 |
Pandora | +0.644 |
ディ | +0.589 |
^^ | +0.574 |
Pesh | +0.563 |
Neg logit contributions | |
orsi | -1.282 |
forging | -1.278 |
ratulations | -1.277 |
remember | -1.265 |
iferation | -1.224 |
Token | out |
Token ID | 448 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Behavioral | +1.784 |
Pandora | +1.653 |
^^ | +1.548 |
ディ | +1.508 |
Stephenson | +1.467 |
Neg logit contributions | |
orsi | -2.177 |
ratulations | -2.171 |
forging | -2.159 |
remember | -2.099 |
merce | -2.053 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ratulations | +0.902 |
forging | +0.895 |
orsi | +0.882 |
merce | +0.843 |
remember | +0.836 |
Neg logit contributions | |
Behavioral | -0.856 |
Pandora | -0.790 |
^^ | -0.760 |
ディ | -0.752 |
Pesh | -0.720 |
Token | : |
Token ID | 25 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
ratulations | +1.274 |
forging | +1.263 |
orsi | +1.251 |
remember | +1.201 |
merce | +1.178 |
Neg logit contributions | |
Behavioral | -1.680 |
Pandora | -1.572 |
ディ | -1.503 |
^^ | -1.477 |
Pesh | -1.452 |
Token | 47 |
Token ID | 2857 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
forging | +0.767 |
remember | +0.760 |
ratulations | +0.755 |
orsi | +0.751 |
sbm | +0.720 |
Neg logit contributions | |
Behavioral | -0.508 |
Pandora | -0.450 |
ディ | -0.426 |
Bronze | -0.406 |
Pesh | -0.405 |
Token | ] |
Token ID | 60 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
forging | +2.472 |
ratulations | +2.460 |
orsi | +2.451 |
remember | +2.409 |
iferation | +2.339 |
Neg logit contributions | |
Behavioral | -1.219 |
Pandora | -1.074 |
ディ | -0.998 |
^^ | -0.948 |
Pesh | -0.928 |
Token | < |
Token ID | 1279 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
forging | +1.224 |
ratulations | +1.209 |
remember | +1.200 |
orsi | +1.198 |
iferation | +1.149 |
Neg logit contributions | |
Behavioral | -0.769 |
Pandora | -0.687 |
ディ | -0.670 |
^^ | -0.610 |
Pesh | -0.609 |
Token | min |
Token ID | 1084 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
forging | +1.925 |
orsi | +1.909 |
remember | +1.906 |
ratulations | +1.902 |
iferation | +1.785 |
Neg logit contributions | |
Behavioral | -2.169 |
Pandora | -1.999 |
ディ | -1.916 |
Pesh | -1.842 |
^^ | -1.832 |
Token | ion |
Token ID | 295 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
orsi | +4.095 |
forging | +4.085 |
remember | +4.076 |
ratulations | +4.030 |
onew | +3.855 |
Neg logit contributions | |
Behavioral | -4.345 |
Pandora | -3.958 |
ディ | -3.725 |
Pesh | -3.621 |
Stephenson | -3.596 |
Token | 13 |
Token ID | 1485 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Behavioral | +0.591 |
Pandora | +0.546 |
ディ | +0.528 |
^^ | +0.508 |
Pesh | +0.499 |
Neg logit contributions | |
forging | -0.582 |
ratulations | -0.573 |
orsi | -0.573 |
remember | -0.564 |
iferation | -0.540 |
Token | 37 |
Token ID | 2718 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
forging | +1.511 |
orsi | +1.494 |
ratulations | +1.490 |
remember | +1.481 |
iferation | +1.408 |
Neg logit contributions | |
Behavioral | -1.343 |
Pandora | -1.227 |
ディ | -1.178 |
^^ | -1.121 |
Pesh | -1.118 |
Token | > |
Token ID | 29 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
forging | +1.090 |
orsi | +1.078 |
ratulations | +1.075 |
remember | +1.072 |
iferation | +1.013 |
Neg logit contributions | |
Behavioral | -1.079 |
Pandora | -0.989 |
ディ | -0.949 |
Pesh | -0.906 |
^^ | -0.903 |
Token | le |
Token ID | 443 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Behavioral | +0.430 |
Pandora | +0.396 |
ディ | +0.371 |
^^ | +0.363 |
Pesh | +0.359 |
Neg logit contributions | |
orsi | -0.518 |
forging | -0.517 |
ratulations | -0.515 |
remember | -0.505 |
iferation | -0.490 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
ratulations | +0.519 |
forging | +0.514 |
orsi | +0.505 |
merce | +0.485 |
iferation | +0.478 |
Neg logit contributions | |
Behavioral | -0.479 |
Pandora | -0.442 |
^^ | -0.427 |
ディ | -0.418 |
Bronze | -0.403 |
Token | : |
Token ID | 25 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
ratulations | +1.133 |
forging | +1.119 |
orsi | +1.109 |
remember | +1.060 |
merce | +1.049 |
Neg logit contributions | |
Behavioral | -1.458 |
Pandora | -1.365 |
ディ | -1.302 |
^^ | -1.283 |
Bronze | -1.259 |
Token | 48 |
Token ID | 2780 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
forging | +0.447 |
remember | +0.441 |
orsi | +0.441 |
ratulations | +0.440 |
iferation | +0.418 |
Neg logit contributions | |
Behavioral | -0.353 |
Pandora | -0.321 |
ディ | -0.306 |
Pesh | -0.290 |
^^ | -0.289 |
Token | ] |
Token ID | 60 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
forging | +2.437 |
ratulations | +2.430 |
orsi | +2.416 |
remember | +2.369 |
iferation | +2.308 |
Neg logit contributions | |
Behavioral | -1.185 |
Pandora | -1.045 |
ディ | -0.969 |
^^ | -0.923 |
Pesh | -0.900 |
Token | < |
Token ID | 1279 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
forging | +1.414 |
orsi | +1.409 |
ratulations | +1.408 |
remember | +1.387 |
iferation | +1.345 |
Neg logit contributions | |
Behavioral | -0.720 |
Pandora | -0.636 |
ディ | -0.587 |
^^ | -0.559 |
Pesh | -0.552 |
Token | min |
Token ID | 1084 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
forging | +1.730 |
orsi | +1.711 |
ratulations | +1.707 |
remember | +1.703 |
iferation | +1.600 |
Neg logit contributions | |
Behavioral | -1.958 |
Pandora | -1.805 |
ディ | -1.736 |
Pesh | -1.663 |
^^ | -1.662 |
Token | ion |
Token ID | 295 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
remember | +5.026 |
forging | +5.022 |
orsi | +5.020 |
ratulations | +4.988 |
onew | +4.802 |
Neg logit contributions | |
Behavioral | -3.411 |
Pandora | -2.989 |
ディ | -2.879 |
Pesh | -2.744 |
Stephenson | -2.667 |
Token | 13 |
Token ID | 1485 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Behavioral | +0.167 |
Pandora | +0.150 |
^^ | +0.149 |
ディ | +0.145 |
Bronze | +0.135 |
Neg logit contributions | |
ratulations | -0.279 |
forging | -0.278 |
orsi | -0.273 |
iferation | -0.266 |
merce | -0.266 |
Token | 37 |
Token ID | 2718 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ratulations | +1.092 |
forging | +1.090 |
orsi | +1.078 |
remember | +1.045 |
merce | +1.042 |
Neg logit contributions | |
Behavioral | -0.767 |
Pandora | -0.694 |
ディ | -0.656 |
^^ | -0.646 |
IRD | -0.613 |
Token | > |
Token ID | 29 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ratulations | +1.227 |
forging | +1.225 |
orsi | +1.213 |
remember | +1.166 |
merce | +1.152 |
Neg logit contributions | |
Behavioral | -1.012 |
Pandora | -0.928 |
ディ | -0.894 |
^^ | -0.873 |
Pesh | -0.840 |
Token | le |
Token ID | 443 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Behavioral | +0.974 |
Pandora | +0.896 |
ディ | +0.840 |
^^ | +0.824 |
Pesh | +0.815 |
Neg logit contributions | |
orsi | -1.172 |
forging | -1.167 |
ratulations | -1.161 |
remember | -1.142 |
iferation | -1.108 |
Token | ASA |
Token ID | 49599 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
forging | +0.323 |
orsi | +0.320 |
ratulations | +0.319 |
remember | +0.317 |
iferation | +0.303 |
Neg logit contributions | |
Behavioral | -0.236 |
Pandora | -0.213 |
ディ | -0.204 |
^^ | -0.192 |
Pesh | -0.191 |
Token | . |
Token ID | 13 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
forging | +1.556 |
orsi | +1.529 |
ratulations | +1.520 |
remember | +1.513 |
iferation | +1.445 |
Neg logit contributions | |
Behavioral | -1.279 |
Pandora | -1.165 |
ディ | -1.129 |
Pesh | -1.060 |
^^ | -1.055 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
forging | +0.751 |
orsi | +0.742 |
ratulations | +0.739 |
remember | +0.737 |
iferation | +0.704 |
Neg logit contributions | |
Behavioral | -0.557 |
Pandora | -0.502 |
ディ | -0.485 |
^^ | -0.456 |
Pesh | -0.453 |
Token |
|
Token ID | 198 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Behavioral | +0.084 |
Pandora | +0.076 |
ディ | +0.070 |
^^ | +0.069 |
Bronze | +0.067 |
Neg logit contributions | |
ratulations | -0.147 |
forging | -0.145 |
orsi | -0.145 |
merce | -0.140 |
remember | -0.139 |
Token | Among |
Token ID | 14311 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Behavioral | +0.375 |
Pandora | +0.347 |
ディ | +0.337 |
^^ | +0.328 |
IRD | +0.321 |
Neg logit contributions | |
forging | -0.361 |
ratulations | -0.355 |
orsi | -0.355 |
remember | -0.344 |
iferation | -0.332 |
Token | other |
Token ID | 584 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
forging | +0.207 |
orsi | +0.205 |
ratulations | +0.204 |
remember | +0.203 |
iferation | +0.193 |
Neg logit contributions | |
Behavioral | -0.167 |
Pandora | -0.152 |
ディ | -0.145 |
^^ | -0.138 |
Pesh | -0.137 |
Token | things |
Token ID | 1243 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
forging | +4.072 |
orsi | +3.884 |
ratulations | +3.862 |
remember | +3.824 |
deadlines | +3.806 |
Neg logit contributions | |
Behavioral | -4.160 |
ディ | -3.757 |
Pandora | -3.738 |
^^ | -3.532 |
Pesh | -3.451 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
forging | +1.976 |
ratulations | +1.936 |
orsi | +1.917 |
remember | +1.902 |
deadlines | +1.823 |
Neg logit contributions | |
Behavioral | -1.821 |
Pandora | -1.648 |
ディ | -1.618 |
Pesh | -1.514 |
^^ | -1.510 |
Token | the |
Token ID | 262 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
forging | +1.191 |
orsi | +1.163 |
ratulations | +1.162 |
remember | +1.156 |
deadlines | +1.099 |
Neg logit contributions | |
Behavioral | -1.059 |
Pandora | -0.962 |
ディ | -0.941 |
^^ | -0.887 |
Pesh | -0.881 |
Token | In |
Token ID | 554 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
forging | +0.642 |
orsi | +0.636 |
ratulations | +0.634 |
remember | +0.629 |
iferation | +0.598 |
Neg logit contributions | |
Behavioral | -0.632 |
Pandora | -0.581 |
ディ | -0.557 |
^^ | -0.533 |
Pesh | -0.532 |
Token | uit |
Token ID | 5013 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
forging | +0.416 |
ratulations | +0.410 |
orsi | +0.409 |
remember | +0.406 |
iferation | +0.392 |
Neg logit contributions | |
Behavioral | -0.232 |
Pandora | -0.207 |
ディ | -0.193 |
^^ | -0.185 |
Pesh | -0.181 |
Token | been |
Token ID | 587 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
forging | +1.984 |
orsi | +1.957 |
ratulations | +1.955 |
remember | +1.940 |
iferation | +1.852 |
Neg logit contributions | |
Behavioral | -1.577 |
Pandora | -1.428 |
ディ | -1.372 |
^^ | -1.299 |
Pesh | -1.292 |
Token | filed |
Token ID | 5717 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
forging | +1.310 |
orsi | +1.300 |
ratulations | +1.298 |
remember | +1.289 |
iferation | +1.239 |
Neg logit contributions | |
Behavioral | -0.728 |
Pandora | -0.646 |
ディ | -0.610 |
^^ | -0.571 |
Pesh | -0.568 |
Token | against |
Token ID | 1028 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ratulations | +0.209 |
orsi | +0.208 |
forging | +0.208 |
remember | +0.206 |
iferation | +0.197 |
Neg logit contributions | |
Behavioral | -0.174 |
Pandora | -0.160 |
ディ | -0.152 |
^^ | -0.146 |
Pesh | -0.145 |
Token | BJP |
Token ID | 18317 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
forging | +1.292 |
orsi | +1.285 |
ratulations | +1.281 |
remember | +1.272 |
iferation | +1.214 |
Neg logit contributions | |
Behavioral | -1.148 |
Pandora | -1.050 |
ディ | -1.002 |
Pesh | -0.960 |
^^ | -0.957 |
Token | MLA |
Token ID | 43265 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
forging | +1.132 |
orsi | +1.117 |
ratulations | +1.114 |
remember | +1.104 |
iferation | +1.043 |
Neg logit contributions | |
Behavioral | -1.367 |
Pandora | -1.266 |
ディ | -1.223 |
^^ | -1.174 |
Pesh | -1.170 |
Token | Narendra |
Token ID | 28113 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
Behavioral | +0.421 |
Pandora | +0.384 |
ディ | +0.364 |
Pesh | +0.350 |
^^ | +0.348 |
Neg logit contributions | |
forging | -0.512 |
orsi | -0.508 |
ratulations | -0.507 |
remember | -0.503 |
iferation | -0.481 |
Token | Me |
Token ID | 2185 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
forging | +4.277 |
orsi | +4.241 |
remember | +4.220 |
ratulations | +4.216 |
sbm | +4.036 |
Neg logit contributions | |
Behavioral | -3.704 |
Pandora | -3.350 |
ディ | -3.312 |
^^ | -3.073 |
IRD | -3.060 |
Token | ht |
Token ID | 4352 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
forging | +0.152 |
ratulations | +0.150 |
orsi | +0.149 |
remember | +0.148 |
iferation | +0.141 |
Neg logit contributions | |
Behavioral | -0.166 |
Pandora | -0.153 |
ディ | -0.147 |
^^ | -0.142 |
Pesh | -0.142 |
Token | a |
Token ID | 64 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
forging | +1.652 |
orsi | +1.632 |
ratulations | +1.621 |
remember | +1.612 |
iferation | +1.527 |
Neg logit contributions | |
Behavioral | -1.754 |
Pandora | -1.610 |
ディ | -1.560 |
^^ | -1.483 |
Pesh | -1.481 |
Token | � |
Token ID | 447 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
forging | +1.742 |
orsi | +1.724 |
ratulations | +1.718 |
remember | +1.708 |
iferation | +1.630 |
Neg logit contributions | |
Behavioral | -1.352 |
Pandora | -1.226 |
ディ | -1.174 |
^^ | -1.112 |
Pesh | -1.107 |
Token | � |
Token ID | 247 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
forging | +1.501 |
orsi | +1.479 |
ratulations | +1.471 |
remember | +1.466 |
sbm | +1.385 |
Neg logit contributions | |
Behavioral | -1.665 |
Pandora | -1.541 |
ディ | -1.475 |
Pesh | -1.413 |
^^ | -1.409 |
Token | Amount |
Token ID | 31264 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
Behavioral | +0.547 |
Pandora | +0.506 |
ディ | +0.487 |
^^ | +0.478 |
Pesh | +0.464 |
Neg logit contributions | |
forging | -0.493 |
ratulations | -0.490 |
orsi | -0.479 |
remember | -0.468 |
merce | -0.453 |
Token | ; |
Token ID | 26 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Behavioral | +0.219 |
Pandora | +0.198 |
ディ | +0.190 |
^^ | +0.178 |
Pesh | +0.178 |
Neg logit contributions | |
forging | -0.300 |
orsi | -0.297 |
ratulations | -0.296 |
remember | -0.294 |
iferation | -0.282 |
Token | } |
Token ID | 1782 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Behavioral | +0.769 |
Pandora | +0.703 |
ディ | +0.666 |
^^ | +0.642 |
Pesh | +0.635 |
Neg logit contributions | |
forging | -0.894 |
orsi | -0.888 |
ratulations | -0.887 |
remember | -0.877 |
iferation | -0.842 |
Token | 1 |
Token ID | 352 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
Behavioral | +0.735 |
Pandora | +0.649 |
ディ | +0.608 |
^^ | +0.574 |
Pesh | +0.567 |
Neg logit contributions | |
forging | -1.364 |
orsi | -1.355 |
ratulations | -1.352 |
remember | -1.341 |
iferation | -1.293 |
Token | 2 |
Token ID | 362 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
forging | +2.465 |
orsi | +2.436 |
ratulations | +2.428 |
remember | +2.421 |
iferation | +2.315 |
Neg logit contributions | |
Behavioral | -1.526 |
Pandora | -1.364 |
ディ | -1.302 |
^^ | -1.216 |
Pesh | -1.212 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
forging | +4.011 |
remember | +3.943 |
ratulations | +3.941 |
orsi | +3.929 |
deadlines | +3.754 |
Neg logit contributions | |
Behavioral | -2.588 |
Pandora | -2.308 |
ディ | -2.274 |
Pesh | -2.077 |
^^ | -2.051 |
Token | 4 |
Token ID | 604 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
forging | +4.320 |
remember | +4.228 |
ratulations | +4.176 |
orsi | +4.106 |
deadlines | +3.943 |
Neg logit contributions | |
Behavioral | -3.615 |
ディ | -3.318 |
Pandora | -3.282 |
IRD | -3.146 |
Pesh | -3.091 |
Token | 5 |
Token ID | 642 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
forging | +3.589 |
remember | +3.504 |
ratulations | +3.503 |
orsi | +3.395 |
deadlines | +3.279 |
Neg logit contributions | |
Behavioral | -3.107 |
ディ | -2.855 |
Pandora | -2.820 |
IRD | -2.666 |
Pesh | -2.653 |
Token | 6 |
Token ID | 718 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
forging | +2.670 |
remember | +2.598 |
ratulations | +2.582 |
orsi | +2.574 |
deadlines | +2.404 |
Neg logit contributions | |
Behavioral | -3.349 |
Pandora | -3.107 |
ディ | -3.078 |
Pesh | -2.930 |
IRD | -2.908 |
Token | 7 |
Token ID | 767 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
forging | +2.884 |
ratulations | +2.793 |
remember | +2.784 |
orsi | +2.721 |
deadlines | +2.604 |
Neg logit contributions | |
Behavioral | -3.632 |
Pandora | -3.374 |
ディ | -3.338 |
Pesh | -3.176 |
IRD | -3.173 |
Token | 8 |
Token ID | 807 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
forging | +3.188 |
remember | +3.083 |
ratulations | +3.036 |
orsi | +2.995 |
deadlines | +2.867 |
Neg logit contributions | |
Behavioral | -3.916 |
Pandora | -3.693 |
ディ | -3.643 |
IRD | -3.467 |
Pesh | -3.445 |
Token | the |
Token ID | 262 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
Behavioral | +0.152 |
Pandora | +0.139 |
ディ | +0.130 |
Pesh | +0.126 |
^^ | +0.126 |
Neg logit contributions | |
ratulations | -0.163 |
orsi | -0.162 |
forging | -0.162 |
remember | -0.160 |
iferation | -0.153 |
Token | experiments |
Token ID | 10256 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
forging | +0.562 |
orsi | +0.559 |
ratulations | +0.558 |
remember | +0.553 |
iferation | +0.527 |
Neg logit contributions | |
Behavioral | -0.499 |
Pandora | -0.454 |
ディ | -0.431 |
^^ | -0.414 |
Pesh | -0.413 |
Token | . |
Token ID | 13 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
forging | +2.449 |
orsi | +2.407 |
remember | +2.384 |
ratulations | +2.376 |
deadlines | +2.264 |
Neg logit contributions | |
Behavioral | -2.201 |
Pandora | -2.025 |
ディ | -1.966 |
Pesh | -1.849 |
^^ | -1.838 |
Token | Behavioral |
Token ID | 38483 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
Behavioral | +0.344 |
Pandora | +0.306 |
ディ | +0.287 |
^^ | +0.276 |
Pesh | +0.275 |
Neg logit contributions | |
forging | -0.491 |
ratulations | -0.488 |
orsi | -0.486 |
remember | -0.481 |
iferation | -0.462 |
Token | Task |
Token ID | 15941 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
ratulations | +0.621 |
forging | +0.620 |
orsi | +0.618 |
remember | +0.612 |
iferation | +0.583 |
Neg logit contributions | |
Behavioral | -0.660 |
Pandora | -0.599 |
ディ | -0.563 |
^^ | -0.551 |
Pesh | -0.549 |
Token | Maze |
Token ID | 33412 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
forging | +3.992 |
orsi | +3.960 |
remember | +3.929 |
ratulations | +3.924 |
iferation | +3.739 |
Neg logit contributions | |
Behavioral | -2.744 |
Pandora | -2.540 |
ディ | -2.492 |
^^ | -2.313 |
Pesh | -2.288 |
Token | design |
Token ID | 1486 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
forging | +4.513 |
orsi | +4.430 |
remember | +4.399 |
ratulations | +4.390 |
deadlines | +4.202 |
Neg logit contributions | |
Behavioral | -3.333 |
Pandora | -3.102 |
ディ | -3.065 |
^^ | -2.820 |
Pesh | -2.812 |
Token | . |
Token ID | 13 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
forging | +0.531 |
orsi | +0.527 |
ratulations | +0.525 |
remember | +0.521 |
iferation | +0.498 |
Neg logit contributions | |
Behavioral | -0.415 |
Pandora | -0.375 |
ディ | -0.356 |
^^ | -0.340 |
Pesh | -0.338 |
Token | A |
Token ID | 317 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Behavioral | +0.044 |
Pandora | +0.039 |
ディ | +0.037 |
^^ | +0.035 |
Pesh | +0.035 |
Neg logit contributions | |
forging | -0.058 |
ratulations | -0.057 |
orsi | -0.057 |
remember | -0.057 |
iferation | -0.054 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
forging | +0.510 |
ratulations | +0.506 |
orsi | +0.506 |
remember | +0.500 |
iferation | +0.476 |
Neg logit contributions | |
Behavioral | -0.549 |
Pandora | -0.505 |
ディ | -0.485 |
^^ | -0.465 |
Pesh | -0.464 |
Token | × |
Token ID | 12906 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
forging | +1.988 |
orsi | +1.953 |
ratulations | +1.947 |
remember | +1.935 |
iferation | +1.827 |
Neg logit contributions | |
Behavioral | -2.285 |
Pandora | -2.117 |
ディ | -2.048 |
Pesh | -1.955 |
^^ | -1.953 |
Token | Huffington |
Token ID | 23807 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
Behavioral | +0.160 |
Pandora | +0.145 |
ディ | +0.136 |
Pesh | +0.132 |
Bronze | +0.132 |
Neg logit contributions | |
orsi | -0.177 |
ratulations | -0.176 |
forging | -0.175 |
remember | -0.173 |
iferation | -0.167 |
Token | Post |
Token ID | 2947 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
Behavioral | +0.415 |
Pandora | +0.374 |
ディ | +0.341 |
Bronze | +0.325 |
Stephenson | +0.323 |
Neg logit contributions | |
orsi | -0.677 |
ratulations | -0.670 |
forging | -0.667 |
remember | -0.658 |
merce | -0.632 |
Token | explained |
Token ID | 4893 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
Behavioral | +2.211 |
Pandora | +2.029 |
ディ | +1.894 |
Pesh | +1.840 |
^^ | +1.817 |
Neg logit contributions | |
ratulations | -2.718 |
orsi | -2.716 |
forging | -2.693 |
remember | -2.645 |
iferation | -2.575 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Behavioral | +0.324 |
Pandora | +0.297 |
ディ | +0.281 |
^^ | +0.269 |
Pesh | +0.268 |
Neg logit contributions | |
forging | -0.403 |
orsi | -0.402 |
ratulations | -0.401 |
remember | -0.397 |
iferation | -0.381 |
Token | Among |
Token ID | 9754 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Behavioral | +0.124 |
Pandora | +0.112 |
ディ | +0.106 |
^^ | +0.101 |
Pesh | +0.101 |
Neg logit contributions | |
forging | -0.168 |
orsi | -0.167 |
ratulations | -0.167 |
remember | -0.165 |
iferation | -0.159 |
Token | other |
Token ID | 584 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
Behavioral | +0.158 |
Pandora | +0.143 |
ディ | +0.136 |
^^ | +0.128 |
Pesh | +0.128 |
Neg logit contributions | |
forging | -0.222 |
orsi | -0.220 |
ratulations | -0.220 |
remember | -0.218 |
iferation | -0.209 |
Token | things |
Token ID | 1243 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
forging | +4.074 |
orsi | +3.913 |
ratulations | +3.903 |
remember | +3.842 |
deadlines | +3.823 |
Neg logit contributions | |
Behavioral | -3.885 |
Pandora | -3.529 |
ディ | -3.520 |
^^ | -3.319 |
Pesh | -3.285 |
Token | , |
Token ID | 11 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
forging | +1.806 |
ratulations | +1.771 |
orsi | +1.748 |
remember | +1.743 |
deadlines | +1.672 |
Neg logit contributions | |
Behavioral | -1.643 |
Pandora | -1.495 |
ディ | -1.460 |
Pesh | -1.383 |
^^ | -1.376 |
Token | HHS |
Token ID | 45497 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
forging | +0.662 |
orsi | +0.653 |
ratulations | +0.652 |
remember | +0.648 |
iferation | +0.615 |
Neg logit contributions | |
Behavioral | -0.559 |
Pandora | -0.509 |
ディ | -0.491 |
^^ | -0.466 |
Pesh | -0.464 |
Token | seeks |
Token ID | 12932 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Behavioral | +0.237 |
Pandora | +0.215 |
ディ | +0.202 |
^^ | +0.195 |
Bronze | +0.194 |
Neg logit contributions | |
ratulations | -0.277 |
orsi | -0.276 |
forging | -0.275 |
remember | -0.273 |
iferation | -0.263 |
Token | to |
Token ID | 284 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Behavioral | +0.096 |
Pandora | +0.087 |
ディ | +0.084 |
^^ | +0.080 |
Pesh | +0.080 |
Neg logit contributions | |
forging | -0.128 |
orsi | -0.125 |
ratulations | -0.125 |
remember | -0.123 |
deadlines | -0.120 |
Token | , |
Token ID | 11 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
forging | +1.245 |
orsi | +1.232 |
ratulations | +1.226 |
remember | +1.221 |
iferation | +1.161 |
Neg logit contributions | |
Behavioral | -1.055 |
Pandora | -0.963 |
ディ | -0.924 |
^^ | -0.879 |
Pesh | -0.875 |
Token | director |
Token ID | 3437 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
forging | +0.764 |
orsi | +0.757 |
ratulations | +0.755 |
remember | +0.748 |
iferation | +0.714 |
Neg logit contributions | |
Behavioral | -0.674 |
Pandora | -0.616 |
ディ | -0.591 |
^^ | -0.563 |
Pesh | -0.560 |
Token | of |
Token ID | 286 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
forging | +1.169 |
orsi | +1.152 |
remember | +1.144 |
ratulations | +1.142 |
iferation | +1.086 |
Neg logit contributions | |
Behavioral | -1.070 |
Pandora | -0.980 |
ディ | -0.942 |
Pesh | -0.895 |
^^ | -0.894 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
forging | +1.572 |
orsi | +1.553 |
ratulations | +1.545 |
remember | +1.541 |
iferation | +1.471 |
Neg logit contributions | |
Behavioral | -1.240 |
Pandora | -1.122 |
ディ | -1.082 |
^^ | -1.027 |
Pesh | -1.020 |
Token | among |
Token ID | 1871 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
forging | +0.913 |
orsi | +0.903 |
ratulations | +0.901 |
remember | +0.895 |
iferation | +0.853 |
Neg logit contributions | |
Behavioral | -0.746 |
Pandora | -0.679 |
ディ | -0.650 |
^^ | -0.618 |
Pesh | -0.615 |
Token | other |
Token ID | 584 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
forging | +1.330 |
orsi | +1.314 |
ratulations | +1.309 |
remember | +1.304 |
iferation | +1.249 |
Neg logit contributions | |
Behavioral | -0.867 |
Pandora | -0.773 |
ディ | -0.738 |
^^ | -0.694 |
Pesh | -0.692 |
Token | things |
Token ID | 1243 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
forging | +3.706 |
orsi | +3.595 |
remember | +3.591 |
ratulations | +3.549 |
deadlines | +3.447 |
Neg logit contributions | |
Behavioral | -4.035 |
Pandora | -3.693 |
ディ | -3.644 |
^^ | -3.446 |
Pesh | -3.430 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
forging | +1.988 |
remember | +1.958 |
orsi | +1.943 |
ratulations | +1.941 |
iferation | +1.836 |
Neg logit contributions | |
Behavioral | -2.010 |
Pandora | -1.843 |
ディ | -1.781 |
^^ | -1.711 |
Pesh | -1.709 |
Token | Weekend |
Token ID | 30537 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
forging | +0.956 |
orsi | +0.945 |
ratulations | +0.942 |
remember | +0.937 |
iferation | +0.895 |
Neg logit contributions | |
Behavioral | -0.748 |
Pandora | -0.678 |
ディ | -0.650 |
^^ | -0.617 |
Pesh | -0.614 |
Token | at |
Token ID | 379 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
Behavioral | +0.102 |
Pandora | +0.092 |
ディ | +0.087 |
^^ | +0.083 |
Pesh | +0.083 |
Neg logit contributions | |
forging | -0.129 |
orsi | -0.127 |
ratulations | -0.127 |
remember | -0.126 |
iferation | -0.120 |
Token | Bernie |
Token ID | 10477 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
forging | +0.034 |
ratulations | +0.034 |
orsi | +0.033 |
remember | +0.033 |
iferation | +0.032 |
Neg logit contributions | |
Behavioral | -0.027 |
Pandora | -0.025 |
ディ | -0.023 |
Pesh | -0.023 |
^^ | -0.022 |
Token | played |
Token ID | 2826 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
forging | +1.446 |
orsi | +1.425 |
ratulations | +1.416 |
remember | +1.413 |
iferation | +1.341 |
Neg logit contributions | |
Behavioral | -1.136 |
Pandora | -1.029 |
ディ | -0.991 |
^^ | -0.935 |
Pesh | -0.928 |
Token | well |
Token ID | 880 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
forging | +0.359 |
orsi | +0.357 |
ratulations | +0.356 |
remember | +0.353 |
iferation | +0.338 |
Neg logit contributions | |
Behavioral | -0.302 |
Pandora | -0.275 |
ディ | -0.263 |
^^ | -0.251 |
Pesh | -0.251 |
Token | , |
Token ID | 11 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Behavioral | +0.435 |
Pandora | +0.396 |
ディ | +0.377 |
^^ | +0.363 |
Pesh | +0.359 |
Neg logit contributions | |
forging | -0.546 |
ratulations | -0.544 |
orsi | -0.543 |
remember | -0.536 |
iferation | -0.517 |
Token | and |
Token ID | 290 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
forging | +0.302 |
orsi | +0.299 |
ratulations | +0.299 |
remember | +0.296 |
iferation | +0.284 |
Neg logit contributions | |
Behavioral | -0.244 |
Pandora | -0.223 |
ディ | -0.213 |
^^ | -0.202 |
Pesh | -0.202 |
Token | since |
Token ID | 1201 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
forging | +0.486 |
orsi | +0.482 |
ratulations | +0.482 |
remember | +0.477 |
iferation | +0.457 |
Neg logit contributions | |
Behavioral | -0.380 |
Pandora | -0.345 |
ディ | -0.329 |
^^ | -0.313 |
Pesh | -0.312 |
Token | then |
Token ID | 788 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
Behavioral | +0.316 |
Pandora | +0.289 |
ディ | +0.276 |
^^ | +0.265 |
Pesh | +0.265 |
Neg logit contributions | |
forging | -0.359 |
orsi | -0.357 |
ratulations | -0.357 |
remember | -0.353 |
iferation | -0.340 |
Token | we |
Token ID | 356 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
forging | +3.920 |
orsi | +3.831 |
remember | +3.817 |
ratulations | +3.793 |
deadlines | +3.577 |
Neg logit contributions | |
Behavioral | -3.831 |
Pandora | -3.501 |
ディ | -3.421 |
^^ | -3.196 |
Possible | -3.174 |
Token | haven |
Token ID | 4398 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
forging | +0.430 |
ratulations | +0.426 |
orsi | +0.425 |
remember | +0.421 |
iferation | +0.403 |
Neg logit contributions | |
Behavioral | -0.377 |
Pandora | -0.345 |
ディ | -0.330 |
^^ | -0.316 |
Pesh | -0.314 |
Token | � |
Token ID | 447 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
forging | +0.766 |
ratulations | +0.761 |
orsi | +0.753 |
remember | +0.735 |
iferation | +0.717 |
Neg logit contributions | |
Behavioral | -0.476 |
Pandora | -0.426 |
ディ | -0.410 |
^^ | -0.395 |
Pesh | -0.379 |
Token | � |
Token ID | 247 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
forging | +0.973 |
ratulations | +0.963 |
orsi | +0.963 |
remember | +0.955 |
iferation | +0.917 |
Neg logit contributions | |
Behavioral | -0.620 |
Pandora | -0.556 |
ディ | -0.529 |
^^ | -0.498 |
Pesh | -0.495 |
Token | t |
Token ID | 83 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
forging | +0.402 |
orsi | +0.398 |
ratulations | +0.397 |
remember | +0.393 |
iferation | +0.375 |
Neg logit contributions | |
Behavioral | -0.354 |
Pandora | -0.323 |
ディ | -0.311 |
^^ | -0.297 |
Pesh | -0.294 |
Token | , |
Token ID | 11 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
forging | +1.123 |
orsi | +1.109 |
remember | +1.102 |
ratulations | +1.100 |
iferation | +1.048 |
Neg logit contributions | |
Behavioral | -1.020 |
Pandora | -0.934 |
ディ | -0.893 |
Pesh | -0.849 |
^^ | -0.848 |
Token | ( |
Token ID | 357 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
forging | +0.657 |
orsi | +0.654 |
ratulations | +0.653 |
remember | +0.645 |
iferation | +0.621 |
Neg logit contributions | |
Behavioral | -0.581 |
Pandora | -0.534 |
ディ | -0.509 |
^^ | -0.487 |
Pesh | -0.487 |
Token | 13 |
Token ID | 1485 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
forging | +0.998 |
orsi | +0.985 |
ratulations | +0.984 |
remember | +0.968 |
iferation | +0.927 |
Neg logit contributions | |
Behavioral | -1.081 |
Pandora | -0.998 |
ディ | -0.965 |
^^ | -0.926 |
Pesh | -0.921 |
Token | , |
Token ID | 11 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
forging | +0.818 |
orsi | +0.808 |
ratulations | +0.807 |
remember | +0.803 |
iferation | +0.765 |
Neg logit contributions | |
Behavioral | -0.645 |
Pandora | -0.586 |
ディ | -0.560 |
^^ | -0.530 |
Pesh | -0.529 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
forging | +0.220 |
orsi | +0.219 |
ratulations | +0.219 |
remember | +0.215 |
iferation | +0.208 |
Neg logit contributions | |
Behavioral | -0.166 |
Pandora | -0.151 |
ディ | -0.145 |
^^ | -0.138 |
Pesh | -0.137 |
Token | )) |
Token ID | 4008 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
forging | +1.558 |
ratulations | +1.537 |
orsi | +1.536 |
remember | +1.529 |
iferation | +1.436 |
Neg logit contributions | |
Behavioral | -1.779 |
Pandora | -1.642 |
ディ | -1.582 |
Pesh | -1.512 |
^^ | -1.505 |
Token | sq |
Token ID | 19862 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
forging | +4.391 |
orsi | +4.298 |
ratulations | +4.260 |
remember | +4.252 |
deadlines | +4.042 |
Neg logit contributions | |
Behavioral | -3.371 |
Pandora | -3.046 |
ディ | -2.977 |
^^ | -2.737 |
IRD | -2.733 |
Token | K |
Token ID | 42 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
forging | +1.994 |
orsi | +1.984 |
remember | +1.958 |
ratulations | +1.957 |
iferation | +1.833 |
Neg logit contributions | |
Behavioral | -2.621 |
Pandora | -2.437 |
ディ | -2.354 |
^^ | -2.250 |
Pesh | -2.242 |
Token | ernel |
Token ID | 7948 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Behavioral | +0.497 |
Pandora | +0.464 |
^^ | +0.450 |
ディ | +0.449 |
Pesh | +0.441 |
Neg logit contributions | |
forging | -0.329 |
ratulations | -0.323 |
remember | -0.306 |
orsi | -0.301 |
merce | -0.298 |
Token | = |
Token ID | 796 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
forging | +0.167 |
orsi | +0.165 |
ratulations | +0.165 |
remember | +0.163 |
iferation | +0.154 |
Neg logit contributions | |
Behavioral | -0.201 |
Pandora | -0.186 |
ディ | -0.179 |
^^ | -0.173 |
Pesh | -0.172 |
Token | c |
Token ID | 269 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
forging | +1.226 |
ratulations | +1.221 |
orsi | +1.220 |
remember | +1.208 |
iferation | +1.158 |
Neg logit contributions | |
Behavioral | -1.134 |
Pandora | -1.039 |
ディ | -0.986 |
^^ | -0.955 |
Pesh | -0.949 |
Token | them |
Token ID | 606 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
forging | +0.227 |
orsi | +0.227 |
ratulations | +0.226 |
remember | +0.224 |
iferation | +0.214 |
Neg logit contributions | |
Behavioral | -0.199 |
Pandora | -0.182 |
ディ | -0.173 |
^^ | -0.166 |
Pesh | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
forging | +0.274 |
orsi | +0.274 |
ratulations | +0.274 |
remember | +0.271 |
iferation | +0.260 |
Neg logit contributions | |
Behavioral | -0.200 |
Pandora | -0.183 |
ディ | -0.171 |
^^ | -0.166 |
Pesh | -0.163 |
Token |
|
Token ID | 198 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
Behavioral | +0.234 |
Pandora | +0.211 |
ディ | +0.197 |
^^ | +0.190 |
Pesh | +0.189 |
Neg logit contributions | |
forging | -0.326 |
ratulations | -0.325 |
orsi | -0.323 |
remember | -0.317 |
iferation | -0.307 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ratulations | +0.525 |
forging | +0.522 |
orsi | +0.519 |
remember | +0.501 |
merce | +0.499 |
Neg logit contributions | |
Behavioral | -0.314 |
Pandora | -0.281 |
ディ | -0.259 |
^^ | -0.256 |
Bronze | -0.249 |
Token | More |
Token ID | 5167 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
forging | +0.119 |
ratulations | +0.118 |
orsi | +0.117 |
remember | +0.113 |
iferation | +0.111 |
Neg logit contributions | |
Behavioral | -0.124 |
Pandora | -0.114 |
ディ | -0.110 |
^^ | -0.108 |
Pesh | -0.105 |
Token | specifically |
Token ID | 5734 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
Behavioral | +0.561 |
Pandora | +0.513 |
ディ | +0.484 |
^^ | +0.470 |
Pesh | +0.466 |
Neg logit contributions | |
forging | -0.609 |
orsi | -0.605 |
ratulations | -0.604 |
remember | -0.597 |
iferation | -0.572 |
Token | to |
Token ID | 284 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
forging | +3.794 |
remember | +3.717 |
ratulations | +3.687 |
orsi | +3.657 |
deadlines | +3.521 |
Neg logit contributions | |
Behavioral | -3.712 |
ディ | -3.420 |
Pandora | -3.383 |
IRD | -3.186 |
Pesh | -3.177 |
Token | this |
Token ID | 428 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
forging | +0.699 |
orsi | +0.694 |
ratulations | +0.694 |
remember | +0.685 |
iferation | +0.656 |
Neg logit contributions | |
Behavioral | -0.634 |
Pandora | -0.581 |
ディ | -0.553 |
^^ | -0.531 |
Pesh | -0.529 |
Token | case |
Token ID | 1339 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
forging | +0.690 |
orsi | +0.682 |
ratulations | +0.680 |
remember | +0.675 |
iferation | +0.643 |
Neg logit contributions | |
Behavioral | -0.640 |
Pandora | -0.586 |
ディ | -0.563 |
^^ | -0.537 |
Pesh | -0.535 |
Token | , |
Token ID | 11 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
Behavioral | +0.208 |
Pandora | +0.190 |
ディ | +0.179 |
^^ | +0.173 |
Pesh | +0.171 |
Neg logit contributions | |
forging | -0.260 |
orsi | -0.258 |
ratulations | -0.258 |
remember | -0.255 |
iferation | -0.245 |
Token | this |
Token ID | 428 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
forging | +0.790 |
orsi | +0.785 |
ratulations | +0.783 |
remember | +0.775 |
iferation | +0.744 |
Neg logit contributions | |
Behavioral | -0.654 |
Pandora | -0.597 |
ディ | -0.566 |
^^ | -0.542 |
Pesh | -0.540 |
Token | she |
Token ID | 673 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
forging | +0.750 |
orsi | +0.747 |
ratulations | +0.745 |
remember | +0.738 |
iferation | +0.707 |
Neg logit contributions | |
Behavioral | -0.645 |
Pandora | -0.590 |
ディ | -0.560 |
^^ | -0.538 |
Pesh | -0.535 |
Token | will |
Token ID | 481 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
forging | +0.551 |
ratulations | +0.547 |
orsi | +0.546 |
remember | +0.538 |
iferation | +0.519 |
Neg logit contributions | |
Behavioral | -0.471 |
Pandora | -0.430 |
ディ | -0.411 |
^^ | -0.395 |
Pesh | -0.392 |
Token | also |
Token ID | 635 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
forging | +0.960 |
orsi | +0.959 |
ratulations | +0.954 |
remember | +0.940 |
iferation | +0.905 |
Neg logit contributions | |
Behavioral | -0.892 |
Pandora | -0.820 |
ディ | -0.778 |
^^ | -0.754 |
Pesh | -0.747 |
Token | hear |
Token ID | 3285 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
orsi | +0.164 |
ratulations | +0.163 |
forging | +0.163 |
remember | +0.160 |
iferation | +0.155 |
Neg logit contributions | |
Behavioral | -0.156 |
Pandora | -0.145 |
ディ | -0.135 |
^^ | -0.133 |
Pesh | -0.132 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
forging | +1.451 |
orsi | +1.437 |
ratulations | +1.433 |
remember | +1.423 |
iferation | +1.355 |
Neg logit contributions | |
Behavioral | -1.340 |
Pandora | -1.228 |
ディ | -1.175 |
^^ | -1.124 |
Pesh | -1.121 |
Token | defense |
Token ID | 3761 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
forging | +1.134 |
orsi | +1.124 |
ratulations | +1.122 |
remember | +1.115 |
iferation | +1.065 |
Neg logit contributions | |
Behavioral | -0.918 |
Pandora | -0.835 |
ディ | -0.797 |
^^ | -0.759 |
Pesh | -0.756 |
Token | � |
Token ID | 447 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
forging | +3.873 |
orsi | +3.793 |
ratulations | +3.770 |
remember | +3.725 |
deadlines | +3.611 |
Neg logit contributions | |
Behavioral | -3.659 |
Pandora | -3.356 |
ディ | -3.298 |
Pesh | -3.052 |
Bronze | -3.041 |
Token | � |
Token ID | 247 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
forging | +1.710 |
ratulations | +1.695 |
orsi | +1.693 |
remember | +1.678 |
iferation | +1.619 |
Neg logit contributions | |
Behavioral | -0.845 |
Pandora | -0.740 |
ディ | -0.698 |
^^ | -0.650 |
Pesh | -0.642 |
Token | s |
Token ID | 82 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Behavioral | +0.012 |
Pandora | +0.011 |
ディ | +0.011 |
^^ | +0.010 |
Pesh | +0.010 |
Neg logit contributions | |
forging | -0.012 |
orsi | -0.012 |
ratulations | -0.012 |
remember | -0.012 |
iferation | -0.011 |
Token | request |
Token ID | 2581 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
forging | +1.083 |
orsi | +1.076 |
ratulations | +1.073 |
remember | +1.066 |
iferation | +1.014 |
Neg logit contributions | |
Behavioral | -1.087 |
Pandora | -0.999 |
ディ | -0.956 |
^^ | -0.918 |
Pesh | -0.914 |
Token | to |
Token ID | 284 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
forging | +0.551 |
orsi | +0.545 |
ratulations | +0.544 |
remember | +0.541 |
iferation | +0.518 |
Neg logit contributions | |
Behavioral | -0.375 |
Pandora | -0.338 |
ディ | -0.322 |
^^ | -0.304 |
Pesh | -0.302 |
Token | ian |
Token ID | 666 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Behavioral | +0.396 |
Pandora | +0.363 |
ディ | +0.350 |
^^ | +0.345 |
Bronze | +0.339 |
Neg logit contributions | |
ratulations | -0.339 |
forging | -0.338 |
orsi | -0.330 |
remember | -0.319 |
merce | -0.313 |
Token | , |
Token ID | 11 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Behavioral | +0.086 |
Pandora | +0.078 |
ディ | +0.073 |
^^ | +0.071 |
Pesh | +0.070 |
Neg logit contributions | |
forging | -0.119 |
ratulations | -0.118 |
orsi | -0.118 |
remember | -0.115 |
iferation | -0.112 |
Token | we |
Token ID | 356 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Behavioral | +0.326 |
Pandora | +0.299 |
^^ | +0.279 |
ディ | +0.278 |
Bronze | +0.269 |
Neg logit contributions | |
ratulations | -0.426 |
forging | -0.423 |
orsi | -0.419 |
remember | -0.406 |
merce | -0.405 |
Token | couldn |
Token ID | 3521 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Behavioral | +0.501 |
Pandora | +0.436 |
ディ | +0.407 |
^^ | +0.384 |
Pesh | +0.378 |
Neg logit contributions | |
forging | -1.079 |
orsi | -1.073 |
ratulations | -1.071 |
remember | -1.060 |
iferation | -1.027 |
Token | 't |
Token ID | 470 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Behavioral | +0.751 |
Pandora | +0.671 |
ディ | +0.643 |
^^ | +0.632 |
Pesh | +0.596 |
Neg logit contributions | |
forging | -1.310 |
ratulations | -1.307 |
orsi | -1.286 |
remember | -1.244 |
merce | -1.242 |
Token | resist |
Token ID | 4180 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
Behavioral | +0.458 |
Pandora | +0.430 |
ディ | +0.408 |
^^ | +0.407 |
Pesh | +0.402 |
Neg logit contributions | |
orsi | -0.272 |
forging | -0.272 |
ratulations | -0.271 |
remember | -0.260 |
iferation | -0.254 |
Token | the |
Token ID | 262 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
forging | +3.830 |
remember | +3.758 |
orsi | +3.748 |
ratulations | +3.705 |
iferation | +3.519 |
Neg logit contributions | |
Behavioral | -3.730 |
Pandora | -3.409 |
ディ | -3.292 |
Pesh | -3.132 |
^^ | -3.123 |
Token | temptation |
Token ID | 29062 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Behavioral | +0.550 |
Pandora | +0.517 |
ディ | +0.499 |
^^ | +0.488 |
Pesh | +0.483 |
Neg logit contributions | |
ratulations | -0.291 |
orsi | -0.290 |
forging | -0.290 |
remember | -0.284 |
iferation | -0.266 |
Token | to |
Token ID | 284 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
forging | +1.958 |
ratulations | +1.946 |
orsi | +1.942 |
remember | +1.918 |
iferation | +1.848 |
Neg logit contributions | |
Behavioral | -1.303 |
Pandora | -1.173 |
ディ | -1.113 |
^^ | -1.060 |
Pesh | -1.046 |
Token | recall |
Token ID | 10014 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
forging | +0.042 |
ratulations | +0.042 |
orsi | +0.042 |
remember | +0.038 |
iferation | +0.038 |
Neg logit contributions | |
Behavioral | -0.101 |
Pandora | -0.096 |
ディ | -0.093 |
^^ | -0.092 |
Pesh | -0.090 |
Token | 1974 |
Token ID | 16489 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
forging | +1.892 |
remember | +1.870 |
orsi | +1.853 |
ratulations | +1.839 |
deadlines | +1.716 |
Neg logit contributions | |
Behavioral | -2.506 |
Pandora | -2.340 |
ディ | -2.252 |
Pesh | -2.192 |
^^ | -2.175 |
Token | ade |
Token ID | 671 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Behavioral | +0.236 |
Pandora | +0.219 |
ディ | +0.212 |
^^ | +0.203 |
Pesh | +0.202 |
Neg logit contributions | |
forging | -0.186 |
orsi | -0.184 |
ratulations | -0.183 |
remember | -0.181 |
iferation | -0.171 |
Token | h |
Token ID | 71 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
forging | +1.124 |
orsi | +1.114 |
ratulations | +1.103 |
remember | +1.097 |
iferation | +1.031 |
Neg logit contributions | |
Behavioral | -1.306 |
Pandora | -1.204 |
ディ | -1.165 |
Pesh | -1.114 |
^^ | -1.111 |
Token | . |
Token ID | 13 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
Behavioral | +0.403 |
Pandora | +0.368 |
ディ | +0.348 |
^^ | +0.335 |
Pesh | +0.334 |
Neg logit contributions | |
forging | -0.504 |
ratulations | -0.500 |
orsi | -0.499 |
remember | -0.496 |
iferation | -0.475 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
forging | +0.733 |
orsi | +0.725 |
ratulations | +0.723 |
remember | +0.719 |
iferation | +0.687 |
Neg logit contributions | |
Behavioral | -0.535 |
Pandora | -0.484 |
ディ | -0.463 |
^^ | -0.437 |
Pesh | -0.435 |
Token | NEW |
Token ID | 13965 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
forging | +0.414 |
orsi | +0.408 |
ratulations | +0.407 |
remember | +0.400 |
iferation | +0.382 |
Neg logit contributions | |
Behavioral | -0.459 |
Pandora | -0.423 |
ディ | -0.410 |
^^ | -0.395 |
Pesh | -0.390 |
Token | DEL |
Token ID | 28163 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
forging | +1.322 |
orsi | +1.306 |
ratulations | +1.304 |
remember | +1.296 |
iferation | +1.237 |
Neg logit contributions | |
Behavioral | -0.968 |
Pandora | -0.876 |
ディ | -0.839 |
^^ | -0.791 |
Pesh | -0.787 |
Token | HI |
Token ID | 25374 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
remember | +3.699 |
forging | +3.692 |
orsi | +3.597 |
ratulations | +3.562 |
sbm | +3.446 |
Neg logit contributions | |
Behavioral | -3.687 |
Pandora | -3.353 |
ディ | -3.290 |
Stephenson | -3.104 |
Bronze | -3.086 |
Token | : |
Token ID | 25 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
forging | +2.947 |
remember | +2.851 |
orsi | +2.850 |
ratulations | +2.831 |
deadlines | +2.653 |
Neg logit contributions | |
Behavioral | -4.454 |
Pandora | -4.155 |
ディ | -4.062 |
^^ | -3.867 |
Pesh | -3.867 |
Token | In |
Token ID | 554 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
forging | +3.224 |
remember | +3.169 |
orsi | +3.163 |
ratulations | +3.139 |
sbm | +3.007 |
Neg logit contributions | |
Behavioral | -2.475 |
Pandora | -2.235 |
ディ | -2.176 |
^^ | -2.047 |
Pesh | -2.013 |
Token | a |
Token ID | 257 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Behavioral | +0.152 |
Pandora | +0.139 |
ディ | +0.133 |
Pesh | +0.127 |
^^ | +0.126 |
Neg logit contributions | |
ratulations | -0.176 |
orsi | -0.176 |
forging | -0.176 |
remember | -0.174 |
iferation | -0.166 |
Token | setback |
Token ID | 34116 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
forging | +0.301 |
orsi | +0.299 |
ratulations | +0.298 |
remember | +0.295 |
iferation | +0.281 |
Neg logit contributions | |
Behavioral | -0.308 |
Pandora | -0.284 |
ディ | -0.273 |
^^ | -0.261 |
Pesh | -0.260 |
Token | 10 |
Token ID | 940 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
ratulations | +0.873 |
forging | +0.866 |
orsi | +0.853 |
merce | +0.816 |
remember | +0.808 |
Neg logit contributions | |
Behavioral | -0.821 |
Pandora | -0.759 |
^^ | -0.729 |
ディ | -0.721 |
Bronze | -0.692 |
Token | : |
Token ID | 25 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ratulations | +1.349 |
forging | +1.338 |
orsi | +1.325 |
remember | +1.273 |
merce | +1.245 |
Neg logit contributions | |
Behavioral | -1.788 |
Pandora | -1.673 |
ディ | -1.599 |
^^ | -1.571 |
Pesh | -1.546 |
Token | 48 |
Token ID | 2780 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
forging | +0.598 |
ratulations | +0.596 |
orsi | +0.595 |
remember | +0.579 |
iferation | +0.569 |
Neg logit contributions | |
Behavioral | -0.298 |
Pandora | -0.265 |
ディ | -0.249 |
^^ | -0.236 |
Pesh | -0.228 |
Token | ] |
Token ID | 60 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
forging | +2.452 |
ratulations | +2.440 |
orsi | +2.431 |
remember | +2.389 |
iferation | +2.324 |
Neg logit contributions | |
Behavioral | -1.220 |
Pandora | -1.078 |
ディ | -1.005 |
^^ | -0.950 |
Pesh | -0.930 |
Token | < |
Token ID | 1279 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
forging | +1.237 |
ratulations | +1.222 |
remember | +1.213 |
orsi | +1.212 |
iferation | +1.163 |
Neg logit contributions | |
Behavioral | -0.766 |
Pandora | -0.683 |
ディ | -0.662 |
^^ | -0.607 |
Pesh | -0.604 |
Token | death |
Token ID | 22595 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
forging | +1.906 |
orsi | +1.887 |
remember | +1.882 |
ratulations | +1.881 |
iferation | +1.764 |
Neg logit contributions | |
Behavioral | -2.152 |
Pandora | -1.983 |
ディ | -1.903 |
Pesh | -1.826 |
^^ | -1.821 |
Token | d |
Token ID | 67 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
forging | +3.579 |
remember | +3.578 |
orsi | +3.562 |
ratulations | +3.534 |
sbm | +3.316 |
Neg logit contributions | |
Behavioral | -3.900 |
Pandora | -3.559 |
ディ | -3.398 |
Pesh | -3.289 |
Stephenson | -3.274 |
Token | ax |
Token ID | 897 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
orsi | +1.801 |
forging | +1.801 |
ratulations | +1.782 |
remember | +1.777 |
iferation | +1.675 |
Neg logit contributions | |
Behavioral | -2.093 |
Pandora | -1.924 |
ディ | -1.861 |
Pesh | -1.777 |
^^ | -1.772 |
Token | > |
Token ID | 29 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
forging | +0.980 |
orsi | +0.970 |
ratulations | +0.967 |
remember | +0.962 |
iferation | +0.913 |
Neg logit contributions | |
Behavioral | -0.908 |
Pandora | -0.829 |
ディ | -0.796 |
^^ | -0.757 |
Pesh | -0.757 |
Token | lol |
Token ID | 19462 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
Behavioral | +0.287 |
Pandora | +0.264 |
ディ | +0.249 |
^^ | +0.242 |
Pesh | +0.240 |
Neg logit contributions | |
orsi | -0.338 |
forging | -0.337 |
ratulations | -0.335 |
remember | -0.330 |
iferation | -0.319 |
Token | m |
Token ID | 285 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
forging | +0.665 |
orsi | +0.655 |
ratulations | +0.654 |
remember | +0.649 |
iferation | +0.612 |
Neg logit contributions | |
Behavioral | -0.802 |
Pandora | -0.742 |
ディ | -0.717 |
^^ | -0.686 |
Pesh | -0.685 |
Token | h |
Token ID | 71 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
forging | +1.124 |
orsi | +1.114 |
ratulations | +1.103 |
remember | +1.097 |
iferation | +1.031 |
Neg logit contributions | |
Behavioral | -1.306 |
Pandora | -1.204 |
ディ | -1.165 |
Pesh | -1.114 |
^^ | -1.111 |
Token | . |
Token ID | 13 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
Behavioral | +0.403 |
Pandora | +0.368 |
ディ | +0.348 |
^^ | +0.335 |
Pesh | +0.334 |
Neg logit contributions | |
forging | -0.504 |
ratulations | -0.500 |
orsi | -0.499 |
remember | -0.496 |
iferation | -0.475 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
forging | +0.733 |
orsi | +0.725 |
ratulations | +0.723 |
remember | +0.719 |
iferation | +0.687 |
Neg logit contributions | |
Behavioral | -0.535 |
Pandora | -0.484 |
ディ | -0.463 |
^^ | -0.437 |
Pesh | -0.435 |
Token | NEW |
Token ID | 13965 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
forging | +0.414 |
orsi | +0.408 |
ratulations | +0.407 |
remember | +0.400 |
iferation | +0.382 |
Neg logit contributions | |
Behavioral | -0.459 |
Pandora | -0.423 |
ディ | -0.410 |
^^ | -0.395 |
Pesh | -0.390 |
Token | DEL |
Token ID | 28163 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
forging | +1.322 |
orsi | +1.306 |
ratulations | +1.304 |
remember | +1.296 |
iferation | +1.237 |
Neg logit contributions | |
Behavioral | -0.968 |
Pandora | -0.876 |
ディ | -0.839 |
^^ | -0.791 |
Pesh | -0.787 |
Token | HI |
Token ID | 25374 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
remember | +3.699 |
forging | +3.692 |
orsi | +3.597 |
ratulations | +3.562 |
sbm | +3.446 |
Neg logit contributions | |
Behavioral | -3.687 |
Pandora | -3.353 |
ディ | -3.290 |
Stephenson | -3.104 |
Bronze | -3.086 |
Token | : |
Token ID | 25 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
forging | +2.947 |
remember | +2.851 |
orsi | +2.850 |
ratulations | +2.831 |
deadlines | +2.653 |
Neg logit contributions | |
Behavioral | -4.454 |
Pandora | -4.155 |
ディ | -4.062 |
^^ | -3.867 |
Pesh | -3.867 |
Token | In |
Token ID | 554 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
forging | +3.224 |
remember | +3.169 |
orsi | +3.163 |
ratulations | +3.139 |
sbm | +3.007 |
Neg logit contributions | |
Behavioral | -2.475 |
Pandora | -2.235 |
ディ | -2.176 |
^^ | -2.047 |
Pesh | -2.013 |
Token | a |
Token ID | 257 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Behavioral | +0.152 |
Pandora | +0.139 |
ディ | +0.133 |
Pesh | +0.127 |
^^ | +0.126 |
Neg logit contributions | |
ratulations | -0.176 |
orsi | -0.176 |
forging | -0.176 |
remember | -0.174 |
iferation | -0.166 |
Token | setback |
Token ID | 34116 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
forging | +0.301 |
orsi | +0.299 |
ratulations | +0.298 |
remember | +0.295 |
iferation | +0.281 |
Neg logit contributions | |
Behavioral | -0.308 |
Pandora | -0.284 |
ディ | -0.273 |
^^ | -0.261 |
Pesh | -0.260 |
Token | to |
Token ID | 284 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
Behavioral | +0.082 |
Pandora | +0.074 |
ディ | +0.071 |
^^ | +0.067 |
Pesh | +0.066 |
Neg logit contributions | |
forging | -0.118 |
orsi | -0.117 |
ratulations | -0.117 |
remember | -0.116 |
iferation | -0.111 |
Token | certain |
Token ID | 1728 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Behavioral | +0.897 |
Pandora | +0.820 |
ディ | +0.783 |
Pesh | +0.745 |
^^ | +0.745 |
Neg logit contributions | |
forging | -1.069 |
ratulations | -1.062 |
orsi | -1.060 |
remember | -1.052 |
iferation | -1.004 |
Token | kinds |
Token ID | 6982 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Behavioral | +0.082 |
Pandora | +0.074 |
ディ | +0.071 |
^^ | +0.067 |
Pesh | +0.067 |
Neg logit contributions | |
forging | -0.112 |
orsi | -0.111 |
ratulations | -0.110 |
remember | -0.110 |
iferation | -0.105 |
Token | of |
Token ID | 286 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Behavioral | +0.639 |
Pandora | +0.585 |
ディ | +0.548 |
^^ | +0.535 |
Pesh | +0.521 |
Neg logit contributions | |
ratulations | -0.892 |
forging | -0.878 |
orsi | -0.866 |
remember | -0.851 |
merce | -0.839 |
Token | people |
Token ID | 661 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Behavioral | +0.390 |
Pandora | +0.357 |
ディ | +0.339 |
^^ | +0.324 |
Pesh | +0.324 |
Neg logit contributions | |
forging | -0.458 |
ratulations | -0.456 |
orsi | -0.454 |
remember | -0.451 |
iferation | -0.430 |
Token | ha |
Token ID | 387 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Behavioral | +0.231 |
Pandora | +0.210 |
ディ | +0.201 |
^^ | +0.192 |
Pesh | +0.191 |
Neg logit contributions | |
forging | -0.275 |
ratulations | -0.272 |
orsi | -0.272 |
remember | -0.270 |
iferation | -0.257 |
Token | iling |
Token ID | 4386 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
Behavioral | +0.124 |
Pandora | +0.114 |
ディ | +0.110 |
^^ | +0.106 |
Pesh | +0.105 |
Neg logit contributions | |
forging | -0.116 |
orsi | -0.114 |
ratulations | -0.114 |
remember | -0.113 |
iferation | -0.107 |
Token | from |
Token ID | 422 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
forging | +3.614 |
orsi | +3.497 |
ratulations | +3.461 |
remember | +3.400 |
iferation | +3.330 |
Neg logit contributions | |
Behavioral | -3.743 |
Pandora | -3.421 |
ディ | -3.378 |
IRD | -3.161 |
^^ | -3.158 |
Token | specific |
Token ID | 2176 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
forging | +0.721 |
orsi | +0.712 |
remember | +0.702 |
ratulations | +0.702 |
iferation | +0.673 |
Neg logit contributions | |
Behavioral | -0.540 |
Pandora | -0.488 |
ディ | -0.468 |
^^ | -0.441 |
Stephenson | -0.436 |
Token | countries |
Token ID | 2678 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
forging | +1.247 |
orsi | +1.227 |
remember | +1.212 |
ratulations | +1.212 |
deadlines | +1.161 |
Neg logit contributions | |
Behavioral | -0.911 |
Pandora | -0.825 |
ディ | -0.797 |
^^ | -0.745 |
Pesh | -0.738 |
Token | in |
Token ID | 287 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Behavioral | +1.590 |
Pandora | +1.445 |
ディ | +1.375 |
^^ | +1.325 |
Pesh | +1.311 |
Neg logit contributions | |
ratulations | -2.025 |
forging | -2.014 |
orsi | -1.999 |
remember | -1.997 |
iferation | -1.910 |
Token | the |
Token ID | 262 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
Behavioral | +0.846 |
Pandora | +0.772 |
ディ | +0.738 |
Pesh | +0.704 |
^^ | +0.702 |
Neg logit contributions | |
ratulations | -0.981 |
forging | -0.978 |
orsi | -0.972 |
remember | -0.964 |
iferation | -0.917 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ratulations | +0.871 |
forging | +0.864 |
orsi | +0.851 |
merce | +0.814 |
remember | +0.808 |
Neg logit contributions | |
Behavioral | -0.828 |
Pandora | -0.764 |
^^ | -0.737 |
ディ | -0.725 |
Bronze | -0.695 |
Token | : |
Token ID | 25 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ratulations | +0.986 |
forging | +0.974 |
orsi | +0.967 |
remember | +0.924 |
merce | +0.914 |
Neg logit contributions | |
Behavioral | -1.273 |
Pandora | -1.191 |
ディ | -1.137 |
^^ | -1.120 |
Bronze | -1.099 |
Token | 47 |
Token ID | 2857 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Behavioral | +0.153 |
Pandora | +0.136 |
ディ | +0.128 |
^^ | +0.120 |
Pesh | +0.119 |
Neg logit contributions | |
forging | -0.276 |
orsi | -0.274 |
ratulations | -0.273 |
remember | -0.271 |
iferation | -0.261 |
Token | ] |
Token ID | 60 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
forging | +2.263 |
ratulations | +2.255 |
orsi | +2.245 |
remember | +2.203 |
iferation | +2.142 |
Neg logit contributions | |
Behavioral | -1.104 |
Pandora | -0.973 |
ディ | -0.901 |
^^ | -0.859 |
Pesh | -0.839 |
Token | < |
Token ID | 1279 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
forging | +0.697 |
ratulations | +0.689 |
orsi | +0.684 |
remember | +0.683 |
iferation | +0.655 |
Neg logit contributions | |
Behavioral | -0.428 |
Pandora | -0.382 |
ディ | -0.371 |
^^ | -0.339 |
Pesh | -0.338 |
Token | dan |
Token ID | 25604 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
forging | +1.484 |
orsi | +1.468 |
ratulations | +1.464 |
remember | +1.459 |
iferation | +1.373 |
Neg logit contributions | |
Behavioral | -1.687 |
Pandora | -1.557 |
ディ | -1.498 |
^^ | -1.435 |
Pesh | -1.435 |
Token | ides |
Token ID | 1460 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
forging | +3.582 |
remember | +3.578 |
orsi | +3.573 |
ratulations | +3.563 |
iferation | +3.353 |
Neg logit contributions | |
Behavioral | -3.752 |
Pandora | -3.417 |
ディ | -3.231 |
Pesh | -3.138 |
Stephenson | -3.109 |
Token | u |
Token ID | 84 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
forging | +1.912 |
orsi | +1.895 |
ratulations | +1.889 |
remember | +1.882 |
iferation | +1.779 |
Neg logit contributions | |
Behavioral | -1.960 |
Pandora | -1.798 |
ディ | -1.719 |
Pesh | -1.649 |
^^ | -1.642 |
Token | > |
Token ID | 29 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
forging | +0.874 |
orsi | +0.865 |
ratulations | +0.860 |
remember | +0.855 |
iferation | +0.808 |
Neg logit contributions | |
Behavioral | -0.965 |
Pandora | -0.889 |
ディ | -0.857 |
Pesh | -0.818 |
^^ | -0.818 |
Token | lol |
Token ID | 19462 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
Behavioral | +0.465 |
Pandora | +0.427 |
ディ | +0.401 |
^^ | +0.392 |
Pesh | +0.388 |
Neg logit contributions | |
orsi | -0.553 |
forging | -0.552 |
ratulations | -0.549 |
remember | -0.540 |
iferation | -0.524 |
Token | m |
Token ID | 285 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
forging | +0.523 |
orsi | +0.516 |
ratulations | +0.514 |
remember | +0.510 |
iferation | +0.482 |
Neg logit contributions | |
Behavioral | -0.616 |
Pandora | -0.570 |
ディ | -0.550 |
^^ | -0.528 |
Pesh | -0.526 |
Token | if |
Token ID | 611 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
forging | +0.724 |
orsi | +0.714 |
ratulations | +0.712 |
remember | +0.710 |
iferation | +0.674 |
Neg logit contributions | |
Behavioral | -0.561 |
Pandora | -0.507 |
ディ | -0.488 |
^^ | -0.462 |
Pesh | -0.460 |
Token | you |
Token ID | 345 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
forging | +0.470 |
orsi | +0.464 |
ratulations | +0.463 |
remember | +0.460 |
iferation | +0.438 |
Neg logit contributions | |
Behavioral | -0.389 |
Pandora | -0.354 |
ディ | -0.340 |
^^ | -0.322 |
Pesh | -0.321 |
Token | 're |
Token ID | 821 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
Behavioral | +1.131 |
Pandora | +1.042 |
ディ | +0.984 |
^^ | +0.948 |
Pesh | +0.940 |
Neg logit contributions | |
orsi | -1.351 |
forging | -1.351 |
ratulations | -1.346 |
remember | -1.313 |
iferation | -1.282 |
Token | really |
Token ID | 1107 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Behavioral | +0.657 |
Pandora | +0.603 |
ディ | +0.572 |
^^ | +0.548 |
Pesh | +0.543 |
Neg logit contributions | |
orsi | -0.791 |
ratulations | -0.789 |
forging | -0.786 |
remember | -0.775 |
iferation | -0.752 |
Token | f |
Token ID | 277 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Behavioral | +0.476 |
Pandora | +0.436 |
ディ | +0.414 |
^^ | +0.397 |
Pesh | +0.394 |
Neg logit contributions | |
forging | -0.567 |
orsi | -0.566 |
ratulations | -0.564 |
remember | -0.558 |
iferation | -0.536 |
Token | **** |
Token ID | 2466 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
Behavioral | +0.228 |
Pandora | +0.207 |
ディ | +0.198 |
^^ | +0.189 |
Pesh | +0.187 |
Neg logit contributions | |
forging | -0.290 |
orsi | -0.286 |
ratulations | -0.286 |
remember | -0.283 |
iferation | -0.271 |
Token | d |
Token ID | 67 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Behavioral | +2.805 |
Pandora | +2.592 |
ディ | +2.460 |
^^ | +2.418 |
Pesh | +2.323 |
Neg logit contributions | |
forging | -3.279 |
ratulations | -3.271 |
orsi | -3.232 |
remember | -3.161 |
iferation | -3.112 |
Token | . |
Token ID | 13 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
forging | +0.185 |
orsi | +0.183 |
ratulations | +0.182 |
remember | +0.181 |
iferation | +0.173 |
Neg logit contributions | |
Behavioral | -0.152 |
Pandora | -0.138 |
ディ | -0.132 |
^^ | -0.126 |
Pesh | -0.125 |
Token |
|
Token ID | 198 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
Behavioral | +0.569 |
Pandora | +0.516 |
ディ | +0.487 |
^^ | +0.466 |
Pesh | +0.462 |
Neg logit contributions | |
forging | -0.776 |
orsi | -0.770 |
ratulations | -0.769 |
remember | -0.759 |
iferation | -0.733 |
Token |
|
Token ID | 198 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
Behavioral | +0.368 |
Pandora | +0.329 |
^^ | +0.302 |
ディ | +0.302 |
Bronze | +0.291 |
Neg logit contributions | |
ratulations | -0.653 |
forging | -0.647 |
orsi | -0.643 |
merce | -0.623 |
iferation | -0.615 |
Token | Let |
Token ID | 5756 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
Behavioral | +0.635 |
Pandora | +0.585 |
ディ | +0.570 |
^^ | +0.551 |
IRD | +0.535 |
Neg logit contributions | |
forging | -0.668 |
ratulations | -0.658 |
orsi | -0.658 |
remember | -0.636 |
iferation | -0.623 |
Token | See |
Token ID | 6214 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Behavioral | +0.378 |
Pandora | +0.351 |
ディ | +0.341 |
^^ | +0.334 |
Pesh | +0.323 |
Neg logit contributions | |
forging | -0.334 |
ratulations | -0.328 |
orsi | -0.328 |
remember | -0.315 |
iferation | -0.307 |
Token | some |
Token ID | 617 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Behavioral | +0.859 |
Pandora | +0.786 |
ディ | +0.737 |
Pesh | +0.717 |
^^ | +0.716 |
Neg logit contributions | |
forging | -0.964 |
orsi | -0.962 |
ratulations | -0.958 |
remember | -0.944 |
iferation | -0.910 |
Token | of |
Token ID | 286 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Behavioral | +0.998 |
Pandora | +0.917 |
ディ | +0.851 |
Pesh | +0.832 |
^^ | +0.829 |
Neg logit contributions | |
orsi | -1.128 |
forging | -1.125 |
ratulations | -1.123 |
remember | -1.115 |
iferation | -1.070 |
Token | Trump |
Token ID | 1301 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
Behavioral | +0.751 |
Pandora | +0.689 |
ディ | +0.653 |
^^ | +0.628 |
Pesh | +0.626 |
Neg logit contributions | |
forging | -0.836 |
orsi | -0.833 |
ratulations | -0.833 |
remember | -0.820 |
iferation | -0.788 |
Token | 's |
Token ID | 338 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Behavioral | +0.660 |
Pandora | +0.602 |
ディ | +0.578 |
^^ | +0.548 |
Pesh | +0.547 |
Neg logit contributions | |
forging | -0.785 |
orsi | -0.775 |
ratulations | -0.773 |
remember | -0.768 |
iferation | -0.731 |
Token | options |
Token ID | 3689 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
Behavioral | +0.963 |
Pandora | +0.882 |
ディ | +0.831 |
^^ | +0.802 |
Pesh | +0.801 |
Neg logit contributions | |
orsi | -1.064 |
forging | -1.059 |
ratulations | -1.057 |
remember | -1.046 |
iferation | -1.004 |
Token | for |
Token ID | 329 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
Behavioral | +2.949 |
Pandora | +2.729 |
ディ | +2.518 |
^^ | +2.486 |
Possible | +2.429 |
Neg logit contributions | |
ratulations | -4.136 |
orsi | -4.113 |
forging | -4.074 |
remember | -4.036 |
iferation | -3.972 |
Token | a |
Token ID | 257 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Behavioral | +0.513 |
Pandora | +0.474 |
ディ | +0.445 |
Pesh | +0.433 |
^^ | +0.431 |
Neg logit contributions | |
orsi | -0.540 |
ratulations | -0.539 |
forging | -0.538 |
remember | -0.533 |
iferation | -0.512 |
Token | VP |
Token ID | 23342 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
forging | +0.346 |
orsi | +0.342 |
ratulations | +0.342 |
remember | +0.339 |
iferation | +0.323 |
Neg logit contributions | |
Behavioral | -0.306 |
Pandora | -0.280 |
ディ | -0.268 |
^^ | -0.256 |
Pesh | -0.255 |
Token | : |
Token ID | 25 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
Behavioral | +0.380 |
Pandora | +0.347 |
ディ | +0.334 |
^^ | +0.318 |
Pesh | +0.317 |
Neg logit contributions | |
forging | -0.415 |
orsi | -0.410 |
ratulations | -0.409 |
remember | -0.406 |
iferation | -0.386 |
Token |
|
Token ID | 198 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Behavioral | +0.312 |
Pandora | +0.283 |
ディ | +0.271 |
^^ | +0.257 |
Pesh | +0.256 |
Neg logit contributions | |
forging | -0.398 |
orsi | -0.394 |
ratulations | -0.392 |
remember | -0.390 |
iferation | -0.372 |
Token | McF |
Token ID | 38222 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
Behavioral | +0.748 |
Pandora | +0.682 |
ディ | +0.653 |
^^ | +0.625 |
Pesh | +0.625 |
Neg logit contributions | |
forging | -0.838 |
ratulations | -0.833 |
orsi | -0.833 |
remember | -0.824 |
iferation | -0.787 |
Token | adden |
Token ID | 38014 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
forging | +0.393 |
ratulations | +0.381 |
orsi | +0.380 |
remember | +0.376 |
iferation | +0.359 |
Neg logit contributions | |
Behavioral | -0.424 |
Pandora | -0.391 |
ディ | -0.374 |
^^ | -0.369 |
Bronze | -0.360 |
Token | in |
Token ID | 287 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
Behavioral | +0.201 |
Pandora | +0.181 |
ディ | +0.172 |
^^ | +0.164 |
Pesh | +0.162 |
Neg logit contributions | |
forging | -0.282 |
ratulations | -0.279 |
orsi | -0.279 |
remember | -0.276 |
iferation | -0.265 |
Token | the |
Token ID | 262 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Behavioral | +0.607 |
Pandora | +0.552 |
ディ | +0.521 |
Pesh | +0.505 |
^^ | +0.503 |
Neg logit contributions | |
ratulations | -0.691 |
orsi | -0.688 |
forging | -0.686 |
remember | -0.677 |
iferation | -0.653 |
Token | Heisman |
Token ID | 49537 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Behavioral | +0.287 |
Pandora | +0.263 |
ディ | +0.249 |
^^ | +0.241 |
Pesh | +0.240 |
Neg logit contributions | |
orsi | -0.295 |
ratulations | -0.295 |
forging | -0.295 |
remember | -0.290 |
iferation | -0.279 |
Token | Trophy |
Token ID | 25640 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
Behavioral | +1.500 |
Pandora | +1.368 |
ディ | +1.290 |
^^ | +1.238 |
Pesh | +1.225 |
Neg logit contributions | |
forging | -1.885 |
orsi | -1.871 |
ratulations | -1.866 |
remember | -1.854 |
iferation | -1.779 |
Token | race |
Token ID | 3234 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
Behavioral | +3.351 |
Pandora | +3.099 |
ディ | +2.873 |
^^ | +2.824 |
Bronze | +2.815 |
Neg logit contributions | |
orsi | -3.581 |
ratulations | -3.574 |
forging | -3.553 |
remember | -3.496 |
iferation | -3.416 |
Token | by |
Token ID | 416 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
forging | +0.640 |
orsi | +0.634 |
ratulations | +0.633 |
remember | +0.627 |
iferation | +0.600 |
Neg logit contributions | |
Behavioral | -0.508 |
Pandora | -0.463 |
ディ | -0.441 |
^^ | -0.421 |
Pesh | -0.417 |
Token | comparing |
Token ID | 14176 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
Behavioral | +0.579 |
Pandora | +0.539 |
ディ | +0.511 |
^^ | +0.501 |
Pesh | +0.499 |
Neg logit contributions | |
ratulations | -0.541 |
orsi | -0.539 |
forging | -0.523 |
remember | -0.521 |
iferation | -0.510 |
Token | him |
Token ID | 683 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
forging | +0.724 |
orsi | +0.716 |
ratulations | +0.713 |
remember | +0.709 |
iferation | +0.673 |
Neg logit contributions | |
Behavioral | -0.671 |
Pandora | -0.614 |
ディ | -0.591 |
^^ | -0.563 |
Pesh | -0.560 |
Token | to |
Token ID | 284 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Behavioral | +0.750 |
Pandora | +0.676 |
ディ | +0.645 |
^^ | +0.609 |
Pesh | +0.606 |
Neg logit contributions | |
forging | -1.057 |
orsi | -1.046 |
ratulations | -1.043 |
remember | -1.036 |
iferation | -0.992 |
Token | � |
Token ID | 447 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Behavioral | +0.655 |
Pandora | +0.597 |
ディ | +0.569 |
^^ | +0.544 |
Pesh | +0.540 |
Neg logit contributions | |
forging | -0.811 |
orsi | -0.805 |
ratulations | -0.804 |
remember | -0.794 |
iferation | -0.764 |
Token | � |
Token ID | 251 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
Behavioral | +0.818 |
Pandora | +0.744 |
ディ | +0.705 |
^^ | +0.679 |
Pesh | +0.668 |
Neg logit contributions | |
forging | -1.079 |
orsi | -1.066 |
ratulations | -1.066 |
remember | -1.049 |
iferation | -1.020 |
Token | I |
Token ID | 314 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Behavioral | +0.482 |
Pandora | +0.439 |
ディ | +0.416 |
^^ | +0.400 |
Pesh | +0.396 |
Neg logit contributions | |
forging | -0.609 |
orsi | -0.604 |
ratulations | -0.603 |
remember | -0.595 |
iferation | -0.574 |
Token | put |
Token ID | 1234 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Behavioral | +1.350 |
Pandora | +1.244 |
ディ | +1.171 |
^^ | +1.144 |
Pesh | +1.131 |
Neg logit contributions | |
orsi | -1.606 |
forging | -1.597 |
ratulations | -1.594 |
remember | -1.532 |
iferation | -1.525 |
Token | my |
Token ID | 616 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Behavioral | +1.166 |
Pandora | +1.076 |
ディ | +1.012 |
^^ | +0.977 |
Pesh | +0.970 |
Neg logit contributions | |
orsi | -1.405 |
forging | -1.404 |
ratulations | -1.394 |
remember | -1.376 |
iferation | -1.334 |
Token | heart |
Token ID | 2612 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
Behavioral | +1.665 |
Pandora | +1.541 |
ディ | +1.448 |
Pesh | +1.414 |
Bronze | +1.407 |
Neg logit contributions | |
orsi | -1.672 |
ratulations | -1.665 |
forging | -1.650 |
remember | -1.633 |
iferation | -1.590 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Behavioral | +2.420 |
Pandora | +2.213 |
ディ | +2.056 |
^^ | +2.027 |
Bronze | +1.930 |
Neg logit contributions | |
orsi | -4.190 |
ratulations | -4.181 |
forging | -4.157 |
remember | -4.116 |
iferation | -4.009 |
Token | my |
Token ID | 616 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Behavioral | +1.082 |
Pandora | +0.998 |
ディ | +0.928 |
Pesh | +0.905 |
^^ | +0.902 |
Neg logit contributions | |
ratulations | -1.328 |
forging | -1.325 |
orsi | -1.323 |
remember | -1.304 |
iferation | -1.276 |
Token | soul |
Token ID | 5848 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Behavioral | +1.858 |
Pandora | +1.720 |
ディ | +1.602 |
Pesh | +1.588 |
Bronze | +1.574 |
Neg logit contributions | |
orsi | -2.123 |
ratulations | -2.123 |
forging | -2.092 |
remember | -2.082 |
iferation | -2.046 |
Token | into |
Token ID | 656 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
Behavioral | +1.340 |
Pandora | +1.202 |
ディ | +1.090 |
^^ | +1.073 |
Pesh | +1.027 |
Neg logit contributions | |
ratulations | -2.782 |
forging | -2.764 |
orsi | -2.762 |
remember | -2.731 |
iferation | -2.663 |
Token | that |
Token ID | 326 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
forging | +0.510 |
orsi | +0.507 |
ratulations | +0.507 |
remember | +0.501 |
iferation | +0.480 |
Neg logit contributions | |
Behavioral | -0.462 |
Pandora | -0.424 |
ディ | -0.406 |
^^ | -0.388 |
Pesh | -0.386 |
Token |
|
Token ID | 198 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
forging | +0.559 |
orsi | +0.554 |
ratulations | +0.552 |
remember | +0.550 |
iferation | +0.524 |
Neg logit contributions | |
Behavioral | -0.411 |
Pandora | -0.372 |
ディ | -0.356 |
^^ | -0.336 |
Pesh | -0.335 |
Token |
|
Token ID | 198 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
ratulations | +0.286 |
forging | +0.285 |
orsi | +0.283 |
remember | +0.273 |
merce | +0.272 |
Neg logit contributions | |
Behavioral | -0.171 |
Pandora | -0.153 |
ディ | -0.142 |
^^ | -0.140 |
Bronze | -0.135 |
Token | @ |
Token ID | 31 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
Behavioral | +0.069 |
Pandora | +0.063 |
ディ | +0.062 |
^^ | +0.060 |
Pesh | +0.058 |
Neg logit contributions | |
forging | -0.069 |
ratulations | -0.068 |
orsi | -0.068 |
remember | -0.066 |
iferation | -0.064 |
Token | Ann |
Token ID | 18858 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
forging | +0.422 |
ratulations | +0.414 |
orsi | +0.414 |
remember | +0.406 |
iferation | +0.386 |
Neg logit contributions | |
Behavioral | -0.555 |
Pandora | -0.517 |
ディ | -0.501 |
^^ | -0.483 |
Pesh | -0.479 |
Token | C |
Token ID | 34 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Behavioral | +2.154 |
Pandora | +1.999 |
ディ | +1.958 |
^^ | +1.876 |
Pesh | +1.854 |
Neg logit contributions | |
forging | -1.960 |
ratulations | -1.917 |
orsi | -1.904 |
remember | -1.871 |
iferation | -1.801 |
Token | oul |
Token ID | 2852 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
Behavioral | +1.857 |
Pandora | +1.734 |
ディ | +1.661 |
^^ | +1.622 |
Stephenson | +1.596 |
Neg logit contributions | |
forging | -1.572 |
ratulations | -1.520 |
remember | -1.508 |
orsi | -1.486 |
deadlines | -1.433 |
Token | ter |
Token ID | 353 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Behavioral | +3.449 |
Pandora | +3.189 |
ディ | +3.042 |
^^ | +2.990 |
Stephenson | +2.907 |
Neg logit contributions | |
forging | -3.567 |
ratulations | -3.490 |
orsi | -3.418 |
remember | -3.377 |
iferation | -3.331 |
Token | HAVE |
Token ID | 21515 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Behavioral | +0.890 |
Pandora | +0.817 |
ディ | +0.777 |
^^ | +0.751 |
Pesh | +0.743 |
Neg logit contributions | |
forging | -0.981 |
orsi | -0.968 |
ratulations | -0.963 |
remember | -0.949 |
iferation | -0.919 |
Token | YOU |
Token ID | 7013 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Behavioral | +1.259 |
Pandora | +1.151 |
ディ | +1.068 |
^^ | +1.047 |
Possible | +1.025 |
Neg logit contributions | |
forging | -1.589 |
orsi | -1.574 |
ratulations | -1.572 |
remember | -1.558 |
iferation | -1.512 |
Token | SE |
Token ID | 7946 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Behavioral | +1.107 |
Pandora | +1.018 |
ディ | +0.961 |
^^ | +0.945 |
Pesh | +0.927 |
Neg logit contributions | |
forging | -1.158 |
orsi | -1.153 |
ratulations | -1.150 |
remember | -1.117 |
iferation | -1.095 |
Token | EN |
Token ID | 1677 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
forging | +1.040 |
orsi | +1.029 |
ratulations | +1.028 |
remember | +1.017 |
iferation | +0.970 |
Neg logit contributions | |
Behavioral | -0.947 |
Pandora | -0.868 |
ディ | -0.832 |
^^ | -0.796 |
Pesh | -0.790 |
Token | they |
Token ID | 484 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Behavioral | +0.285 |
Pandora | +0.259 |
ディ | +0.245 |
Pesh | +0.234 |
^^ | +0.234 |
Neg logit contributions | |
forging | -0.359 |
orsi | -0.359 |
ratulations | -0.359 |
remember | -0.354 |
iferation | -0.341 |
Token | said |
Token ID | 531 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
forging | +1.225 |
orsi | +1.211 |
ratulations | +1.208 |
remember | +1.202 |
iferation | +1.146 |
Neg logit contributions | |
Behavioral | -0.950 |
Pandora | -0.862 |
ディ | -0.827 |
^^ | -0.783 |
Pesh | -0.779 |
Token | . |
Token ID | 13 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
forging | +1.341 |
ratulations | +1.300 |
orsi | +1.294 |
remember | +1.286 |
deadlines | +1.226 |
Neg logit contributions | |
Behavioral | -1.327 |
Pandora | -1.214 |
ディ | -1.195 |
^^ | -1.119 |
IRD | -1.108 |
Token |
|
Token ID | 198 |
Feature activation | +9.64e-03 |
Pos logit contributions | |
forging | +0.375 |
orsi | +0.371 |
remember | +0.369 |
ratulations | +0.368 |
sbm | +0.350 |
Neg logit contributions | |
Behavioral | -0.290 |
Pandora | -0.263 |
ディ | -0.255 |
^^ | -0.241 |
Pesh | -0.238 |
Token |
|
Token ID | 198 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Behavioral | +0.005 |
Pandora | +0.005 |
ディ | +0.004 |
^^ | +0.004 |
Bronze | +0.004 |
Neg logit contributions | |
ratulations | -0.009 |
forging | -0.009 |
orsi | -0.009 |
merce | -0.009 |
remember | -0.009 |
Token | P |
Token ID | 47 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
Behavioral | +0.242 |
Pandora | +0.222 |
ディ | +0.215 |
^^ | +0.207 |
Pesh | +0.204 |
Neg logit contributions | |
forging | -0.234 |
orsi | -0.231 |
ratulations | -0.230 |
remember | -0.225 |
iferation | -0.217 |
Token | eder |
Token ID | 5702 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
Behavioral | +0.524 |
Pandora | +0.487 |
ディ | +0.469 |
^^ | +0.460 |
Bronze | +0.452 |
Neg logit contributions | |
forging | -0.413 |
ratulations | -0.405 |
orsi | -0.398 |
remember | -0.396 |
merce | -0.380 |
Token | was |
Token ID | 373 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
Behavioral | +0.472 |
Pandora | +0.429 |
ディ | +0.405 |
^^ | +0.387 |
Pesh | +0.385 |
Neg logit contributions | |
forging | -0.615 |
ratulations | -0.613 |
orsi | -0.612 |
remember | -0.606 |
iferation | -0.582 |
Token | charged |
Token ID | 5047 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Behavioral | +0.125 |
Pandora | +0.115 |
ディ | +0.108 |
^^ | +0.104 |
Pesh | +0.104 |
Neg logit contributions | |
orsi | -0.148 |
ratulations | -0.148 |
forging | -0.147 |
remember | -0.146 |
iferation | -0.140 |
Token | in |
Token ID | 287 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
forging | +1.389 |
orsi | +1.359 |
remember | +1.349 |
ratulations | +1.349 |
deadlines | +1.287 |
Neg logit contributions | |
Behavioral | -1.124 |
Pandora | -1.027 |
ディ | -0.992 |
^^ | -0.936 |
Pesh | -0.931 |
Token | December |
Token ID | 3426 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
forging | +0.915 |
orsi | +0.907 |
ratulations | +0.905 |
remember | +0.898 |
iferation | +0.856 |
Neg logit contributions | |
Behavioral | -0.787 |
Pandora | -0.718 |
ディ | -0.686 |
^^ | -0.654 |
Pesh | -0.653 |
Token | ) |
Token ID | 8 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
forging | +1.374 |
orsi | +1.358 |
ratulations | +1.352 |
remember | +1.344 |
iferation | +1.276 |
Neg logit contributions | |
Behavioral | -1.326 |
Pandora | -1.216 |
ディ | -1.171 |
^^ | -1.116 |
Pesh | -1.114 |
Token | in |
Token ID | 287 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
forging | +0.981 |
orsi | +0.970 |
ratulations | +0.965 |
remember | +0.962 |
iferation | +0.915 |
Neg logit contributions | |
Behavioral | -0.777 |
Pandora | -0.706 |
ディ | -0.678 |
Pesh | -0.639 |
^^ | -0.639 |
Token | March |
Token ID | 2805 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
forging | +0.270 |
orsi | +0.268 |
ratulations | +0.268 |
remember | +0.265 |
iferation | +0.254 |
Neg logit contributions | |
Behavioral | -0.237 |
Pandora | -0.217 |
ディ | -0.206 |
^^ | -0.197 |
Pesh | -0.197 |
Token | and |
Token ID | 290 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Behavioral | +0.064 |
Pandora | +0.058 |
ディ | +0.056 |
^^ | +0.053 |
Pesh | +0.053 |
Neg logit contributions | |
forging | -0.077 |
orsi | -0.076 |
ratulations | -0.076 |
remember | -0.076 |
iferation | -0.072 |
Token | early |
Token ID | 1903 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Behavioral | +0.250 |
Pandora | +0.229 |
ディ | +0.215 |
Pesh | +0.209 |
^^ | +0.207 |
Neg logit contributions | |
forging | -0.275 |
ratulations | -0.274 |
orsi | -0.273 |
remember | -0.270 |
iferation | -0.260 |
Token | April |
Token ID | 3035 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Behavioral | +0.894 |
Pandora | +0.817 |
ディ | +0.776 |
Pesh | +0.744 |
^^ | +0.742 |
Neg logit contributions | |
forging | -0.995 |
ratulations | -0.990 |
orsi | -0.989 |
remember | -0.977 |
iferation | -0.938 |
Token | and |
Token ID | 290 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
Behavioral | +1.053 |
Pandora | +0.954 |
ディ | +0.910 |
^^ | +0.872 |
Pesh | +0.865 |
Neg logit contributions | |
forging | -1.292 |
ratulations | -1.280 |
orsi | -1.278 |
remember | -1.267 |
iferation | -1.215 |
Token | pass |
Token ID | 1208 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Behavioral | +0.195 |
Pandora | +0.178 |
ディ | +0.169 |
^^ | +0.163 |
Pesh | +0.163 |
Neg logit contributions | |
forging | -0.210 |
ratulations | -0.209 |
orsi | -0.208 |
remember | -0.206 |
iferation | -0.197 |
Token | cub |
Token ID | 13617 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Behavioral | +0.074 |
Pandora | +0.068 |
ディ | +0.064 |
^^ | +0.062 |
Pesh | +0.062 |
Neg logit contributions | |
forging | -0.086 |
orsi | -0.086 |
ratulations | -0.085 |
remember | -0.085 |
iferation | -0.081 |
Token | s |
Token ID | 82 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Behavioral | +0.255 |
Pandora | +0.234 |
ディ | +0.224 |
^^ | +0.215 |
Pesh | +0.214 |
Neg logit contributions | |
forging | -0.264 |
orsi | -0.261 |
ratulations | -0.261 |
remember | -0.258 |
iferation | -0.246 |
Token | around |
Token ID | 1088 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
forging | +0.318 |
orsi | +0.316 |
ratulations | +0.316 |
remember | +0.313 |
iferation | +0.300 |
Neg logit contributions | |
Behavioral | -0.235 |
Pandora | -0.213 |
ディ | -0.200 |
^^ | -0.193 |
Pesh | -0.191 |
Token | husband |
Token ID | 5229 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
Behavioral | +0.362 |
Pandora | +0.329 |
ディ | +0.310 |
Pesh | +0.301 |
^^ | +0.298 |
Neg logit contributions | |
ratulations | -0.431 |
forging | -0.431 |
orsi | -0.431 |
remember | -0.427 |
iferation | -0.411 |
Token | Nat |
Token ID | 14393 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
Behavioral | +0.054 |
Pandora | +0.049 |
ディ | +0.047 |
^^ | +0.044 |
Pesh | +0.044 |
Neg logit contributions | |
forging | -0.071 |
orsi | -0.071 |
ratulations | -0.070 |
remember | -0.070 |
iferation | -0.067 |
Token | v |
Token ID | 85 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Behavioral | +0.433 |
Pandora | +0.401 |
ディ | +0.386 |
^^ | +0.372 |
Pesh | +0.371 |
Neg logit contributions | |
forging | -0.371 |
ratulations | -0.364 |
orsi | -0.364 |
remember | -0.360 |
iferation | -0.340 |
Token | arl |
Token ID | 7063 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
forging | +0.754 |
orsi | +0.750 |
ratulations | +0.746 |
remember | +0.737 |
iferation | +0.700 |
Neg logit contributions | |
Behavioral | -0.844 |
Pandora | -0.776 |
ディ | -0.752 |
^^ | -0.718 |
Pesh | -0.715 |
Token | al |
Token ID | 282 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Behavioral | +1.392 |
Pandora | +1.298 |
ディ | +1.241 |
Pesh | +1.203 |
^^ | +1.202 |
Neg logit contributions | |
forging | -1.130 |
orsi | -1.117 |
ratulations | -1.113 |
remember | -1.099 |
iferation | -1.038 |
Token | , |
Token ID | 11 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Behavioral | +1.409 |
Pandora | +1.288 |
ディ | +1.216 |
Pesh | +1.174 |
^^ | +1.168 |
Neg logit contributions | |
forging | -1.727 |
ratulations | -1.710 |
orsi | -1.708 |
remember | -1.692 |
iferation | -1.628 |
Token | who |
Token ID | 508 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Behavioral | +1.205 |
Pandora | +1.097 |
ディ | +1.035 |
Pesh | +1.013 |
^^ | +0.995 |
Neg logit contributions | |
ratulations | -1.490 |
orsi | -1.486 |
forging | -1.480 |
remember | -1.461 |
iferation | -1.423 |
Token | was |
Token ID | 373 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Behavioral | +0.187 |
Pandora | +0.170 |
ディ | +0.161 |
Pesh | +0.153 |
^^ | +0.153 |
Neg logit contributions | |
forging | -0.263 |
ratulations | -0.262 |
orsi | -0.262 |
remember | -0.259 |
iferation | -0.249 |
Token | following |
Token ID | 1708 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
Behavioral | +0.667 |
Pandora | +0.610 |
ディ | +0.577 |
Pesh | +0.561 |
Bronze | +0.553 |
Neg logit contributions | |
orsi | -0.840 |
ratulations | -0.838 |
forging | -0.833 |
remember | -0.833 |
iferation | -0.808 |
Token | her |
Token ID | 607 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Behavioral | +0.412 |
Pandora | +0.379 |
ディ | +0.361 |
Pesh | +0.348 |
^^ | +0.347 |
Neg logit contributions | |
forging | -0.435 |
orsi | -0.432 |
ratulations | -0.429 |
remember | -0.427 |
iferation | -0.406 |
Token | upstairs |
Token ID | 26148 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
forging | +1.067 |
orsi | +1.051 |
ratulations | +1.048 |
remember | +1.043 |
iferation | +0.993 |
Neg logit contributions | |
Behavioral | -0.868 |
Pandora | -0.789 |
ディ | -0.761 |
^^ | -0.718 |
Pesh | -0.713 |
Token | managed |
Token ID | 5257 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
Behavioral | +0.164 |
Pandora | +0.150 |
ディ | +0.140 |
^^ | +0.136 |
Pesh | +0.134 |
Neg logit contributions | |
ratulations | -0.233 |
forging | -0.233 |
orsi | -0.232 |
remember | -0.229 |
iferation | -0.223 |
Token | to |
Token ID | 284 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
Behavioral | +0.245 |
Pandora | +0.218 |
ディ | +0.210 |
Pesh | +0.198 |
^^ | +0.197 |
Neg logit contributions | |
forging | -0.319 |
ratulations | -0.314 |
orsi | -0.314 |
remember | -0.313 |
iferation | -0.297 |
Token | control |
Token ID | 1630 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
Behavioral | +0.720 |
Pandora | +0.672 |
ディ | +0.625 |
^^ | +0.616 |
Pesh | +0.607 |
Neg logit contributions | |
orsi | -0.754 |
ratulations | -0.753 |
forging | -0.746 |
remember | -0.729 |
iferation | -0.714 |
Token | his |
Token ID | 465 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
forging | +0.056 |
orsi | +0.055 |
ratulations | +0.055 |
remember | +0.055 |
iferation | +0.052 |
Neg logit contributions | |
Behavioral | -0.039 |
Pandora | -0.035 |
ディ | -0.034 |
^^ | -0.032 |
Pesh | -0.032 |
Token | anger |
Token ID | 8993 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Behavioral | +0.553 |
Pandora | +0.508 |
ディ | +0.480 |
^^ | +0.466 |
Pesh | +0.465 |
Neg logit contributions | |
orsi | -0.554 |
ratulations | -0.553 |
forging | -0.552 |
remember | -0.544 |
iferation | -0.520 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Behavioral | +0.070 |
Pandora | +0.064 |
ディ | +0.061 |
^^ | +0.058 |
Pesh | +0.057 |
Neg logit contributions | |
forging | -0.087 |
ratulations | -0.087 |
orsi | -0.087 |
remember | -0.086 |
iferation | -0.082 |
Token | � |
Token ID | 564 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
Behavioral | +0.694 |
Pandora | +0.630 |
ディ | +0.597 |
^^ | +0.570 |
Pesh | +0.564 |
Neg logit contributions | |
forging | -0.952 |
ratulations | -0.948 |
orsi | -0.947 |
remember | -0.930 |
iferation | -0.900 |
Token | � |
Token ID | 250 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
Behavioral | +0.507 |
Pandora | +0.462 |
ディ | +0.446 |
^^ | +0.427 |
Pesh | +0.421 |
Neg logit contributions | |
forging | -0.598 |
orsi | -0.592 |
ratulations | -0.592 |
remember | -0.581 |
iferation | -0.561 |
Token | Orange |
Token ID | 40141 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
forging | +0.293 |
orsi | +0.289 |
ratulations | +0.288 |
remember | +0.282 |
iferation | +0.271 |
Neg logit contributions | |
Behavioral | -0.324 |
Pandora | -0.300 |
ディ | -0.290 |
^^ | -0.280 |
Pesh | -0.276 |
Token | head |
Token ID | 2256 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Behavioral | +0.051 |
Pandora | +0.047 |
ディ | +0.045 |
^^ | +0.043 |
Pesh | +0.042 |
Neg logit contributions | |
forging | -0.060 |
orsi | -0.059 |
ratulations | -0.059 |
remember | -0.059 |
iferation | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
Behavioral | +0.112 |
Pandora | +0.102 |
ディ | +0.098 |
^^ | +0.094 |
Pesh | +0.093 |
Neg logit contributions | |
forging | -0.131 |
orsi | -0.129 |
ratulations | -0.129 |
remember | -0.128 |
iferation | -0.122 |
Token | ians |
Token ID | 1547 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Behavioral | +0.016 |
Pandora | +0.015 |
ディ | +0.015 |
^^ | +0.014 |
Pesh | +0.014 |
Neg logit contributions | |
forging | -0.012 |
orsi | -0.012 |
ratulations | -0.012 |
remember | -0.012 |
iferation | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
forging | +1.880 |
orsi | +1.860 |
ratulations | +1.855 |
remember | +1.842 |
iferation | +1.754 |
Neg logit contributions | |
Behavioral | -1.685 |
Pandora | -1.541 |
ディ | -1.479 |
^^ | -1.411 |
Pesh | -1.404 |
Token | at |
Token ID | 379 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
forging | +1.112 |
orsi | +1.102 |
ratulations | +1.101 |
remember | +1.091 |
iferation | +1.044 |
Neg logit contributions | |
Behavioral | -0.926 |
Pandora | -0.845 |
ディ | -0.807 |
^^ | -0.771 |
Pesh | -0.766 |
Token | least |
Token ID | 1551 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Behavioral | +0.092 |
Pandora | +0.084 |
ディ | +0.080 |
^^ | +0.076 |
Pesh | +0.076 |
Neg logit contributions | |
forging | -0.112 |
ratulations | -0.112 |
orsi | -0.112 |
remember | -0.110 |
iferation | -0.106 |
Token | not |
Token ID | 407 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
forging | +0.244 |
orsi | +0.242 |
ratulations | +0.242 |
remember | +0.240 |
iferation | +0.230 |
Neg logit contributions | |
Behavioral | -0.169 |
Pandora | -0.153 |
ディ | -0.145 |
^^ | -0.137 |
Pesh | -0.137 |
Token | before |
Token ID | 878 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
Behavioral | +0.094 |
Pandora | +0.086 |
ディ | +0.081 |
^^ | +0.078 |
Pesh | +0.077 |
Neg logit contributions | |
forging | -0.128 |
ratulations | -0.128 |
orsi | -0.128 |
remember | -0.127 |
iferation | -0.122 |
Token | we |
Token ID | 356 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
Behavioral | +0.622 |
Pandora | +0.574 |
ディ | +0.541 |
^^ | +0.527 |
Pesh | +0.522 |
Neg logit contributions | |
orsi | -0.713 |
ratulations | -0.711 |
forging | -0.709 |
remember | -0.702 |
iferation | -0.680 |
Token | lost |
Token ID | 2626 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Behavioral | +0.020 |
Pandora | +0.018 |
ディ | +0.017 |
^^ | +0.017 |
Pesh | +0.017 |
Neg logit contributions | |
forging | -0.020 |
orsi | -0.020 |
ratulations | -0.020 |
remember | -0.019 |
iferation | -0.018 |
Token | our |
Token ID | 674 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
Behavioral | +1.284 |
Pandora | +1.185 |
ディ | +1.115 |
^^ | +1.078 |
Pesh | +1.073 |
Neg logit contributions | |
forging | -1.512 |
orsi | -1.506 |
ratulations | -1.502 |
remember | -1.483 |
iferation | -1.433 |
Token | collective |
Token ID | 10098 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Behavioral | +0.052 |
Pandora | +0.048 |
ディ | +0.046 |
^^ | +0.044 |
Pesh | +0.044 |
Neg logit contributions | |
forging | -0.052 |
orsi | -0.051 |
ratulations | -0.051 |
remember | -0.050 |
iferation | -0.048 |
Token | minds |
Token ID | 9017 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
forging | +0.885 |
orsi | +0.873 |
ratulations | +0.871 |
remember | +0.866 |
iferation | +0.819 |
Neg logit contributions | |
Behavioral | -0.850 |
Pandora | -0.778 |
ディ | -0.752 |
^^ | -0.716 |
Pesh | -0.713 |
Token | . |
Token ID | 13 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
forging | +0.014 |
ratulations | +0.014 |
orsi | +0.014 |
remember | +0.014 |
iferation | +0.013 |
Neg logit contributions | |
Behavioral | -0.011 |
Pandora | -0.010 |
ディ | -0.010 |
^^ | -0.010 |
Pesh | -0.009 |
Token | � |
Token ID | 447 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Behavioral | +0.427 |
Pandora | +0.389 |
ディ | +0.364 |
^^ | +0.352 |
Pesh | +0.350 |
Neg logit contributions | |
forging | -0.552 |
ratulations | -0.552 |
orsi | -0.547 |
remember | -0.537 |
iferation | -0.522 |
Token | � |
Token ID | 251 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Behavioral | +0.261 |
Pandora | +0.231 |
ディ | +0.218 |
^^ | +0.205 |
Pesh | +0.202 |
Neg logit contributions | |
forging | -0.473 |
orsi | -0.468 |
ratulations | -0.468 |
remember | -0.464 |
iferation | -0.447 |
Token | Well |
Token ID | 3894 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Behavioral | +0.104 |
Pandora | +0.095 |
ディ | +0.090 |
^^ | +0.086 |
Pesh | +0.086 |
Neg logit contributions | |
forging | -0.135 |
ratulations | -0.133 |
orsi | -0.133 |
remember | -0.132 |
iferation | -0.127 |
Token | , |
Token ID | 11 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
forging | +1.620 |
orsi | +1.594 |
remember | +1.594 |
ratulations | +1.590 |
deadlines | +1.496 |
Neg logit contributions | |
Behavioral | -1.461 |
Pandora | -1.321 |
ディ | -1.292 |
Pesh | -1.211 |
^^ | -1.204 |
Token | after |
Token ID | 706 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
forging | +0.891 |
orsi | +0.881 |
ratulations | +0.878 |
remember | +0.873 |
iferation | +0.831 |
Neg logit contributions | |
Behavioral | -0.755 |
Pandora | -0.687 |
ディ | -0.661 |
^^ | -0.627 |
Pesh | -0.625 |
Token | that |
Token ID | 326 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
forging | +0.955 |
orsi | +0.951 |
ratulations | +0.950 |
remember | +0.939 |
iferation | +0.901 |
Neg logit contributions | |
Behavioral | -0.854 |
Pandora | -0.785 |
ディ | -0.746 |
^^ | -0.716 |
Pesh | -0.713 |
Token | I |
Token ID | 314 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Behavioral | +0.234 |
Pandora | +0.212 |
ディ | +0.204 |
^^ | +0.193 |
Pesh | +0.192 |
Neg logit contributions | |
forging | -0.297 |
orsi | -0.294 |
ratulations | -0.293 |
remember | -0.291 |
iferation | -0.278 |
Token | did |
Token ID | 750 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
forging | +0.462 |
orsi | +0.458 |
ratulations | +0.458 |
remember | +0.451 |
iferation | +0.437 |
Neg logit contributions | |
Behavioral | -0.320 |
Pandora | -0.290 |
ディ | -0.274 |
^^ | -0.262 |
Pesh | -0.259 |
Token | give |
Token ID | 1577 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
forging | +0.739 |
orsi | +0.733 |
ratulations | +0.731 |
remember | +0.724 |
iferation | +0.694 |
Neg logit contributions | |
Behavioral | -0.611 |
Pandora | -0.557 |
ディ | -0.531 |
^^ | -0.508 |
Pesh | -0.504 |
Token | it |
Token ID | 340 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
forging | +1.661 |
ratulations | +1.630 |
orsi | +1.626 |
remember | +1.623 |
deadlines | +1.543 |
Neg logit contributions | |
Behavioral | -1.397 |
Pandora | -1.261 |
ディ | -1.229 |
Pesh | -1.154 |
^^ | -1.153 |
Token | basis |
Token ID | 4308 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Behavioral | +0.825 |
Pandora | +0.726 |
ディ | +0.672 |
^^ | +0.633 |
Pesh | +0.626 |
Neg logit contributions | |
forging | -1.660 |
ratulations | -1.657 |
orsi | -1.656 |
remember | -1.640 |
iferation | -1.582 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Behavioral | +0.796 |
Pandora | +0.725 |
ディ | +0.692 |
^^ | +0.667 |
Pesh | +0.654 |
Neg logit contributions | |
forging | -0.969 |
ratulations | -0.966 |
orsi | -0.966 |
remember | -0.954 |
iferation | -0.915 |
Token |
|
Token ID | 198 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
forging | +0.237 |
orsi | +0.235 |
ratulations | +0.235 |
remember | +0.232 |
iferation | +0.223 |
Neg logit contributions | |
Behavioral | -0.181 |
Pandora | -0.164 |
ディ | -0.156 |
^^ | -0.149 |
Pesh | -0.148 |
Token |
|
Token ID | 198 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
ratulations | +0.428 |
forging | +0.427 |
orsi | +0.424 |
remember | +0.410 |
merce | +0.406 |
Neg logit contributions | |
Behavioral | -0.262 |
Pandora | -0.236 |
ディ | -0.220 |
^^ | -0.214 |
Bronze | -0.207 |
Token | The |
Token ID | 464 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
forging | +0.348 |
orsi | +0.343 |
ratulations | +0.343 |
remember | +0.332 |
iferation | +0.322 |
Neg logit contributions | |
Behavioral | -0.370 |
Pandora | -0.341 |
ディ | -0.332 |
^^ | -0.321 |
Pesh | -0.313 |
Token | pilot |
Token ID | 8022 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
forging | +0.368 |
orsi | +0.365 |
ratulations | +0.364 |
remember | +0.361 |
iferation | +0.345 |
Neg logit contributions | |
Behavioral | -0.298 |
Pandora | -0.271 |
ディ | -0.258 |
^^ | -0.246 |
Pesh | -0.245 |
Token | introduced |
Token ID | 5495 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Behavioral | +0.382 |
Pandora | +0.347 |
ディ | +0.333 |
^^ | +0.316 |
Pesh | +0.314 |
Neg logit contributions | |
forging | -0.477 |
orsi | -0.472 |
ratulations | -0.471 |
remember | -0.468 |
iferation | -0.446 |
Token | us |
Token ID | 514 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Behavioral | +0.684 |
Pandora | +0.626 |
ディ | +0.593 |
^^ | +0.569 |
Pesh | +0.563 |
Neg logit contributions | |
forging | -0.832 |
orsi | -0.830 |
ratulations | -0.827 |
remember | -0.819 |
iferation | -0.786 |
Token | to |
Token ID | 284 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
forging | +1.190 |
orsi | +1.171 |
ratulations | +1.170 |
remember | +1.164 |
iferation | +1.107 |
Neg logit contributions | |
Behavioral | -0.885 |
Pandora | -0.794 |
ディ | -0.765 |
Pesh | -0.721 |
^^ | -0.718 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
forging | +0.456 |
orsi | +0.452 |
ratulations | +0.451 |
remember | +0.447 |
iferation | +0.428 |
Neg logit contributions | |
Behavioral | -0.331 |
Pandora | -0.299 |
ディ | -0.285 |
^^ | -0.270 |
Pesh | -0.269 |
Token | LOT |
Token ID | 30314 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Behavioral | +0.101 |
Pandora | +0.093 |
ディ | +0.089 |
^^ | +0.085 |
Pesh | +0.085 |
Neg logit contributions | |
forging | -0.107 |
orsi | -0.106 |
ratulations | -0.106 |
remember | -0.105 |
iferation | -0.100 |
Token | both |
Token ID | 1111 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
Behavioral | +0.106 |
Pandora | +0.097 |
ディ | +0.094 |
^^ | +0.089 |
Pesh | +0.088 |
Neg logit contributions | |
forging | -0.113 |
ratulations | -0.111 |
orsi | -0.111 |
remember | -0.110 |
iferation | -0.105 |
Token | died |
Token ID | 3724 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
Behavioral | +0.424 |
Pandora | +0.382 |
ディ | +0.364 |
^^ | +0.343 |
Pesh | +0.341 |
Neg logit contributions | |
forging | -0.620 |
orsi | -0.613 |
ratulations | -0.612 |
remember | -0.608 |
iferation | -0.582 |
Token | of |
Token ID | 286 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
forging | +0.401 |
orsi | +0.399 |
ratulations | +0.398 |
remember | +0.395 |
iferation | +0.378 |
Neg logit contributions | |
Behavioral | -0.328 |
Pandora | -0.299 |
ディ | -0.286 |
^^ | -0.274 |
Pesh | -0.273 |
Token | cerebral |
Token ID | 31169 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
forging | +0.621 |
orsi | +0.613 |
ratulations | +0.610 |
remember | +0.606 |
iferation | +0.573 |
Neg logit contributions | |
Behavioral | -0.678 |
Pandora | -0.625 |
ディ | -0.604 |
^^ | -0.578 |
Pesh | -0.575 |
Token | ha |
Token ID | 387 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
forging | +0.946 |
ratulations | +0.935 |
orsi | +0.935 |
remember | +0.928 |
iferation | +0.885 |
Neg logit contributions | |
Behavioral | -0.863 |
Pandora | -0.790 |
ディ | -0.756 |
^^ | -0.723 |
Pesh | -0.721 |
Token | em |
Token ID | 368 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
forging | +0.658 |
orsi | +0.646 |
ratulations | +0.644 |
remember | +0.637 |
iferation | +0.592 |
Neg logit contributions | |
Behavioral | -1.188 |
Pandora | -1.113 |
ディ | -1.081 |
^^ | -1.046 |
Pesh | -1.042 |
Token | or |
Token ID | 273 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Behavioral | +0.244 |
Pandora | +0.224 |
ディ | +0.215 |
^^ | +0.206 |
Pesh | +0.206 |
Neg logit contributions | |
forging | -0.240 |
orsi | -0.237 |
ratulations | -0.237 |
remember | -0.235 |
iferation | -0.223 |
Token | rh |
Token ID | 17179 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
forging | +1.579 |
orsi | +1.557 |
ratulations | +1.549 |
remember | +1.538 |
iferation | +1.446 |
Neg logit contributions | |
Behavioral | -2.088 |
Pandora | -1.941 |
ディ | -1.871 |
^^ | -1.809 |
Pesh | -1.803 |
Token | age |
Token ID | 496 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
forging | +0.861 |
orsi | +0.855 |
ratulations | +0.851 |
remember | +0.846 |
iferation | +0.815 |
Neg logit contributions | |
Behavioral | -0.557 |
Pandora | -0.498 |
ディ | -0.480 |
^^ | -0.445 |
Pesh | -0.444 |
Token | ," |
Token ID | 553 |
Feature activation | -6.24e-03 |
Pos logit contributions | |
forging | +0.201 |
orsi | +0.199 |
ratulations | +0.198 |
remember | +0.197 |
iferation | +0.187 |
Neg logit contributions | |
Behavioral | -0.183 |
Pandora | -0.167 |
ディ | -0.160 |
^^ | -0.153 |
Pesh | -0.152 |
Token | said |
Token ID | 531 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
forging | +0.005 |
orsi | +0.005 |
ratulations | +0.005 |
remember | +0.005 |
iferation | +0.005 |
Neg logit contributions | |
Behavioral | -0.004 |
Pandora | -0.004 |
ディ | -0.004 |
^^ | -0.003 |
Pesh | -0.003 |
Token | types |
Token ID | 3858 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
forging | +0.298 |
orsi | +0.295 |
ratulations | +0.295 |
remember | +0.292 |
iferation | +0.278 |
Neg logit contributions | |
Behavioral | -0.300 |
Pandora | -0.276 |
ディ | -0.263 |
^^ | -0.253 |
Pesh | -0.252 |
Token | of |
Token ID | 286 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
ratulations | +0.945 |
forging | +0.941 |
orsi | +0.940 |
remember | +0.922 |
iferation | +0.896 |
Neg logit contributions | |
Behavioral | -0.739 |
Pandora | -0.673 |
ディ | -0.632 |
^^ | -0.614 |
Pesh | -0.598 |
Token | data |
Token ID | 1366 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
forging | +0.239 |
orsi | +0.238 |
ratulations | +0.238 |
remember | +0.234 |
iferation | +0.222 |
Neg logit contributions | |
Behavioral | -0.344 |
Pandora | -0.320 |
ディ | -0.306 |
^^ | -0.297 |
Pesh | -0.297 |
Token | structures |
Token ID | 8573 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
forging | +0.621 |
orsi | +0.621 |
ratulations | +0.620 |
remember | +0.613 |
iferation | +0.584 |
Neg logit contributions | |
Behavioral | -0.668 |
Pandora | -0.614 |
ディ | -0.589 |
^^ | -0.566 |
Pesh | -0.563 |
Token | in |
Token ID | 287 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
forging | +0.455 |
orsi | +0.451 |
ratulations | +0.450 |
remember | +0.446 |
iferation | +0.426 |
Neg logit contributions | |
Behavioral | -0.384 |
Pandora | -0.350 |
ディ | -0.335 |
^^ | -0.320 |
Pesh | -0.318 |
Token | C |
Token ID | 327 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
forging | +0.541 |
ratulations | +0.539 |
orsi | +0.538 |
remember | +0.532 |
iferation | +0.509 |
Neg logit contributions | |
Behavioral | -0.441 |
Pandora | -0.402 |
ディ | -0.380 |
^^ | -0.363 |
Pesh | -0.362 |
Token | and |
Token ID | 290 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
forging | +0.513 |
orsi | +0.508 |
ratulations | +0.507 |
remember | +0.504 |
iferation | +0.483 |
Neg logit contributions | |
Behavioral | -0.307 |
Pandora | -0.274 |
ディ | -0.259 |
^^ | -0.243 |
Pesh | -0.242 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Behavioral | +0.309 |
Pandora | +0.278 |
ディ | +0.260 |
^^ | +0.252 |
Pesh | +0.251 |
Neg logit contributions | |
orsi | -0.410 |
forging | -0.409 |
ratulations | -0.409 |
remember | -0.403 |
iferation | -0.387 |
Token | to |
Token ID | 284 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
Behavioral | +1.207 |
Pandora | +1.090 |
ディ | +1.030 |
^^ | +0.979 |
Pesh | +0.973 |
Neg logit contributions | |
forging | -1.735 |
orsi | -1.725 |
ratulations | -1.721 |
remember | -1.706 |
iferation | -1.639 |
Token | switch |
Token ID | 5078 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Behavioral | +0.504 |
Pandora | +0.467 |
ディ | +0.431 |
^^ | +0.427 |
Pesh | +0.424 |
Neg logit contributions | |
orsi | -0.504 |
ratulations | -0.500 |
forging | -0.495 |
remember | -0.486 |
iferation | -0.477 |
Token | over |
Token ID | 625 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
forging | +0.117 |
orsi | +0.116 |
ratulations | +0.116 |
remember | +0.115 |
iferation | +0.110 |
Neg logit contributions | |
Behavioral | -0.089 |
Pandora | -0.081 |
ディ | -0.076 |
^^ | -0.073 |
Pesh | -0.073 |
Token | right |
Token ID | 826 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
forging | +0.709 |
orsi | +0.699 |
ratulations | +0.698 |
remember | +0.693 |
iferation | +0.661 |
Neg logit contributions | |
Behavioral | -0.594 |
Pandora | -0.540 |
ディ | -0.519 |
^^ | -0.493 |
Pesh | -0.491 |
Token | now |
Token ID | 783 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
forging | +0.147 |
orsi | +0.146 |
ratulations | +0.146 |
remember | +0.144 |
iferation | +0.138 |
Neg logit contributions | |
Behavioral | -0.130 |
Pandora | -0.120 |
ディ | -0.114 |
^^ | -0.109 |
Pesh | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
Behavioral | +0.179 |
Pandora | +0.164 |
ディ | +0.156 |
^^ | +0.150 |
Pesh | +0.148 |
Neg logit contributions | |
forging | -0.215 |
orsi | -0.214 |
ratulations | -0.213 |
remember | -0.211 |
iferation | -0.202 |
Token | Also |
Token ID | 4418 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Behavioral | +0.261 |
Pandora | +0.236 |
ディ | +0.222 |
^^ | +0.213 |
Pesh | +0.212 |
Neg logit contributions | |
forging | -0.356 |
ratulations | -0.355 |
orsi | -0.353 |
remember | -0.347 |
iferation | -0.336 |
Token | , |
Token ID | 11 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
Behavioral | +1.176 |
Pandora | +1.080 |
ディ | +1.018 |
^^ | +0.973 |
Pesh | +0.971 |
Neg logit contributions | |
forging | -1.506 |
orsi | -1.502 |
ratulations | -1.499 |
remember | -1.473 |
sbm | -1.426 |
Token | while |
Token ID | 981 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
forging | +0.723 |
orsi | +0.716 |
ratulations | +0.714 |
remember | +0.709 |
iferation | +0.677 |
Neg logit contributions | |
Behavioral | -0.582 |
Pandora | -0.529 |
ディ | -0.505 |
^^ | -0.481 |
Pesh | -0.479 |
Token | I |
Token ID | 314 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Behavioral | +0.263 |
Pandora | +0.240 |
ディ | +0.228 |
^^ | +0.218 |
Pesh | +0.217 |
Neg logit contributions | |
forging | -0.306 |
orsi | -0.304 |
ratulations | -0.304 |
remember | -0.300 |
iferation | -0.288 |
Token | 've |
Token ID | 1053 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Behavioral | +0.310 |
Pandora | +0.286 |
ディ | +0.268 |
^^ | +0.261 |
Pesh | +0.258 |
Neg logit contributions | |
orsi | -0.360 |
forging | -0.359 |
ratulations | -0.357 |
remember | -0.349 |
sbm | -0.341 |
Token | mainly |
Token ID | 8384 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
Behavioral | +0.706 |
Pandora | +0.652 |
ディ | +0.606 |
^^ | +0.584 |
Pesh | +0.579 |
Neg logit contributions | |
orsi | -1.000 |
ratulations | -0.991 |
forging | -0.989 |
remember | -0.979 |
iferation | -0.950 |
Token | commented |
Token ID | 16476 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
Behavioral | +0.522 |
Pandora | +0.479 |
ディ | +0.444 |
^^ | +0.429 |
Pesh | +0.425 |
Neg logit contributions | |
orsi | -0.739 |
ratulations | -0.737 |
forging | -0.736 |
remember | -0.724 |
iferation | -0.705 |
Token | on |
Token ID | 319 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
forging | +0.657 |
orsi | +0.648 |
ratulations | +0.646 |
remember | +0.641 |
iferation | +0.610 |
Neg logit contributions | |
Behavioral | -0.627 |
Pandora | -0.575 |
ディ | -0.554 |
^^ | -0.527 |
Pesh | -0.526 |
Token | ability |
Token ID | 2694 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
forging | +0.472 |
ratulations | +0.470 |
orsi | +0.470 |
remember | +0.464 |
iferation | +0.442 |
Neg logit contributions | |
Behavioral | -0.485 |
Pandora | -0.445 |
ディ | -0.426 |
^^ | -0.410 |
Pesh | -0.409 |
Token | . |
Token ID | 13 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
forging | +0.133 |
ratulations | +0.132 |
orsi | +0.132 |
remember | +0.131 |
iferation | +0.125 |
Neg logit contributions | |
Behavioral | -0.101 |
Pandora | -0.091 |
ディ | -0.086 |
^^ | -0.083 |
Pesh | -0.082 |
Token | It |
Token ID | 632 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Behavioral | +0.623 |
Pandora | +0.558 |
ディ | +0.512 |
^^ | +0.502 |
Pesh | +0.498 |
Neg logit contributions | |
ratulations | -0.868 |
forging | -0.865 |
orsi | -0.860 |
remember | -0.837 |
iferation | -0.823 |
Token | 's |
Token ID | 338 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
Behavioral | +0.208 |
Pandora | +0.189 |
ディ | +0.180 |
^^ | +0.172 |
Pesh | +0.171 |
Neg logit contributions | |
forging | -0.260 |
orsi | -0.258 |
ratulations | -0.258 |
remember | -0.255 |
iferation | -0.244 |
Token | so |
Token ID | 523 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Behavioral | +0.021 |
Pandora | +0.019 |
ディ | +0.018 |
^^ | +0.017 |
Pesh | +0.017 |
Neg logit contributions | |
forging | -0.026 |
orsi | -0.026 |
ratulations | -0.025 |
remember | -0.025 |
iferation | -0.024 |
Token | easy |
Token ID | 2562 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
forging | +0.446 |
orsi | +0.441 |
ratulations | +0.439 |
remember | +0.436 |
iferation | +0.416 |
Neg logit contributions | |
Behavioral | -0.389 |
Pandora | -0.355 |
ディ | -0.341 |
^^ | -0.325 |
Pesh | -0.323 |
Token | to |
Token ID | 284 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
forging | +2.790 |
remember | +2.722 |
ratulations | +2.684 |
orsi | +2.682 |
deadlines | +2.579 |
Neg logit contributions | |
Behavioral | -2.234 |
Pandora | -2.016 |
ディ | -1.989 |
Pesh | -1.862 |
^^ | -1.840 |
Token | forget |
Token ID | 6044 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
orsi | +0.075 |
ratulations | +0.075 |
forging | +0.075 |
remember | +0.073 |
iferation | +0.071 |
Neg logit contributions | |
Behavioral | -0.074 |
Pandora | -0.069 |
ディ | -0.063 |
^^ | -0.063 |
Pesh | -0.062 |
Token | what |
Token ID | 644 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
Behavioral | +0.069 |
Pandora | +0.063 |
ディ | +0.059 |
^^ | +0.057 |
Pesh | +0.057 |
Neg logit contributions | |
orsi | -0.088 |
ratulations | -0.088 |
forging | -0.088 |
remember | -0.086 |
iferation | -0.084 |
Token | got |
Token ID | 1392 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Behavioral | +0.581 |
Pandora | +0.529 |
ディ | +0.492 |
^^ | +0.479 |
Pesh | +0.476 |
Neg logit contributions | |
ratulations | -0.726 |
forging | -0.724 |
orsi | -0.723 |
remember | -0.716 |
iferation | -0.693 |
Token | you |
Token ID | 345 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
Behavioral | +0.264 |
Pandora | +0.241 |
ディ | +0.228 |
^^ | +0.219 |
Pesh | +0.218 |
Neg logit contributions | |
forging | -0.323 |
orsi | -0.320 |
ratulations | -0.320 |
remember | -0.317 |
iferation | -0.304 |
Token | had |
Token ID | 550 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Behavioral | +0.297 |
Pandora | +0.269 |
ディ | +0.256 |
^^ | +0.243 |
Pesh | +0.241 |
Neg logit contributions | |
forging | -0.414 |
orsi | -0.410 |
ratulations | -0.409 |
remember | -0.405 |
iferation | -0.389 |
Token | been |
Token ID | 587 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
Behavioral | +0.209 |
Pandora | +0.189 |
ディ | +0.181 |
^^ | +0.172 |
Pesh | +0.171 |
Neg logit contributions | |
forging | -0.270 |
orsi | -0.267 |
ratulations | -0.267 |
remember | -0.265 |
iferation | -0.253 |
Token | hacked |
Token ID | 19957 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
forging | +0.017 |
orsi | +0.017 |
ratulations | +0.017 |
remember | +0.017 |
iferation | +0.016 |
Neg logit contributions | |
Behavioral | -0.016 |
Pandora | -0.015 |
ディ | -0.014 |
^^ | -0.014 |
Pesh | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
forging | +1.150 |
orsi | +1.132 |
ratulations | +1.127 |
remember | +1.127 |
deadlines | +1.063 |
Neg logit contributions | |
Behavioral | -0.972 |
Pandora | -0.880 |
ディ | -0.849 |
Pesh | -0.804 |
^^ | -0.798 |
Token | Not |
Token ID | 1892 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
Behavioral | +0.280 |
Pandora | +0.255 |
ディ | +0.243 |
^^ | +0.232 |
Pesh | +0.230 |
Neg logit contributions | |
forging | -0.355 |
orsi | -0.351 |
ratulations | -0.351 |
remember | -0.347 |
iferation | -0.333 |
Token | long |
Token ID | 890 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
forging | +0.428 |
orsi | +0.423 |
ratulations | +0.422 |
remember | +0.419 |
iferation | +0.399 |
Neg logit contributions | |
Behavioral | -0.375 |
Pandora | -0.343 |
ディ | -0.329 |
^^ | -0.313 |
Pesh | -0.312 |
Token | after |
Token ID | 706 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
forging | +3.215 |
remember | +3.161 |
orsi | +3.157 |
ratulations | +3.111 |
deadlines | +2.993 |
Neg logit contributions | |
Behavioral | -2.241 |
Pandora | -1.994 |
ディ | -1.955 |
Pesh | -1.810 |
Stephenson | -1.784 |
Token | the |
Token ID | 262 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
forging | +1.521 |
orsi | +1.494 |
ratulations | +1.489 |
remember | +1.486 |
iferation | +1.403 |
Neg logit contributions | |
Behavioral | -1.306 |
Pandora | -1.182 |
ディ | -1.146 |
Pesh | -1.079 |
^^ | -1.079 |
Token | claims |
Token ID | 3667 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Behavioral | +0.224 |
Pandora | +0.206 |
ディ | +0.196 |
^^ | +0.188 |
Pesh | +0.188 |
Neg logit contributions | |
forging | -0.237 |
orsi | -0.236 |
ratulations | -0.235 |
remember | -0.233 |
iferation | -0.222 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Behavioral | +0.788 |
Pandora | +0.713 |
ディ | +0.670 |
^^ | +0.640 |
Pesh | +0.632 |
Neg logit contributions | |
forging | -1.202 |
orsi | -1.196 |
ratulations | -1.196 |
remember | -1.180 |
iferation | -1.135 |
Token | North |
Token ID | 2258 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Behavioral | +0.817 |
Pandora | +0.758 |
ディ | +0.724 |
Pesh | +0.696 |
^^ | +0.695 |
Neg logit contributions | |
orsi | -0.760 |
forging | -0.759 |
ratulations | -0.757 |
remember | -0.746 |
iferation | -0.712 |
Token | well |
Token ID | 880 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
forging | +0.224 |
orsi | +0.223 |
ratulations | +0.223 |
remember | +0.220 |
iferation | +0.209 |
Neg logit contributions | |
Behavioral | -0.286 |
Pandora | -0.267 |
ディ | -0.256 |
Pesh | -0.247 |
^^ | -0.247 |
Token | . |
Token ID | 13 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
forging | +1.570 |
orsi | +1.547 |
remember | +1.533 |
ratulations | +1.531 |
deadlines | +1.451 |
Neg logit contributions | |
Behavioral | -1.273 |
Pandora | -1.155 |
ディ | -1.112 |
Pesh | -1.047 |
^^ | -1.045 |
Token |
|
Token ID | 198 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
Behavioral | +0.182 |
Pandora | +0.164 |
ディ | +0.155 |
^^ | +0.149 |
Pesh | +0.148 |
Neg logit contributions | |
forging | -0.254 |
ratulations | -0.254 |
orsi | -0.252 |
remember | -0.248 |
iferation | -0.240 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ratulations | +0.566 |
forging | +0.562 |
orsi | +0.560 |
remember | +0.539 |
merce | +0.538 |
Neg logit contributions | |
Behavioral | -0.336 |
Pandora | -0.301 |
ディ | -0.279 |
^^ | -0.275 |
Bronze | -0.266 |
Token | Key |
Token ID | 9218 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
forging | +0.118 |
ratulations | +0.116 |
orsi | +0.116 |
remember | +0.112 |
iferation | +0.108 |
Neg logit contributions | |
Behavioral | -0.127 |
Pandora | -0.117 |
ディ | -0.114 |
^^ | -0.111 |
Pesh | -0.108 |
Token | d |
Token ID | 67 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
forging | +0.171 |
orsi | +0.169 |
ratulations | +0.168 |
remember | +0.168 |
iferation | +0.159 |
Neg logit contributions | |
Behavioral | -0.162 |
Pandora | -0.149 |
ディ | -0.143 |
^^ | -0.135 |
Pesh | -0.135 |
Token | will |
Token ID | 481 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
forging | +2.317 |
orsi | +2.281 |
remember | +2.254 |
ratulations | +2.253 |
deadlines | +2.146 |
Neg logit contributions | |
Behavioral | -1.879 |
Pandora | -1.720 |
ディ | -1.651 |
^^ | -1.546 |
Pesh | -1.546 |
Token | need |
Token ID | 761 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
forging | +0.477 |
orsi | +0.477 |
ratulations | +0.475 |
remember | +0.466 |
iferation | +0.451 |
Neg logit contributions | |
Behavioral | -0.425 |
Pandora | -0.390 |
ディ | -0.368 |
^^ | -0.358 |
Pesh | -0.355 |
Token | a |
Token ID | 257 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
Behavioral | +0.250 |
Pandora | +0.227 |
ディ | +0.217 |
^^ | +0.205 |
Pesh | +0.204 |
Neg logit contributions | |
forging | -0.334 |
orsi | -0.331 |
ratulations | -0.330 |
remember | -0.328 |
iferation | -0.313 |
Token | wider |
Token ID | 10595 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
forging | +0.033 |
ratulations | +0.033 |
orsi | +0.033 |
remember | +0.032 |
iferation | +0.031 |
Neg logit contributions | |
Behavioral | -0.031 |
Pandora | -0.028 |
ディ | -0.027 |
^^ | -0.026 |
Pesh | -0.026 |
Token | range |
Token ID | 2837 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
forging | +0.668 |
ratulations | +0.663 |
orsi | +0.663 |
remember | +0.656 |
iferation | +0.623 |
Neg logit contributions | |
Behavioral | -0.694 |
Pandora | -0.640 |
ディ | -0.613 |
Pesh | -0.587 |
^^ | -0.587 |
Token | fighting |
Token ID | 4330 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
forging | +0.250 |
orsi | +0.250 |
ratulations | +0.249 |
remember | +0.246 |
iferation | +0.237 |
Neg logit contributions | |
Behavioral | -0.232 |
Pandora | -0.214 |
ディ | -0.204 |
^^ | -0.196 |
Pesh | -0.195 |
Token | it |
Token ID | 340 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Behavioral | +0.281 |
Pandora | +0.257 |
ディ | +0.242 |
^^ | +0.232 |
Pesh | +0.232 |
Neg logit contributions | |
forging | -0.366 |
orsi | -0.365 |
ratulations | -0.365 |
remember | -0.361 |
iferation | -0.348 |
Token | . |
Token ID | 13 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
forging | +0.604 |
ratulations | +0.602 |
orsi | +0.602 |
remember | +0.595 |
iferation | +0.571 |
Neg logit contributions | |
Behavioral | -0.449 |
Pandora | -0.410 |
ディ | -0.387 |
^^ | -0.371 |
Pesh | -0.368 |
Token | But |
Token ID | 887 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
forging | +0.324 |
orsi | +0.320 |
ratulations | +0.319 |
remember | +0.317 |
iferation | +0.303 |
Neg logit contributions | |
Behavioral | -0.249 |
Pandora | -0.226 |
ディ | -0.216 |
^^ | -0.205 |
Pesh | -0.204 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
forging | +0.829 |
orsi | +0.819 |
ratulations | +0.816 |
remember | +0.812 |
iferation | +0.772 |
Neg logit contributions | |
Behavioral | -0.684 |
Pandora | -0.621 |
ディ | -0.598 |
^^ | -0.566 |
Pesh | -0.563 |
Token | one |
Token ID | 530 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
forging | +0.919 |
orsi | +0.909 |
ratulations | +0.908 |
remember | +0.900 |
iferation | +0.855 |
Neg logit contributions | |
Behavioral | -0.932 |
Pandora | -0.858 |
ディ | -0.823 |
^^ | -0.789 |
Pesh | -0.787 |
Token | today |
Token ID | 1909 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
forging | +2.830 |
orsi | +2.771 |
ratulations | +2.760 |
remember | +2.758 |
deadlines | +2.626 |
Neg logit contributions | |
Behavioral | -2.463 |
Pandora | -2.235 |
ディ | -2.205 |
^^ | -2.045 |
Pesh | -2.032 |
Token | was |
Token ID | 373 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
forging | +1.379 |
orsi | +1.362 |
ratulations | +1.357 |
remember | +1.351 |
iferation | +1.286 |
Neg logit contributions | |
Behavioral | -1.052 |
Pandora | -0.951 |
ディ | -0.913 |
^^ | -0.861 |
Pesh | -0.857 |
Token | small |
Token ID | 1402 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
forging | +0.470 |
orsi | +0.467 |
ratulations | +0.466 |
remember | +0.462 |
iferation | +0.441 |
Neg logit contributions | |
Behavioral | -0.411 |
Pandora | -0.377 |
ディ | -0.360 |
^^ | -0.344 |
Pesh | -0.343 |
Token | – |
Token ID | 784 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
forging | +0.723 |
orsi | +0.714 |
ratulations | +0.712 |
remember | +0.707 |
iferation | +0.673 |
Neg logit contributions | |
Behavioral | -0.639 |
Pandora | -0.583 |
ディ | -0.561 |
^^ | -0.533 |
Pesh | -0.531 |
Token | a |
Token ID | 257 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Behavioral | +0.650 |
Pandora | +0.596 |
ディ | +0.562 |
^^ | +0.543 |
Pesh | +0.537 |
Neg logit contributions | |
forging | -0.838 |
orsi | -0.834 |
ratulations | -0.832 |
remember | -0.820 |
iferation | -0.796 |
Token | Cloud |
Token ID | 18839 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
forging | +1.076 |
orsi | +1.063 |
ratulations | +1.060 |
remember | +1.051 |
iferation | +0.995 |
Neg logit contributions | |
Behavioral | -1.186 |
Pandora | -1.094 |
ディ | -1.055 |
^^ | -1.011 |
Pesh | -1.007 |
Token | ) |
Token ID | 8 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
forging | +1.222 |
orsi | +1.204 |
ratulations | +1.200 |
remember | +1.193 |
iferation | +1.132 |
Neg logit contributions | |
Behavioral | -1.313 |
Pandora | -1.209 |
ディ | -1.171 |
Pesh | -1.115 |
^^ | -1.115 |
Token |
|
Token ID | 198 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
forging | +0.823 |
orsi | +0.811 |
ratulations | +0.809 |
remember | +0.807 |
iferation | +0.769 |
Neg logit contributions | |
Behavioral | -0.619 |
Pandora | -0.559 |
ディ | -0.538 |
^^ | -0.507 |
Pesh | -0.505 |
Token |
|
Token ID | 198 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ratulations | +0.608 |
forging | +0.606 |
orsi | +0.601 |
remember | +0.579 |
merce | +0.575 |
Neg logit contributions | |
Behavioral | -0.372 |
Pandora | -0.334 |
ディ | -0.314 |
^^ | -0.305 |
Pesh | -0.295 |
Token | On |
Token ID | 2202 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
forging | +0.221 |
orsi | +0.218 |
ratulations | +0.218 |
remember | +0.211 |
iferation | +0.204 |
Neg logit contributions | |
Behavioral | -0.247 |
Pandora | -0.229 |
ディ | -0.223 |
^^ | -0.215 |
IRD | -0.211 |
Token | Record |
Token ID | 13266 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
Behavioral | +0.027 |
Pandora | +0.024 |
ディ | +0.023 |
^^ | +0.022 |
Pesh | +0.022 |
Neg logit contributions | |
forging | -0.029 |
orsi | -0.029 |
ratulations | -0.029 |
remember | -0.029 |
iferation | -0.028 |
Token | Store |
Token ID | 9363 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
forging | +2.002 |
orsi | +1.957 |
remember | +1.953 |
ratulations | +1.951 |
deadlines | +1.848 |
Neg logit contributions | |
Behavioral | -2.202 |
Pandora | -2.032 |
ディ | -1.968 |
Pesh | -1.886 |
^^ | -1.876 |
Token | Day |
Token ID | 3596 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
forging | +0.837 |
orsi | +0.828 |
ratulations | +0.826 |
remember | +0.821 |
iferation | +0.785 |
Neg logit contributions | |
Behavioral | -0.591 |
Pandora | -0.533 |
ディ | -0.509 |
^^ | -0.480 |
Pesh | -0.478 |
Token | ( |
Token ID | 357 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
Behavioral | +0.430 |
Pandora | +0.392 |
ディ | +0.369 |
^^ | +0.356 |
Pesh | +0.352 |
Neg logit contributions | |
forging | -0.559 |
orsi | -0.557 |
ratulations | -0.554 |
remember | -0.547 |
iferation | -0.528 |
Token | April |
Token ID | 16784 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
forging | +0.549 |
orsi | +0.543 |
ratulations | +0.541 |
remember | +0.525 |
iferation | +0.511 |
Neg logit contributions | |
Behavioral | -0.565 |
Pandora | -0.521 |
ディ | -0.504 |
^^ | -0.486 |
Pesh | -0.477 |
Token | 19 |
Token ID | 678 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Behavioral | +0.874 |
Pandora | +0.792 |
ディ | +0.736 |
^^ | +0.719 |
Pesh | +0.713 |
Neg logit contributions | |
ratulations | -1.164 |
forging | -1.153 |
orsi | -1.147 |
remember | -1.113 |
merce | -1.101 |