Token | ed |
Token ID | 276 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
corrid | +1.789 |
KS | +1.775 |
Nieto | +1.723 |
Moj | +1.694 |
Okin | +1.674 |
Neg logit contributions | |
Ult | -1.543 |
uez | -1.500 |
--- | -1.391 |
Temp | -1.292 |
20439 | -1.284 |
Token | Volunteers |
Token ID | 45646 |
Feature activation | +5.11e-03 |
Pos logit contributions | |
KS | +1.980 |
corrid | +1.953 |
Nieto | +1.898 |
Moj | +1.858 |
Okin | +1.839 |
Neg logit contributions | |
Ult | -2.789 |
uez | -2.705 |
--- | -2.535 |
Temp | -2.427 |
alach | -2.415 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Ult | +0.036 |
uez | +0.035 |
--- | +0.033 |
Temp | +0.031 |
alach | +0.031 |
Neg logit contributions | |
corrid | -0.035 |
KS | -0.035 |
Nieto | -0.034 |
Moj | -0.033 |
Okin | -0.032 |
Token | Read |
Token ID | 4149 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
KS | +1.138 |
corrid | +1.123 |
Nieto | +1.082 |
Moj | +1.048 |
Okin | +1.019 |
Neg logit contributions | |
Ult | -2.340 |
uez | -2.297 |
--- | -2.177 |
Temp | -2.079 |
alach | -2.064 |
Token | the |
Token ID | 262 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Ult | +1.905 |
uez | +1.862 |
--- | +1.763 |
Olymp | +1.621 |
alach | +1.618 |
Neg logit contributions | |
corrid | -2.076 |
KS | -1.994 |
Nieto | -1.960 |
Moj | -1.917 |
Okin | -1.875 |
Token | 2018 |
Token ID | 2864 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Ult | +2.373 |
uez | +2.325 |
--- | +2.218 |
Olymp | +2.049 |
Temp | +2.031 |
Neg logit contributions | |
corrid | -2.342 |
KS | -2.225 |
Nieto | -2.190 |
Moj | -2.134 |
Okin | -2.087 |
Token | R |
Token ID | 371 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
uez | +7.913 |
Ult | +7.895 |
--- | +7.764 |
Olymp | +7.091 |
alach | +6.939 |
Neg logit contributions | |
corrid | -7.588 |
KS | -6.949 |
Nieto | -6.880 |
Moj | -6.727 |
ikan | -6.617 |
Token | upp |
Token ID | 7211 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
corrid | +0.908 |
KS | +0.883 |
Nieto | +0.849 |
Moj | +0.818 |
Okin | +0.794 |
Neg logit contributions | |
Ult | -1.839 |
uez | -1.800 |
--- | -1.718 |
Temp | -1.632 |
alach | -1.622 |
Token | e |
Token ID | 68 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
Ult | +1.024 |
uez | +1.002 |
--- | +0.941 |
Temp | +0.866 |
alach | +0.856 |
Neg logit contributions | |
corrid | -1.138 |
KS | -1.093 |
Nieto | -1.066 |
Moj | -1.042 |
Okin | -1.025 |
Token | Award |
Token ID | 11289 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Ult | +0.686 |
uez | +0.672 |
--- | +0.643 |
Temp | +0.607 |
alach | +0.603 |
Neg logit contributions | |
corrid | -0.370 |
KS | -0.354 |
Nieto | -0.341 |
Moj | -0.330 |
Okin | -0.322 |
Token | announcement |
Token ID | 8009 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Ult | +0.863 |
uez | +0.839 |
--- | +0.786 |
Temp | +0.717 |
alach | +0.709 |
Neg logit contributions | |
corrid | -1.103 |
KS | -1.072 |
Nieto | -1.050 |
Moj | -1.028 |
Okin | -1.013 |
Token | The |
Token ID | 464 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
Ult | +1.430 |
uez | +1.375 |
--- | +1.307 |
Temp | +1.214 |
._ | +1.183 |
Neg logit contributions | |
corrid | -1.620 |
KS | -1.562 |
Nieto | -1.523 |
Moj | -1.484 |
Okin | -1.473 |
Token | Cap |
Token ID | 15610 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
corrid | +0.192 |
KS | +0.186 |
Nieto | +0.182 |
Moj | +0.177 |
Okin | +0.175 |
Neg logit contributions | |
Ult | -0.145 |
uez | -0.139 |
--- | -0.131 |
Temp | -0.120 |
alach | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Ult | +1.286 |
uez | +1.248 |
--- | +1.174 |
Temp | +1.086 |
alach | +1.076 |
Neg logit contributions | |
corrid | -1.381 |
KS | -1.344 |
Nieto | -1.311 |
Moj | -1.281 |
Okin | -1.261 |
Token | com |
Token ID | 785 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Ult | +0.781 |
uez | +0.760 |
--- | +0.716 |
Temp | +0.666 |
alach | +0.660 |
Neg logit contributions | |
corrid | -0.752 |
KS | -0.730 |
Nieto | -0.711 |
Moj | -0.694 |
Okin | -0.682 |
Token | unless |
Token ID | 4556 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
Ult | +2.575 |
uez | +2.504 |
--- | +2.369 |
Temp | +2.152 |
._ | +2.136 |
Neg logit contributions | |
corrid | -3.268 |
KS | -3.154 |
Nieto | -3.088 |
Moj | -3.014 |
Okin | -2.999 |
Token | otherwise |
Token ID | 4306 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Ult | +2.028 |
uez | +1.969 |
--- | +1.835 |
Temp | +1.667 |
alach | +1.654 |
Neg logit contributions | |
corrid | -2.773 |
KS | -2.703 |
Nieto | -2.651 |
Moj | -2.590 |
Okin | -2.558 |
Token | indicated |
Token ID | 8203 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
uez | +4.809 |
--- | +4.717 |
Ult | +4.692 |
diff | +4.098 |
._ | +3.845 |
Neg logit contributions | |
corrid | -9.850 |
Nieto | -8.978 |
KS | -8.947 |
Okin | -8.793 |
Moj | -8.671 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Ult | +2.249 |
uez | +2.181 |
--- | +2.063 |
Temp | +1.889 |
._ | +1.876 |
Neg logit contributions | |
corrid | -2.546 |
KS | -2.470 |
Nieto | -2.413 |
Moj | -2.360 |
Okin | -2.330 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Ult | +1.539 |
uez | +1.491 |
--- | +1.416 |
Temp | +1.310 |
Olymp | +1.301 |
Neg logit contributions | |
corrid | -1.487 |
KS | -1.423 |
Nieto | -1.388 |
Moj | -1.354 |
Okin | -1.336 |
Token | President |
Token ID | 10364 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
corrid | +1.189 |
KS | +1.185 |
Nieto | +1.149 |
Moj | +1.135 |
ico | +1.112 |
Neg logit contributions | |
Ult | -1.119 |
uez | -1.114 |
--- | -1.018 |
alach | -0.968 |
Olymp | -0.960 |
Token | Donald |
Token ID | 3759 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
corrid | +0.966 |
KS | +0.955 |
Nieto | +0.943 |
Moj | +0.914 |
Okin | +0.894 |
Neg logit contributions | |
Ult | -1.054 |
uez | -1.026 |
--- | -0.955 |
Temp | -0.900 |
alach | -0.893 |
Token | name |
Token ID | 3672 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
corrid | +1.078 |
KS | +1.063 |
Nieto | +1.035 |
Moj | +1.012 |
ico | +1.001 |
Neg logit contributions | |
Ult | -0.870 |
uez | -0.848 |
--- | -0.780 |
Olymp | -0.723 |
alach | -0.721 |
Token | "> |
Token ID | 23984 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
corrid | +1.046 |
KS | +1.027 |
Nieto | +1.004 |
Moj | +0.989 |
Okin | +0.966 |
Neg logit contributions | |
Ult | -0.665 |
uez | -0.640 |
--- | -0.574 |
alach | -0.535 |
Temp | -0.530 |
Token | span |
Token ID | 12626 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
Ult | +0.205 |
uez | +0.197 |
--- | +0.177 |
Temp | +0.161 |
alach | +0.158 |
Neg logit contributions | |
corrid | -0.377 |
KS | -0.374 |
Nieto | -0.366 |
Moj | -0.361 |
ico | -0.355 |
Token | > |
Token ID | 29 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
corrid | +0.360 |
KS | +0.356 |
Nieto | +0.349 |
Moj | +0.344 |
Okin | +0.339 |
Neg logit contributions | |
Ult | -0.150 |
uez | -0.143 |
--- | -0.126 |
Temp | -0.111 |
alach | -0.110 |
Token | < |
Token ID | 1279 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Ult | +1.655 |
uez | +1.606 |
--- | +1.508 |
Temp | +1.385 |
alach | +1.367 |
Neg logit contributions | |
corrid | -1.933 |
KS | -1.876 |
Nieto | -1.833 |
Moj | -1.790 |
Okin | -1.771 |
Token | p |
Token ID | 79 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Ult | +2.381 |
uez | +2.289 |
--- | +2.166 |
Temp | +1.926 |
._ | +1.890 |
Neg logit contributions | |
corrid | -3.752 |
KS | -3.637 |
Nieto | -3.563 |
Moj | -3.490 |
Okin | -3.456 |
Token | ng |
Token ID | 23370 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
Ult | +4.206 |
uez | +3.970 |
--- | +3.855 |
._ | +3.346 |
diff | +3.195 |
Neg logit contributions | |
corrid | -9.819 |
KS | -9.621 |
Nieto | -9.558 |
Moj | -9.401 |
Okin | -9.334 |
Token | - |
Token ID | 12 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
Ult | +4.906 |
--- | +4.758 |
uez | +4.727 |
._ | +4.054 |
Temp | +4.041 |
Neg logit contributions | |
corrid | -8.770 |
KS | -7.913 |
Nieto | -7.842 |
Okin | -7.603 |
Moj | -7.583 |
Token | bind |
Token ID | 21653 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
Ult | +5.806 |
uez | +5.528 |
--- | +5.434 |
Temp | +4.896 |
._ | +4.800 |
Neg logit contributions | |
corrid | -6.812 |
KS | -6.417 |
Nieto | -6.378 |
Moj | -6.193 |
Okin | -6.055 |
Token | =" |
Token ID | 2625 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Ult | +1.720 |
uez | +1.554 |
--- | +1.337 |
Temp | +0.946 |
._ | +0.888 |
Neg logit contributions | |
corrid | -8.771 |
KS | -8.607 |
Nieto | -8.515 |
Moj | -8.362 |
Okin | -8.315 |
Token | phone |
Token ID | 4862 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
Ult | +2.202 |
uez | +2.112 |
--- | +1.973 |
Temp | +1.738 |
._ | +1.708 |
Neg logit contributions | |
corrid | -3.951 |
KS | -3.833 |
Nieto | -3.760 |
Moj | -3.692 |
Okin | -3.661 |
Token | Phone |
Token ID | 6132 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
KS | +2.543 |
corrid | +2.535 |
Nieto | +2.471 |
Moj | +2.428 |
ico | +2.404 |
Neg logit contributions | |
Ult | -1.714 |
uez | -1.699 |
--- | -1.526 |
alach | -1.438 |
Olymp | -1.416 |
Token | List |
Token ID | 8053 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
KS | +4.690 |
corrid | +4.659 |
Nieto | +4.495 |
Moj | +4.390 |
ico | +4.264 |
Neg logit contributions | |
Ult | -5.705 |
uez | -5.698 |
--- | -5.187 |
alach | -5.072 |
Olymp | -5.030 |
Token | Ctrl |
Token ID | 40069 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
corrid | +0.687 |
KS | +0.673 |
Nieto | +0.654 |
Moj | +0.640 |
Okin | +0.627 |
Neg logit contributions | |
Ult | -0.661 |
uez | -0.647 |
--- | -0.603 |
alach | -0.560 |
Olymp | -0.558 |
Token | "> |
Token ID | 5320 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Ult | +1.370 |
uez | +1.291 |
--- | +1.169 |
Temp | +0.977 |
._ | +0.949 |
Neg logit contributions | |
corrid | -4.000 |
KS | -3.909 |
Nieto | -3.858 |
Moj | -3.786 |
Okin | -3.754 |
Token | < |
Token ID | 1279 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
Ult | +1.507 |
uez | +1.456 |
--- | +1.364 |
Temp | +1.236 |
alach | +1.215 |
Neg logit contributions | |
corrid | -2.121 |
KS | -2.060 |
Nieto | -2.024 |
Moj | -1.976 |
Okin | -1.955 |
Token | ul |
Token ID | 377 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Ult | +1.999 |
uez | +1.944 |
--- | +1.847 |
Temp | +1.702 |
._ | +1.682 |
Neg logit contributions | |
corrid | -1.981 |
KS | -1.912 |
Nieto | -1.874 |
Moj | -1.820 |
Okin | -1.789 |
Token | > |
Token ID | 29 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
Ult | +5.704 |
uez | +5.429 |
--- | +5.308 |
._ | +4.733 |
diff | +4.726 |
Neg logit contributions | |
corrid | -8.295 |
KS | -8.095 |
Nieto | -8.014 |
Moj | -7.743 |
Okin | -7.730 |
Token | < |
Token ID | 1279 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Ult | +3.344 |
uez | +3.203 |
--- | +3.043 |
Temp | +2.710 |
._ | +2.676 |
Neg logit contributions | |
corrid | -5.110 |
KS | -4.929 |
Nieto | -4.860 |
Moj | -4.721 |
Okin | -4.713 |
Token | li |
Token ID | 4528 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Ult | +1.018 |
uez | +0.995 |
--- | +0.949 |
Temp | +0.889 |
alach | +0.879 |
Neg logit contributions | |
corrid | -0.715 |
KS | -0.688 |
Nieto | -0.668 |
Moj | -0.648 |
Okin | -0.633 |
Token | ng |
Token ID | 23370 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
Ult | +1.181 |
uez | +1.154 |
--- | +1.097 |
Temp | +1.031 |
alach | +1.024 |
Neg logit contributions | |
corrid | -0.811 |
KS | -0.784 |
Nieto | -0.760 |
Moj | -0.738 |
Okin | -0.722 |
Token | - |
Token ID | 12 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
Ult | +4.574 |
--- | +4.434 |
uez | +4.353 |
._ | +3.767 |
Temp | +3.725 |
Neg logit contributions | |
corrid | -8.424 |
KS | -7.449 |
Nieto | -7.395 |
Moj | -7.167 |
Okin | -7.116 |
Token | argument |
Token ID | 49140 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
corrid | +0.275 |
KS | +0.272 |
Nieto | +0.264 |
Moj | +0.259 |
Okin | +0.255 |
Neg logit contributions | |
Ult | -0.289 |
uez | -0.282 |
--- | -0.264 |
Temp | -0.247 |
alach | -0.245 |
Token | (" |
Token ID | 7203 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Ult | +4.043 |
uez | +3.849 |
--- | +3.640 |
._ | +3.271 |
Temp | +3.240 |
Neg logit contributions | |
corrid | -7.411 |
KS | -6.859 |
Nieto | -6.798 |
Okin | -6.549 |
Moj | -6.524 |
Token | - |
Token ID | 12 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Ult | +3.762 |
uez | +3.618 |
--- | +3.536 |
Temp | +3.035 |
._ | +3.011 |
Neg logit contributions | |
corrid | -5.790 |
KS | -5.413 |
Nieto | -5.321 |
Moj | -5.156 |
Okin | -5.137 |
Token | i |
Token ID | 72 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
KS | +1.487 |
corrid | +1.474 |
Nieto | +1.434 |
Moj | +1.405 |
ico | +1.391 |
Neg logit contributions | |
Ult | -1.804 |
uez | -1.763 |
--- | -1.656 |
alach | -1.569 |
Olymp | -1.556 |
Token | ", |
Token ID | 1600 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
Ult | +1.614 |
uez | +1.582 |
--- | +1.516 |
Temp | +1.435 |
alach | +1.421 |
Neg logit contributions | |
corrid | -0.790 |
KS | -0.740 |
Nieto | -0.712 |
Moj | -0.684 |
Okin | -0.668 |
Token | " |
Token ID | 366 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Ult | +4.781 |
uez | +4.669 |
--- | +4.572 |
diff | +4.059 |
._ | +4.034 |
Neg logit contributions | |
corrid | -5.951 |
KS | -5.339 |
Nieto | -5.338 |
Okin | -5.168 |
Moj | -5.095 |
Token | -- |
Token ID | 438 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
Ult | +2.142 |
--- | +2.041 |
uez | +1.922 |
Temp | +1.174 |
._ | +1.085 |
Neg logit contributions | |
corrid | -12.409 |
KS | -11.757 |
Nieto | -11.589 |
Okin | -11.378 |
Moj | -11.353 |
Token | images |
Token ID | 17566 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
corrid | +0.227 |
KS | +0.225 |
Nieto | +0.218 |
Moj | +0.214 |
ico | +0.210 |
Neg logit contributions | |
Ult | -0.208 |
uez | -0.201 |
--- | -0.188 |
Temp | -0.175 |
alach | -0.174 |
Token | ", |
Token ID | 1600 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
KS | +0.647 |
corrid | +0.621 |
Nieto | +0.609 |
Moj | +0.592 |
ico | +0.569 |
Neg logit contributions | |
Ult | -1.650 |
uez | -1.620 |
--- | -1.538 |
alach | -1.487 |
Temp | -1.472 |
Token | required |
Token ID | 2672 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
Ult | +3.690 |
uez | +3.598 |
--- | +3.467 |
Temp | +3.118 |
diff | +3.101 |
Neg logit contributions | |
corrid | -4.304 |
KS | -4.147 |
Nieto | -4.099 |
Moj | -3.960 |
Okin | -3.955 |
Token | = |
Token ID | 28 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
KS | +0.165 |
Nieto | +0.161 |
corrid | +0.161 |
Moj | +0.159 |
ico | +0.157 |
Neg logit contributions | |
Ult | -0.066 |
uez | -0.063 |
--- | -0.054 |
alach | -0.050 |
utenberg | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
Ult | +3.842 |
uez | +3.670 |
--- | +3.634 |
._ | +3.331 |
Temp | +3.194 |
Neg logit contributions | |
corrid | -5.770 |
Nieto | -4.925 |
KS | -4.917 |
Okin | -4.766 |
Moj | -4.708 |
Token | res |
Token ID | 411 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
Ult | +3.253 |
uez | +3.174 |
--- | +3.051 |
Temp | +2.748 |
._ | +2.744 |
Neg logit contributions | |
corrid | -4.477 |
KS | -4.152 |
Nieto | -4.134 |
Okin | -3.980 |
Moj | -3.945 |
Token | ize |
Token ID | 1096 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
KS | +0.419 |
corrid | +0.417 |
Nieto | +0.405 |
Moj | +0.397 |
ico | +0.388 |
Neg logit contributions | |
Ult | -0.481 |
uez | -0.468 |
--- | -0.439 |
alach | -0.412 |
Temp | -0.411 |
Token | ( |
Token ID | 7 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
Ult | +1.351 |
uez | +1.315 |
--- | +1.256 |
Temp | +1.174 |
._ | +1.158 |
Neg logit contributions | |
corrid | -1.040 |
KS | -0.983 |
Nieto | -0.958 |
Moj | -0.929 |
Okin | -0.911 |
Token | image |
Token ID | 9060 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Ult | +3.187 |
uez | +3.130 |
--- | +2.915 |
Temp | +2.628 |
._ | +2.608 |
Neg logit contributions | |
corrid | -4.614 |
KS | -4.315 |
Nieto | -4.274 |
Moj | -4.168 |
Okin | -4.108 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Ult | +1.052 |
uez | +1.024 |
--- | +0.962 |
Temp | +0.891 |
alach | +0.883 |
Neg logit contributions | |
corrid | -1.100 |
KS | -1.070 |
Nieto | -1.044 |
Moj | -1.020 |
Okin | -1.002 |
Token | height |
Token ID | 6001 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Ult | +3.440 |
uez | +3.352 |
--- | +3.194 |
diff | +2.685 |
._ | +2.530 |
Neg logit contributions | |
corrid | -10.848 |
Nieto | -10.130 |
KS | -9.897 |
Okin | -9.795 |
Moj | -9.676 |
Token | = |
Token ID | 28 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
Ult | +1.459 |
uez | +1.368 |
--- | +1.230 |
Temp | +1.013 |
._ | +0.989 |
Neg logit contributions | |
corrid | -4.659 |
KS | -4.455 |
Nieto | -4.408 |
Moj | -4.330 |
Okin | -4.289 |
Token | 600 |
Token ID | 8054 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Ult | +2.898 |
uez | +2.706 |
--- | +2.537 |
Temp | +2.150 |
._ | +2.146 |
Neg logit contributions | |
corrid | -6.525 |
Nieto | -6.180 |
KS | -6.128 |
Moj | -5.983 |
Okin | -5.939 |
Token | ) |
Token ID | 8 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
Ult | +2.354 |
uez | +2.297 |
--- | +2.215 |
Temp | +2.061 |
._ | +2.047 |
Neg logit contributions | |
corrid | -1.735 |
KS | -1.577 |
Nieto | -1.556 |
Moj | -1.497 |
Okin | -1.478 |
Token | gray |
Token ID | 12768 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Ult | +2.341 |
uez | +2.259 |
--- | +2.113 |
diff | +1.736 |
._ | +1.701 |
Neg logit contributions | |
corrid | -7.010 |
KS | -6.851 |
Nieto | -6.770 |
Moj | -6.617 |
Okin | -6.598 |
Token | utils |
Token ID | 26791 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Ult | +1.928 |
uez | +1.868 |
--- | +1.727 |
Temp | +1.556 |
._ | +1.530 |
Neg logit contributions | |
corrid | -3.163 |
KS | -3.028 |
Nieto | -2.977 |
Moj | -2.912 |
Okin | -2.889 |
Token | import |
Token ID | 1330 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Ult | +1.968 |
uez | +1.905 |
--- | +1.760 |
Temp | +1.524 |
._ | +1.522 |
Neg logit contributions | |
corrid | -4.047 |
KS | -3.874 |
Nieto | -3.821 |
Moj | -3.746 |
Okin | -3.715 |
Token | paths |
Token ID | 13532 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Ult | +1.913 |
uez | +1.867 |
--- | +1.774 |
Temp | +1.617 |
Olymp | +1.604 |
Neg logit contributions | |
corrid | -2.077 |
KS | -2.006 |
Nieto | -1.980 |
Moj | -1.916 |
Okin | -1.898 |
Token | import |
Token ID | 1330 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Ult | +1.133 |
uez | +1.093 |
--- | +1.003 |
Temp | +0.889 |
alach | +0.874 |
Neg logit contributions | |
corrid | -2.122 |
KS | -2.066 |
Nieto | -2.029 |
Moj | -1.991 |
Okin | -1.967 |
Token | n |
Token ID | 299 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Ult | +1.876 |
uez | +1.833 |
--- | +1.752 |
Temp | +1.643 |
Olymp | +1.632 |
Neg logit contributions | |
corrid | -1.204 |
KS | -1.158 |
Nieto | -1.120 |
Moj | -1.084 |
Okin | -1.063 |
Token | umpy |
Token ID | 32152 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
Ult | +1.702 |
uez | +1.654 |
--- | +1.541 |
Temp | +1.342 |
._ | +1.336 |
Neg logit contributions | |
corrid | -3.372 |
KS | -3.184 |
Nieto | -3.131 |
Moj | -3.069 |
Okin | -3.033 |
Token | as |
Token ID | 355 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Ult | +5.647 |
uez | +5.538 |
--- | +5.370 |
._ | +4.929 |
diff | +4.758 |
Neg logit contributions | |
corrid | -8.579 |
KS | -7.588 |
Nieto | -7.580 |
Moj | -7.377 |
Okin | -7.362 |
Token | np |
Token ID | 45941 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Ult | +1.976 |
uez | +1.916 |
--- | +1.828 |
Olymp | +1.576 |
._ | +1.572 |
Neg logit contributions | |
corrid | -3.706 |
KS | -3.500 |
Nieto | -3.453 |
Moj | -3.380 |
Okin | -3.337 |
Token | import |
Token ID | 1330 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
Ult | +3.776 |
uez | +3.654 |
--- | +3.538 |
diff | +3.074 |
._ | +2.991 |
Neg logit contributions | |
corrid | -9.748 |
Nieto | -9.086 |
KS | -9.065 |
Moj | -8.842 |
Okin | -8.823 |
Token | arg |
Token ID | 1822 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Ult | +5.360 |
uez | +5.184 |
--- | +5.140 |
diff | +4.647 |
._ | +4.596 |
Neg logit contributions | |
corrid | -5.879 |
Nieto | -5.694 |
KS | -5.609 |
Moj | -5.419 |
Okin | -5.392 |
Token | parse |
Token ID | 29572 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
Ult | +2.866 |
uez | +2.792 |
--- | +2.629 |
Temp | +2.381 |
._ | +2.365 |
Neg logit contributions | |
corrid | -3.837 |
KS | -3.646 |
Nieto | -3.561 |
Moj | -3.476 |
Okin | -3.440 |
Token | and |
Token ID | 290 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
Ult | +3.545 |
uez | +3.499 |
--- | +3.336 |
._ | +3.026 |
Temp | +3.015 |
Neg logit contributions | |
corrid | -4.309 |
KS | -3.897 |
Nieto | -3.851 |
Okin | -3.715 |
Moj | -3.703 |
Token | the |
Token ID | 262 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
uez | +5.025 |
Ult | +4.988 |
--- | +4.775 |
._ | +4.208 |
Temp | +4.208 |
Neg logit contributions | |
corrid | -8.267 |
KS | -7.388 |
Nieto | -7.366 |
Okin | -7.107 |
ikan | -7.044 |
Token | archived |
Token ID | 33962 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
Ult | +2.333 |
uez | +2.235 |
--- | +2.040 |
Temp | +1.789 |
alach | +1.763 |
Neg logit contributions | |
corrid | -5.065 |
KS | -4.956 |
Nieto | -4.883 |
Moj | -4.775 |
Okin | -4.730 |
Token | file |
Token ID | 2393 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
uez | +3.444 |
Ult | +3.430 |
--- | +3.216 |
Temp | +2.723 |
._ | +2.719 |
Neg logit contributions | |
corrid | -8.602 |
KS | -8.073 |
Nieto | -8.071 |
Okin | -7.766 |
Moj | -7.744 |
Token | is |
Token ID | 318 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
Ult | +3.399 |
uez | +3.306 |
--- | +3.145 |
Temp | +2.784 |
._ | +2.777 |
Neg logit contributions | |
corrid | -5.580 |
KS | -5.126 |
Nieto | -5.072 |
Moj | -4.908 |
Okin | -4.885 |
Token | uploaded |
Token ID | 19144 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
Ult | +3.255 |
uez | +3.196 |
--- | +2.977 |
diff | +2.658 |
._ | +2.627 |
Neg logit contributions | |
corrid | -6.181 |
KS | -5.763 |
Nieto | -5.718 |
Okin | -5.575 |
Moj | -5.526 |
Token | to |
Token ID | 284 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Ult | +5.756 |
--- | +5.629 |
uez | +5.570 |
._ | +4.991 |
Temp | +4.898 |
Neg logit contributions | |
corrid | -8.766 |
Nieto | -7.244 |
KS | -7.125 |
Okin | -7.031 |
�� | -6.953 |
Token | it |
Token ID | 340 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Ult | +2.522 |
uez | +2.464 |
--- | +2.314 |
Temp | +2.084 |
._ | +2.065 |
Neg logit contributions | |
corrid | -3.488 |
KS | -3.286 |
Nieto | -3.232 |
Moj | -3.138 |
Okin | -3.125 |
Token | . |
Token ID | 13 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Ult | +1.792 |
uez | +1.738 |
--- | +1.651 |
Temp | +1.508 |
._ | +1.501 |
Neg logit contributions | |
corrid | -2.120 |
KS | -1.991 |
Nieto | -1.956 |
Moj | -1.900 |
Okin | -1.885 |
Token | In |
Token ID | 554 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Ult | +1.896 |
uez | +1.846 |
--- | +1.736 |
Temp | +1.610 |
alach | +1.596 |
Neg logit contributions | |
corrid | -1.926 |
KS | -1.873 |
Nieto | -1.827 |
Moj | -1.782 |
Okin | -1.753 |
Token | the |
Token ID | 262 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Ult | +1.335 |
uez | +1.298 |
--- | +1.214 |
Temp | +1.122 |
alach | +1.115 |
Neg logit contributions | |
corrid | -1.483 |
KS | -1.452 |
Nieto | -1.411 |
Moj | -1.388 |
Okin | -1.358 |
Token | paths |
Token ID | 13532 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Ult | +1.913 |
uez | +1.867 |
--- | +1.774 |
Temp | +1.617 |
Olymp | +1.604 |
Neg logit contributions | |
corrid | -2.077 |
KS | -2.006 |
Nieto | -1.980 |
Moj | -1.916 |
Okin | -1.898 |
Token | import |
Token ID | 1330 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Ult | +1.133 |
uez | +1.093 |
--- | +1.003 |
Temp | +0.889 |
alach | +0.874 |
Neg logit contributions | |
corrid | -2.122 |
KS | -2.066 |
Nieto | -2.029 |
Moj | -1.991 |
Okin | -1.967 |
Token | n |
Token ID | 299 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Ult | +1.876 |
uez | +1.833 |
--- | +1.752 |
Temp | +1.643 |
Olymp | +1.632 |
Neg logit contributions | |
corrid | -1.204 |
KS | -1.158 |
Nieto | -1.120 |
Moj | -1.084 |
Okin | -1.063 |
Token | umpy |
Token ID | 32152 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
Ult | +1.702 |
uez | +1.654 |
--- | +1.541 |
Temp | +1.342 |
._ | +1.336 |
Neg logit contributions | |
corrid | -3.372 |
KS | -3.184 |
Nieto | -3.131 |
Moj | -3.069 |
Okin | -3.033 |
Token | as |
Token ID | 355 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Ult | +5.647 |
uez | +5.538 |
--- | +5.370 |
._ | +4.929 |
diff | +4.758 |
Neg logit contributions | |
corrid | -8.579 |
KS | -7.588 |
Nieto | -7.580 |
Moj | -7.377 |
Okin | -7.362 |
Token | np |
Token ID | 45941 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Ult | +1.976 |
uez | +1.916 |
--- | +1.828 |
Olymp | +1.576 |
._ | +1.572 |
Neg logit contributions | |
corrid | -3.706 |
KS | -3.500 |
Nieto | -3.453 |
Moj | -3.380 |
Okin | -3.337 |
Token | import |
Token ID | 1330 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
Ult | +3.776 |
uez | +3.654 |
--- | +3.538 |
diff | +3.074 |
._ | +2.991 |
Neg logit contributions | |
corrid | -9.748 |
Nieto | -9.086 |
KS | -9.065 |
Moj | -8.842 |
Okin | -8.823 |
Token | arg |
Token ID | 1822 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Ult | +5.360 |
uez | +5.184 |
--- | +5.140 |
diff | +4.647 |
._ | +4.596 |
Neg logit contributions | |
corrid | -5.879 |
Nieto | -5.694 |
KS | -5.609 |
Moj | -5.419 |
Okin | -5.392 |
Token | parse |
Token ID | 29572 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
Ult | +2.866 |
uez | +2.792 |
--- | +2.629 |
Temp | +2.381 |
._ | +2.365 |
Neg logit contributions | |
corrid | -3.837 |
KS | -3.646 |
Nieto | -3.561 |
Moj | -3.476 |
Okin | -3.440 |
Token | import |
Token ID | 1330 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
Ult | +3.001 |
uez | +2.957 |
--- | +2.689 |
._ | +2.354 |
diff | +2.313 |
Neg logit contributions | |
corrid | -6.892 |
KS | -6.471 |
Nieto | -6.400 |
Moj | -6.262 |
Okin | -6.230 |
Token | im |
Token ID | 545 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
Ult | +3.512 |
uez | +3.365 |
--- | +3.200 |
diff | +2.754 |
._ | +2.707 |
Neg logit contributions | |
corrid | -7.778 |
KS | -7.284 |
Nieto | -7.238 |
Moj | -7.029 |
Okin | -6.990 |
Token | Time |
Token ID | 3862 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Ult | +1.839 |
uez | +1.774 |
--- | +1.650 |
Temp | +1.468 |
Olymp | +1.431 |
Neg logit contributions | |
corrid | -3.361 |
KS | -3.266 |
Nieto | -3.209 |
Moj | -3.140 |
Okin | -3.111 |
Token | component |
Token ID | 7515 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
Ult | +0.964 |
uez | +0.935 |
--- | +0.874 |
Temp | +0.784 |
._ | +0.773 |
Neg logit contributions | |
corrid | -1.491 |
KS | -1.445 |
Nieto | -1.418 |
Moj | -1.385 |
Okin | -1.370 |
Token | const |
Token ID | 1500 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
Ult | +0.160 |
uez | +0.156 |
--- | +0.146 |
alach | +0.136 |
Temp | +0.135 |
Neg logit contributions | |
corrid | -0.161 |
KS | -0.159 |
Nieto | -0.154 |
Moj | -0.151 |
Okin | -0.148 |
Token | float |
Token ID | 12178 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
Ult | +2.536 |
uez | +2.446 |
--- | +2.301 |
Temp | +2.074 |
Olymp | +2.026 |
Neg logit contributions | |
corrid | -3.857 |
KS | -3.681 |
Nieto | -3.665 |
Moj | -3.568 |
Okin | -3.537 |
Token | TA |
Token ID | 21664 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Ult | +2.981 |
uez | +2.812 |
--- | +2.756 |
Temp | +2.369 |
Olymp | +2.327 |
Neg logit contributions | |
corrid | -5.828 |
Nieto | -5.473 |
KS | -5.447 |
Moj | -5.341 |
Okin | -5.316 |
Token | U |
Token ID | 52 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
Ult | +2.948 |
uez | +2.830 |
--- | +2.729 |
Temp | +2.500 |
._ | +2.479 |
Neg logit contributions | |
corrid | -3.102 |
KS | -2.759 |
Nieto | -2.729 |
Moj | -2.672 |
Okin | -2.636 |
Token | = |
Token ID | 796 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Ult | +3.917 |
--- | +3.666 |
uez | +3.573 |
._ | +3.058 |
Temp | +3.042 |
Neg logit contributions | |
corrid | -10.533 |
Nieto | -8.963 |
Okin | -8.773 |
KS | -8.685 |
Moj | -8.671 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Ult | +1.391 |
uez | +1.356 |
--- | +1.270 |
Temp | +1.158 |
alach | +1.145 |
Neg logit contributions | |
corrid | -1.740 |
KS | -1.674 |
Nieto | -1.654 |
Moj | -1.607 |
Okin | -1.588 |
Token | . |
Token ID | 13 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
Ult | +1.788 |
uez | +1.731 |
--- | +1.657 |
._ | +1.518 |
Temp | +1.513 |
Neg logit contributions | |
corrid | -2.026 |
KS | -1.861 |
Nieto | -1.841 |
Okin | -1.775 |
Moj | -1.773 |
Token | 283 |
Token ID | 30290 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Ult | +3.447 |
uez | +3.276 |
--- | +3.158 |
._ | +2.722 |
alach | +2.691 |
Neg logit contributions | |
corrid | -5.897 |
KS | -5.808 |
Nieto | -5.638 |
Okin | -5.522 |
Moj | -5.490 |
Token | 185 |
Token ID | 21652 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
corrid | +1.536 |
KS | +1.526 |
Nieto | +1.491 |
Moj | +1.460 |
Okin | +1.435 |
Neg logit contributions | |
Ult | -1.258 |
uez | -1.241 |
--- | -1.130 |
Temp | -1.049 |
alach | -1.042 |
Token | "> |
Token ID | 23984 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
corrid | +1.046 |
KS | +1.027 |
Nieto | +1.004 |
Moj | +0.989 |
Okin | +0.966 |
Neg logit contributions | |
Ult | -0.665 |
uez | -0.640 |
--- | -0.574 |
alach | -0.535 |
Temp | -0.530 |
Token | span |
Token ID | 12626 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
Ult | +0.205 |
uez | +0.197 |
--- | +0.177 |
Temp | +0.161 |
alach | +0.158 |
Neg logit contributions | |
corrid | -0.377 |
KS | -0.374 |
Nieto | -0.366 |
Moj | -0.361 |
ico | -0.355 |
Token | > |
Token ID | 29 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
corrid | +0.360 |
KS | +0.356 |
Nieto | +0.349 |
Moj | +0.344 |
Okin | +0.339 |
Neg logit contributions | |
Ult | -0.150 |
uez | -0.143 |
--- | -0.126 |
Temp | -0.111 |
alach | -0.110 |
Token | < |
Token ID | 1279 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Ult | +1.655 |
uez | +1.606 |
--- | +1.508 |
Temp | +1.385 |
alach | +1.367 |
Neg logit contributions | |
corrid | -1.933 |
KS | -1.876 |
Nieto | -1.833 |
Moj | -1.790 |
Okin | -1.771 |
Token | p |
Token ID | 79 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Ult | +2.381 |
uez | +2.289 |
--- | +2.166 |
Temp | +1.926 |
._ | +1.890 |
Neg logit contributions | |
corrid | -3.752 |
KS | -3.637 |
Nieto | -3.563 |
Moj | -3.490 |
Okin | -3.456 |
Token | ng |
Token ID | 23370 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
Ult | +4.206 |
uez | +3.970 |
--- | +3.855 |
._ | +3.346 |
diff | +3.195 |
Neg logit contributions | |
corrid | -9.819 |
KS | -9.621 |
Nieto | -9.558 |
Moj | -9.401 |
Okin | -9.334 |
Token | - |
Token ID | 12 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
Ult | +4.906 |
--- | +4.758 |
uez | +4.727 |
._ | +4.054 |
Temp | +4.041 |
Neg logit contributions | |
corrid | -8.770 |
KS | -7.913 |
Nieto | -7.842 |
Okin | -7.603 |
Moj | -7.583 |
Token | bind |
Token ID | 21653 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
Ult | +5.806 |
uez | +5.528 |
--- | +5.434 |
Temp | +4.896 |
._ | +4.800 |
Neg logit contributions | |
corrid | -6.812 |
KS | -6.417 |
Nieto | -6.378 |
Moj | -6.193 |
Okin | -6.055 |
Token | =" |
Token ID | 2625 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Ult | +1.720 |
uez | +1.554 |
--- | +1.337 |
Temp | +0.946 |
._ | +0.888 |
Neg logit contributions | |
corrid | -8.771 |
KS | -8.607 |
Nieto | -8.515 |
Moj | -8.362 |
Okin | -8.315 |
Token | phone |
Token ID | 4862 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
Ult | +2.202 |
uez | +2.112 |
--- | +1.973 |
Temp | +1.738 |
._ | +1.708 |
Neg logit contributions | |
corrid | -3.951 |
KS | -3.833 |
Nieto | -3.760 |
Moj | -3.692 |
Okin | -3.661 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
corrid | +0.151 |
KS | +0.148 |
Nieto | +0.143 |
Moj | +0.140 |
Okin | +0.137 |
Neg logit contributions | |
Ult | -0.141 |
uez | -0.138 |
--- | -0.127 |
Temp | -0.119 |
alach | -0.119 |
Token | - |
Token ID | 12 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
Ult | +4.574 |
--- | +4.434 |
uez | +4.353 |
._ | +3.767 |
Temp | +3.725 |
Neg logit contributions | |
corrid | -8.424 |
KS | -7.449 |
Nieto | -7.395 |
Moj | -7.167 |
Okin | -7.116 |
Token | repeat |
Token ID | 44754 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
Ult | +2.439 |
uez | +2.199 |
--- | +2.118 |
._ | +1.535 |
Temp | +1.521 |
Neg logit contributions | |
corrid | -9.901 |
KS | -9.508 |
Nieto | -9.499 |
Moj | -9.305 |
Okin | -9.114 |
Token | =" |
Token ID | 2625 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Ult | +1.615 |
uez | +1.365 |
--- | +1.269 |
._ | +0.801 |
Temp | +0.740 |
Neg logit contributions | |
corrid | -10.301 |
KS | -9.610 |
Nieto | -9.565 |
Okin | -9.390 |
Moj | -9.363 |
Token | phone |
Token ID | 4862 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Ult | +1.336 |
uez | +1.284 |
--- | +1.190 |
Temp | +1.058 |
alach | +1.037 |
Neg logit contributions | |
corrid | -2.387 |
KS | -2.329 |
Nieto | -2.284 |
Moj | -2.244 |
Okin | -2.217 |
Token | in |
Token ID | 287 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
corrid | +2.806 |
KS | +2.755 |
Nieto | +2.643 |
Moj | +2.588 |
Okin | +2.518 |
Neg logit contributions | |
Ult | -2.926 |
uez | -2.878 |
--- | -2.609 |
Olymp | -2.510 |
alach | -2.490 |
Token | phones |
Token ID | 9512 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
corrid | +2.019 |
KS | +1.993 |
Nieto | +1.936 |
Moj | +1.889 |
Okin | +1.843 |
Neg logit contributions | |
Ult | -2.026 |
uez | -1.967 |
--- | -1.829 |
Temp | -1.721 |
alach | -1.709 |
Token | "> |
Token ID | 5320 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Ult | +3.615 |
uez | +3.433 |
--- | +3.365 |
diff | +2.681 |
._ | +2.679 |
Neg logit contributions | |
corrid | -9.286 |
KS | -9.133 |
Nieto | -9.049 |
Okin | -8.880 |
Moj | -8.809 |
Token | < |
Token ID | 1279 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Ult | +2.486 |
uez | +2.364 |
--- | +2.222 |
Temp | +1.977 |
._ | +1.926 |
Neg logit contributions | |
corrid | -4.402 |
KS | -4.276 |
Nieto | -4.205 |
Okin | -4.108 |
Moj | -4.099 |
Token | span |
Token ID | 12626 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Ult | +2.825 |
uez | +2.716 |
--- | +2.587 |
Temp | +2.293 |
._ | +2.249 |
Neg logit contributions | |
corrid | -4.430 |
KS | -4.311 |
Nieto | -4.220 |
Moj | -4.134 |
Okin | -4.096 |
Token | ng |
Token ID | 23370 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
Ult | +1.631 |
uez | +1.570 |
--- | +1.463 |
Temp | +1.309 |
alach | +1.300 |
Neg logit contributions | |
corrid | -2.627 |
KS | -2.564 |
Nieto | -2.517 |
Moj | -2.463 |
Okin | -2.436 |
Token | - |
Token ID | 12 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Ult | +3.762 |
uez | +3.602 |
--- | +3.450 |
Temp | +3.124 |
._ | +3.055 |
Neg logit contributions | |
corrid | -5.441 |
KS | -5.196 |
Nieto | -5.123 |
Moj | -4.981 |
Okin | -4.941 |
Token | . |
Token ID | 13 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
Ult | +0.417 |
uez | +0.404 |
--- | +0.379 |
Temp | +0.351 |
alach | +0.349 |
Neg logit contributions | |
corrid | -0.438 |
KS | -0.429 |
Nieto | -0.417 |
Moj | -0.409 |
Okin | -0.400 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Ult | +0.220 |
uez | +0.215 |
--- | +0.203 |
Temp | +0.191 |
alach | +0.190 |
Neg logit contributions | |
corrid | -0.163 |
KS | -0.160 |
Nieto | -0.154 |
Moj | -0.151 |
Okin | -0.146 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
KS | +0.599 |
Nieto | +0.573 |
corrid | +0.571 |
Moj | +0.563 |
Okin | +0.544 |
Neg logit contributions | |
Ult | -0.880 |
uez | -0.863 |
--- | -0.806 |
alach | -0.777 |
Temp | -0.766 |
Token | is |
Token ID | 271 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
corrid | +0.834 |
KS | +0.827 |
Moj | +0.798 |
Nieto | +0.793 |
ico | +0.780 |
Neg logit contributions | |
Ult | -0.746 |
uez | -0.737 |
--- | -0.676 |
Olymp | -0.640 |
alach | -0.636 |
Token | created |
Token ID | 2727 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Ult | +4.401 |
uez | +4.304 |
--- | +4.101 |
Temp | +3.766 |
diff | +3.739 |
Neg logit contributions | |
corrid | -5.144 |
KS | -4.894 |
Nieto | -4.849 |
Okin | -4.660 |
Moj | -4.639 |
Token | and |
Token ID | 290 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
Ult | +3.545 |
uez | +3.499 |
--- | +3.336 |
._ | +3.026 |
Temp | +3.015 |
Neg logit contributions | |
corrid | -4.309 |
KS | -3.897 |
Nieto | -3.851 |
Okin | -3.715 |
Moj | -3.703 |
Token | the |
Token ID | 262 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
uez | +5.025 |
Ult | +4.988 |
--- | +4.775 |
._ | +4.208 |
Temp | +4.208 |
Neg logit contributions | |
corrid | -8.267 |
KS | -7.388 |
Nieto | -7.366 |
Okin | -7.107 |
ikan | -7.044 |
Token | archived |
Token ID | 33962 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
Ult | +2.333 |
uez | +2.235 |
--- | +2.040 |
Temp | +1.789 |
alach | +1.763 |
Neg logit contributions | |
corrid | -5.065 |
KS | -4.956 |
Nieto | -4.883 |
Moj | -4.775 |
Okin | -4.730 |
Token | file |
Token ID | 2393 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
uez | +3.444 |
Ult | +3.430 |
--- | +3.216 |
Temp | +2.723 |
._ | +2.719 |
Neg logit contributions | |
corrid | -8.602 |
KS | -8.073 |
Nieto | -8.071 |
Okin | -7.766 |
Moj | -7.744 |
Token | is |
Token ID | 318 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
Ult | +3.399 |
uez | +3.306 |
--- | +3.145 |
Temp | +2.784 |
._ | +2.777 |
Neg logit contributions | |
corrid | -5.580 |
KS | -5.126 |
Nieto | -5.072 |
Moj | -4.908 |
Okin | -4.885 |
Token | uploaded |
Token ID | 19144 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
Ult | +3.255 |
uez | +3.196 |
--- | +2.977 |
diff | +2.658 |
._ | +2.627 |
Neg logit contributions | |
corrid | -6.181 |
KS | -5.763 |
Nieto | -5.718 |
Okin | -5.575 |
Moj | -5.526 |
Token | : |
Token ID | 25 |
Feature activation | +5.61e-03 |
Pos logit contributions | |
Ult | +0.426 |
uez | +0.413 |
--- | +0.387 |
Temp | +0.356 |
alach | +0.352 |
Neg logit contributions | |
corrid | -0.506 |
KS | -0.492 |
Nieto | -0.481 |
Moj | -0.470 |
Okin | -0.463 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Ult | +0.045 |
uez | +0.044 |
--- | +0.042 |
Temp | +0.040 |
alach | +0.039 |
Neg logit contributions | |
corrid | -0.033 |
KS | -0.033 |
Nieto | -0.031 |
Moj | -0.031 |
Okin | -0.030 |
Token | ) |
Token ID | 8 |
Feature activation | -1.15e-04 |
Pos logit contributions | |
KS | +1.319 |
corrid | +1.309 |
Nieto | +1.233 |
Moj | +1.220 |
ico | +1.178 |
Neg logit contributions | |
Ult | -2.321 |
uez | -2.270 |
--- | -2.156 |
20439 | -2.053 |
alach | -2.047 |
Token | I |
Token ID | 40 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
corrid | +0.001 |
KS | +0.001 |
Nieto | +0.001 |
Moj | +0.001 |
Okin | +0.001 |
Neg logit contributions | |
Ult | -0.001 |
uez | -0.001 |
--- | -0.001 |
Temp | -0.001 |
alach | -0.001 |
Token | hor |
Token ID | 17899 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
Ult | +1.576 |
uez | +1.519 |
--- | +1.398 |
Temp | +1.256 |
alach | +1.245 |
Neg logit contributions | |
corrid | -2.669 |
KS | -2.612 |
Nieto | -2.560 |
Moj | -2.512 |
Okin | -2.478 |
Token | Mal |
Token ID | 4434 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
Ult | +2.513 |
uez | +2.464 |
--- | +2.348 |
Temp | +2.210 |
Olymp | +2.201 |
Neg logit contributions | |
corrid | -1.543 |
KS | -1.463 |
Nieto | -1.414 |
Moj | -1.360 |
Okin | -1.345 |
Token | anch |
Token ID | 3702 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
Ult | +4.916 |
uez | +4.789 |
--- | +4.523 |
alach | +4.076 |
utenberg | +3.943 |
Neg logit contributions | |
corrid | -8.522 |
Nieto | -7.575 |
KS | -7.501 |
Okin | -7.299 |
Moj | -7.223 |
Token | ak |
Token ID | 461 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
corrid | +0.168 |
KS | +0.167 |
Nieto | +0.161 |
Moj | +0.157 |
Okin | +0.154 |
Neg logit contributions | |
Ult | -0.231 |
uez | -0.226 |
--- | -0.214 |
Temp | -0.201 |
alach | -0.200 |
Token | is |
Token ID | 318 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
Ult | +0.516 |
uez | +0.499 |
--- | +0.466 |
Temp | +0.433 |
alach | +0.428 |
Neg logit contributions | |
corrid | -0.584 |
KS | -0.573 |
Nieto | -0.560 |
Moj | -0.548 |
Okin | -0.537 |
Token | the |
Token ID | 262 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Ult | +1.669 |
uez | +1.633 |
--- | +1.539 |
Temp | +1.426 |
alach | +1.416 |
Neg logit contributions | |
corrid | -1.627 |
KS | -1.567 |
Nieto | -1.533 |
Moj | -1.487 |
Okin | -1.471 |
Token | CEO |
Token ID | 6123 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Ult | +2.648 |
uez | +2.608 |
--- | +2.468 |
Olymp | +2.308 |
Temp | +2.268 |
Neg logit contributions | |
corrid | -2.505 |
KS | -2.368 |
Nieto | -2.326 |
Moj | -2.226 |
Okin | -2.225 |
Token | on |
Token ID | 319 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Ult | +1.651 |
uez | +1.602 |
--- | +1.508 |
Temp | +1.366 |
Olymp | +1.356 |
Neg logit contributions | |
corrid | -2.170 |
KS | -2.107 |
Nieto | -2.065 |
Moj | -2.024 |
Okin | -1.989 |
Token | as |
Token ID | 355 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
corrid | +0.949 |
KS | +0.935 |
Nieto | +0.909 |
Moj | +0.890 |
Okin | +0.875 |
Neg logit contributions | |
Ult | -0.888 |
uez | -0.859 |
--- | -0.792 |
Temp | -0.747 |
20439 | -0.741 |
Token | before |
Token ID | 878 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
Ult | +0.957 |
uez | +0.929 |
--- | +0.871 |
Temp | +0.793 |
Olymp | +0.788 |
Neg logit contributions | |
corrid | -1.277 |
KS | -1.240 |
Nieto | -1.216 |
Moj | -1.188 |
Okin | -1.169 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
corrid | +0.231 |
KS | +0.227 |
Nieto | +0.221 |
Moj | +0.216 |
Okin | +0.212 |
Neg logit contributions | |
Ult | -0.227 |
uez | -0.220 |
--- | -0.204 |
Temp | -0.192 |
alach | -0.191 |
Token | William |
Token ID | 3977 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
Ult | +0.992 |
uez | +0.965 |
--- | +0.919 |
Temp | +0.852 |
Olymp | +0.851 |
Neg logit contributions | |
corrid | -0.909 |
KS | -0.860 |
Nieto | -0.841 |
Moj | -0.817 |
Okin | -0.802 |
Token | the |
Token ID | 262 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
Ult | +0.426 |
uez | +0.414 |
--- | +0.387 |
Temp | +0.361 |
alach | +0.358 |
Neg logit contributions | |
corrid | -0.424 |
KS | -0.415 |
Nieto | -0.404 |
Moj | -0.396 |
Okin | -0.388 |
Token | Conquer |
Token ID | 40963 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Ult | +6.416 |
uez | +6.246 |
--- | +5.963 |
Olymp | +5.633 |
Temp | +5.455 |
Neg logit contributions | |
corrid | -6.390 |
KS | -6.023 |
Nieto | -5.859 |
Moj | -5.744 |
ikan | -5.683 |
Token | or |
Token ID | 273 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
Ult | +2.286 |
uez | +2.220 |
--- | +2.104 |
Temp | +1.892 |
._ | +1.884 |
Neg logit contributions | |
corrid | -2.824 |
KS | -2.680 |
Nieto | -2.611 |
Moj | -2.559 |
Okin | -2.532 |
Token | was |
Token ID | 373 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
corrid | +0.114 |
KS | +0.112 |
Nieto | +0.109 |
Moj | +0.106 |
Okin | +0.105 |
Neg logit contributions | |
Ult | -0.111 |
uez | -0.108 |
--- | -0.101 |
Temp | -0.094 |
alach | -0.093 |
Token | certainly |
Token ID | 3729 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
corrid | +0.479 |
KS | +0.473 |
Nieto | +0.459 |
Moj | +0.450 |
Okin | +0.443 |
Neg logit contributions | |
Ult | -0.451 |
uez | -0.439 |
--- | -0.408 |
Temp | -0.380 |
20439 | -0.377 |
Token | busy |
Token ID | 8179 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Ult | +1.467 |
uez | +1.426 |
--- | +1.336 |
Temp | +1.236 |
alach | +1.226 |
Neg logit contributions | |
corrid | -1.596 |
KS | -1.557 |
Nieto | -1.518 |
Moj | -1.485 |
Okin | -1.461 |
Token | _ |
Token ID | 62 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
Ult | +1.208 |
uez | +1.172 |
--- | +1.101 |
Temp | +1.014 |
alach | +0.999 |
Neg logit contributions | |
corrid | -1.396 |
KS | -1.347 |
Nieto | -1.318 |
Moj | -1.288 |
Okin | -1.269 |
Token | t |
Token ID | 83 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Ult | +0.270 |
uez | +0.263 |
--- | +0.242 |
alach | +0.224 |
Temp | +0.223 |
Neg logit contributions | |
corrid | -0.347 |
KS | -0.346 |
Nieto | -0.336 |
Moj | -0.331 |
Okin | -0.325 |
Token | count |
Token ID | 954 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
corrid | +1.749 |
KS | +1.721 |
Nieto | +1.671 |
Moj | +1.637 |
Okin | +1.612 |
Neg logit contributions | |
Ult | -1.258 |
uez | -1.224 |
--- | -1.109 |
Temp | -1.025 |
alach | -1.021 |
Token | | |
Token ID | 930 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
KS | +0.309 |
corrid | +0.303 |
Nieto | +0.297 |
Moj | +0.293 |
Okin | +0.286 |
Neg logit contributions | |
Ult | -0.312 |
uez | -0.304 |
--- | -0.280 |
alach | -0.267 |
Temp | -0.263 |
Token | < |
Token ID | 1279 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
Ult | +2.467 |
uez | +2.390 |
--- | +2.253 |
Temp | +2.053 |
alach | +2.030 |
Neg logit contributions | |
corrid | -3.053 |
KS | -2.966 |
Nieto | -2.908 |
Moj | -2.839 |
Okin | -2.802 |
Token | -- |
Token ID | 438 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
Ult | +1.561 |
uez | +1.410 |
--- | +1.335 |
Temp | +0.926 |
alach | +0.867 |
Neg logit contributions | |
corrid | -7.185 |
KS | -7.056 |
Nieto | -6.955 |
Moj | -6.864 |
Okin | -6.799 |
Token | read |
Token ID | 1100 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
Ult | +6.079 |
uez | +5.800 |
--- | +5.789 |
diff | +5.280 |
Temp | +5.196 |
Neg logit contributions | |
corrid | -6.480 |
Nieto | -5.949 |
KS | -5.903 |
Moj | -5.769 |
Okin | -5.691 |
Token | () |
Token ID | 3419 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
Ult | +2.170 |
uez | +2.109 |
--- | +1.989 |
Temp | +1.822 |
._ | +1.798 |
Neg logit contributions | |
corrid | -2.579 |
KS | -2.486 |
Nieto | -2.441 |
Moj | -2.396 |
Okin | -2.352 |
Token | ' |
Token ID | 6 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Ult | +0.515 |
uez | +0.500 |
--- | +0.469 |
Temp | +0.435 |
alach | +0.431 |
Neg logit contributions | |
corrid | -0.550 |
KS | -0.536 |
Nieto | -0.523 |
Moj | -0.511 |
Okin | -0.502 |
Token | s |
Token ID | 82 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
KS | +0.995 |
corrid | +0.961 |
Nieto | +0.956 |
Moj | +0.933 |
Okin | +0.916 |
Neg logit contributions | |
Ult | -1.063 |
uez | -1.027 |
--- | -0.954 |
alach | -0.910 |
Temp | -0.900 |
Token | frame |
Token ID | 5739 |
Feature activation | -7.24e-03 |
Pos logit contributions | |
Ult | +0.890 |
uez | +0.862 |
--- | +0.805 |
Temp | +0.733 |
alach | +0.725 |
Neg logit contributions | |
corrid | -1.208 |
KS | -1.176 |
Nieto | -1.153 |
Moj | -1.129 |
Okin | -1.112 |
Token | :: |
Token ID | 3712 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Ult | +3.475 |
uez | +3.290 |
--- | +3.227 |
Temp | +2.921 |
._ | +2.900 |
Neg logit contributions | |
corrid | -5.396 |
KS | -4.780 |
Nieto | -4.753 |
Moj | -4.623 |
Okin | -4.594 |
Token | B |
Token ID | 33 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Ult | +2.191 |
uez | +2.092 |
--- | +2.001 |
Temp | +1.863 |
._ | +1.810 |
Neg logit contributions | |
corrid | -2.255 |
KS | -2.153 |
Nieto | -2.096 |
Moj | -2.036 |
Okin | -2.015 |
Token | old |
Token ID | 727 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
KS | +1.746 |
corrid | +1.739 |
Nieto | +1.702 |
Moj | +1.669 |
ico | +1.636 |
Neg logit contributions | |
Ult | -1.679 |
uez | -1.631 |
--- | -1.523 |
Olymp | -1.413 |
Temp | -1.412 |
Token | ) |
Token ID | 8 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
corrid | +0.093 |
KS | +0.090 |
Nieto | +0.087 |
Moj | +0.085 |
Okin | +0.083 |
Neg logit contributions | |
Ult | -0.144 |
uez | -0.141 |
--- | -0.134 |
Temp | -0.126 |
alach | -0.125 |
Token | $ |
Token ID | 720 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Ult | +3.204 |
uez | +3.130 |
--- | +3.029 |
Temp | +2.827 |
diff | +2.798 |
Neg logit contributions | |
corrid | -2.615 |
Nieto | -2.437 |
KS | -2.430 |
Okin | -2.351 |
Moj | -2.330 |
Token | Br |
Token ID | 9414 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
Ult | +1.700 |
uez | +1.646 |
--- | +1.551 |
Temp | +1.444 |
alach | +1.414 |
Neg logit contributions | |
corrid | -1.873 |
KS | -1.808 |
Nieto | -1.767 |
Moj | -1.724 |
Okin | -1.709 |
Token | ush |
Token ID | 1530 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
Ult | +3.928 |
uez | +3.927 |
--- | +3.589 |
._ | +3.130 |
Temp | +3.109 |
Neg logit contributions | |
corrid | -9.573 |
KS | -8.422 |
Nieto | -8.336 |
Okin | -8.243 |
Moj | -8.215 |
Token | 2 |
Token ID | 17 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Ult | +0.624 |
uez | +0.608 |
--- | +0.577 |
Temp | +0.542 |
alach | +0.536 |
Neg logit contributions | |
corrid | -0.482 |
KS | -0.466 |
Nieto | -0.452 |
Moj | -0.441 |
Okin | -0.432 |
Token | = |
Token ID | 796 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
Ult | +3.107 |
uez | +2.880 |
--- | +2.791 |
Temp | +2.489 |
._ | +2.467 |
Neg logit contributions | |
corrid | -6.856 |
KS | -5.993 |
Nieto | -5.992 |
Okin | -5.849 |
Moj | -5.832 |
Token | New |
Token ID | 968 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
corrid | +0.344 |
KS | +0.329 |
Nieto | +0.321 |
Moj | +0.312 |
Okin | +0.307 |
Neg logit contributions | |
Ult | -0.367 |
uez | -0.358 |
--- | -0.339 |
Temp | -0.315 |
Olymp | -0.311 |
Token | - |
Token ID | 12 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Ult | +1.899 |
uez | +1.828 |
--- | +1.748 |
Temp | +1.562 |
._ | +1.543 |
Neg logit contributions | |
corrid | -2.761 |
KS | -2.575 |
Nieto | -2.532 |
Moj | -2.466 |
Okin | -2.448 |
Token | box |
Token ID | 3091 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
KS | +2.094 |
corrid | +2.065 |
Nieto | +2.025 |
Moj | +2.000 |
Okin | +1.961 |
Neg logit contributions | |
Ult | -1.613 |
uez | -1.517 |
--- | -1.386 |
alach | -1.320 |
Temp | -1.316 |
Token | underneath |
Token ID | 14638 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
Ult | +0.407 |
uez | +0.395 |
--- | +0.369 |
Temp | +0.341 |
alach | +0.338 |
Neg logit contributions | |
corrid | -0.482 |
KS | -0.470 |
Nieto | -0.459 |
Moj | -0.449 |
Okin | -0.442 |
Token | roughly |
Token ID | 7323 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Ult | +0.505 |
uez | +0.490 |
--- | +0.461 |
Temp | +0.421 |
alach | +0.419 |
Neg logit contributions | |
corrid | -0.608 |
KS | -0.592 |
Nieto | -0.578 |
Moj | -0.565 |
Okin | -0.558 |
Token | ( |
Token ID | 357 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
Ult | +2.706 |
uez | +2.639 |
--- | +2.531 |
Temp | +2.355 |
Olymp | +2.336 |
Neg logit contributions | |
corrid | -1.969 |
KS | -1.865 |
Nieto | -1.821 |
Moj | -1.764 |
Okin | -1.729 |
Token | 6 |
Token ID | 21 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
Ult | +0.440 |
uez | +0.426 |
--- | +0.392 |
Temp | +0.355 |
alach | +0.353 |
Neg logit contributions | |
corrid | -0.693 |
KS | -0.680 |
Nieto | -0.663 |
Moj | -0.652 |
Okin | -0.644 |
Token | ) |
Token ID | 8 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
Ult | +0.524 |
uez | +0.513 |
--- | +0.487 |
Temp | +0.459 |
alach | +0.456 |
Neg logit contributions | |
corrid | -0.339 |
KS | -0.328 |
Nieto | -0.316 |
Moj | -0.307 |
Okin | -0.300 |
Token | C |
Token ID | 327 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
Ult | +5.591 |
uez | +5.376 |
--- | +5.204 |
Temp | +4.701 |
Olymp | +4.677 |
Neg logit contributions | |
corrid | -6.915 |
KS | -6.543 |
Nieto | -6.451 |
Moj | -6.266 |
ico | -6.217 |
Token | – |
Token ID | 1906 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
Ult | +2.074 |
uez | +2.012 |
--- | +1.909 |
Temp | +1.764 |
alach | +1.748 |
Neg logit contributions | |
corrid | -2.005 |
KS | -1.947 |
Nieto | -1.915 |
Moj | -1.859 |
Okin | -1.828 |
Token | S |
Token ID | 50 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Ult | +2.518 |
uez | +2.429 |
--- | +2.310 |
Temp | +2.142 |
._ | +2.102 |
Neg logit contributions | |
corrid | -2.441 |
KS | -2.346 |
Nieto | -2.295 |
Moj | -2.241 |
Okin | -2.206 |
Token | –– |
Token ID | 25608 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Ult | +2.696 |
uez | +2.603 |
--- | +2.448 |
Temp | +2.211 |
alach | +2.207 |
Neg logit contributions | |
corrid | -3.423 |
KS | -3.319 |
Nieto | -3.262 |
Moj | -3.180 |
Okin | -3.144 |
Token | – |
Token ID | 1906 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Ult | +1.814 |
uez | +1.742 |
--- | +1.623 |
Temp | +1.463 |
alach | +1.440 |
Neg logit contributions | |
corrid | -2.842 |
KS | -2.767 |
Nieto | -2.712 |
Moj | -2.659 |
Okin | -2.624 |
Token | span |
Token ID | 12626 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
Ult | +0.205 |
uez | +0.197 |
--- | +0.177 |
Temp | +0.161 |
alach | +0.158 |
Neg logit contributions | |
corrid | -0.377 |
KS | -0.374 |
Nieto | -0.366 |
Moj | -0.361 |
ico | -0.355 |
Token | > |
Token ID | 29 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
corrid | +0.360 |
KS | +0.356 |
Nieto | +0.349 |
Moj | +0.344 |
Okin | +0.339 |
Neg logit contributions | |
Ult | -0.150 |
uez | -0.143 |
--- | -0.126 |
Temp | -0.111 |
alach | -0.110 |
Token | < |
Token ID | 1279 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Ult | +1.655 |
uez | +1.606 |
--- | +1.508 |
Temp | +1.385 |
alach | +1.367 |
Neg logit contributions | |
corrid | -1.933 |
KS | -1.876 |
Nieto | -1.833 |
Moj | -1.790 |
Okin | -1.771 |
Token | p |
Token ID | 79 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Ult | +2.381 |
uez | +2.289 |
--- | +2.166 |
Temp | +1.926 |
._ | +1.890 |
Neg logit contributions | |
corrid | -3.752 |
KS | -3.637 |
Nieto | -3.563 |
Moj | -3.490 |
Okin | -3.456 |
Token | ng |
Token ID | 23370 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
Ult | +4.206 |
uez | +3.970 |
--- | +3.855 |
._ | +3.346 |
diff | +3.195 |
Neg logit contributions | |
corrid | -9.819 |
KS | -9.621 |
Nieto | -9.558 |
Moj | -9.401 |
Okin | -9.334 |
Token | - |
Token ID | 12 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
Ult | +4.906 |
--- | +4.758 |
uez | +4.727 |
._ | +4.054 |
Temp | +4.041 |
Neg logit contributions | |
corrid | -8.770 |
KS | -7.913 |
Nieto | -7.842 |
Okin | -7.603 |
Moj | -7.583 |
Token | bind |
Token ID | 21653 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
Ult | +5.806 |
uez | +5.528 |
--- | +5.434 |
Temp | +4.896 |
._ | +4.800 |
Neg logit contributions | |
corrid | -6.812 |
KS | -6.417 |
Nieto | -6.378 |
Moj | -6.193 |
Okin | -6.055 |
Token | =" |
Token ID | 2625 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Ult | +1.720 |
uez | +1.554 |
--- | +1.337 |
Temp | +0.946 |
._ | +0.888 |
Neg logit contributions | |
corrid | -8.771 |
KS | -8.607 |
Nieto | -8.515 |
Moj | -8.362 |
Okin | -8.315 |
Token | phone |
Token ID | 4862 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
Ult | +2.202 |
uez | +2.112 |
--- | +1.973 |
Temp | +1.738 |
._ | +1.708 |
Neg logit contributions | |
corrid | -3.951 |
KS | -3.833 |
Nieto | -3.760 |
Moj | -3.692 |
Okin | -3.661 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
corrid | +0.151 |
KS | +0.148 |
Nieto | +0.143 |
Moj | +0.140 |
Okin | +0.137 |
Neg logit contributions | |
Ult | -0.141 |
uez | -0.138 |
--- | -0.127 |
Temp | -0.119 |
alach | -0.119 |
Token | sn |
Token ID | 16184 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
corrid | +2.009 |
KS | +1.988 |
Nieto | +1.942 |
ico | +1.879 |
Moj | +1.870 |
Neg logit contributions | |
Ult | -2.230 |
uez | -2.171 |
--- | -2.014 |
Olymp | -1.909 |
Temp | -1.903 |
Token | ( |
Token ID | 7 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Ult | +1.349 |
uez | +1.314 |
--- | +1.254 |
Temp | +1.173 |
._ | +1.158 |
Neg logit contributions | |
corrid | -1.047 |
KS | -0.985 |
Nieto | -0.963 |
Moj | -0.932 |
Okin | -0.915 |
Token | image |
Token ID | 9060 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Ult | +2.593 |
uez | +2.542 |
--- | +2.365 |
Temp | +2.149 |
._ | +2.123 |
Neg logit contributions | |
corrid | -3.588 |
KS | -3.395 |
Nieto | -3.353 |
Moj | -3.273 |
Okin | -3.220 |
Token | Path |
Token ID | 15235 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
corrid | +0.898 |
KS | +0.886 |
Nieto | +0.854 |
Moj | +0.833 |
Okin | +0.811 |
Neg logit contributions | |
Ult | -1.351 |
uez | -1.324 |
--- | -1.250 |
alach | -1.181 |
Temp | -1.173 |
Token | ) |
Token ID | 8 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Ult | +2.643 |
uez | +2.582 |
--- | +2.484 |
Temp | +2.323 |
._ | +2.305 |
Neg logit contributions | |
corrid | -2.000 |
KS | -1.803 |
Nieto | -1.782 |
Moj | -1.708 |
Okin | -1.680 |
Token | image |
Token ID | 2939 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Ult | +2.085 |
uez | +2.029 |
--- | +1.893 |
Temp | +1.708 |
Olymp | +1.687 |
Neg logit contributions | |
corrid | -3.103 |
KS | -2.985 |
Nieto | -2.941 |
Moj | -2.872 |
Okin | -2.837 |
Token | = |
Token ID | 796 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Ult | +1.153 |
uez | +1.105 |
--- | +1.030 |
Temp | +0.929 |
._ | +0.907 |
Neg logit contributions | |
corrid | -1.967 |
KS | -1.880 |
Nieto | -1.850 |
Moj | -1.813 |
Okin | -1.794 |
Token | im |
Token ID | 545 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
Ult | +3.367 |
uez | +3.217 |
--- | +3.062 |
diff | +2.640 |
._ | +2.577 |
Neg logit contributions | |
corrid | -9.332 |
KS | -8.621 |
Nieto | -8.582 |
Moj | -8.327 |
Okin | -8.283 |
Token | utils |
Token ID | 26791 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
Ult | +3.139 |
uez | +3.019 |
--- | +2.800 |
Temp | +2.508 |
._ | +2.491 |
Neg logit contributions | |
corrid | -5.692 |
KS | -5.320 |
Nieto | -5.239 |
Moj | -5.110 |
Okin | -5.104 |
Token | . |
Token ID | 13 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
Ult | +3.842 |
uez | +3.670 |
--- | +3.634 |
._ | +3.331 |
Temp | +3.194 |
Neg logit contributions | |
corrid | -5.770 |
Nieto | -4.925 |
KS | -4.917 |
Okin | -4.766 |
Moj | -4.708 |
Token | res |
Token ID | 411 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
Ult | +3.253 |
uez | +3.174 |
--- | +3.051 |
Temp | +2.748 |
._ | +2.744 |
Neg logit contributions | |
corrid | -4.477 |
KS | -4.152 |
Nieto | -4.134 |
Okin | -3.980 |
Moj | -3.945 |
Token | ize |
Token ID | 1096 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
KS | +0.419 |
corrid | +0.417 |
Nieto | +0.405 |
Moj | +0.397 |
ico | +0.388 |
Neg logit contributions | |
Ult | -0.481 |
uez | -0.468 |
--- | -0.439 |
alach | -0.412 |
Temp | -0.411 |
Token | . |
Token ID | 13 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Ult | +1.281 |
uez | +1.245 |
--- | +1.173 |
Temp | +1.080 |
._ | +1.065 |
Neg logit contributions | |
corrid | -1.435 |
KS | -1.377 |
Nieto | -1.348 |
Moj | -1.314 |
Okin | -1.296 |
Token | windows |
Token ID | 28457 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
Ult | +2.943 |
uez | +2.814 |
--- | +2.629 |
alach | +2.263 |
Temp | +2.257 |
Neg logit contributions | |
corrid | -5.975 |
KS | -5.800 |
Nieto | -5.762 |
Moj | -5.567 |
Okin | -5.540 |
Token | . |
Token ID | 13 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
Ult | +0.626 |
uez | +0.609 |
--- | +0.569 |
Temp | +0.528 |
alach | +0.527 |
Neg logit contributions | |
corrid | -0.653 |
KS | -0.646 |
Nieto | -0.628 |
Moj | -0.616 |
Okin | -0.603 |
Token | forms |
Token ID | 23914 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
corrid | +0.464 |
KS | +0.459 |
Nieto | +0.443 |
Moj | +0.440 |
ico | +0.436 |
Neg logit contributions | |
Ult | -0.363 |
uez | -0.353 |
--- | -0.325 |
Temp | -0.301 |
Olymp | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
KS | +0.755 |
Nieto | +0.725 |
corrid | +0.721 |
Moj | +0.719 |
ico | +0.699 |
Neg logit contributions | |
Ult | -0.789 |
uez | -0.769 |
--- | -0.710 |
alach | -0.680 |
Temp | -0.670 |
Token | text |
Token ID | 5239 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Ult | +0.732 |
uez | +0.714 |
--- | +0.672 |
Temp | +0.628 |
alach | +0.625 |
Neg logit contributions | |
corrid | -0.645 |
KS | -0.630 |
Nieto | -0.610 |
Moj | -0.597 |
Okin | -0.584 |
Token | rend |
Token ID | 10920 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ico | +5.541 |
KS | +5.536 |
Nieto | +5.342 |
Moj | +5.263 |
ikan | +5.212 |
Neg logit contributions | |
Ult | -9.535 |
uez | -8.885 |
Olymp | -8.409 |
--- | -8.343 |
Temp | -8.236 |
Token | erer |
Token ID | 11882 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
KS | +0.913 |
corrid | +0.912 |
Nieto | +0.896 |
Moj | +0.882 |
ico | +0.868 |
Neg logit contributions | |
Ult | -0.478 |
uez | -0.449 |
--- | -0.410 |
Temp | -0.371 |
alach | -0.368 |
Token | ] |
Token ID | 60 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Ult | +0.285 |
uez | +0.277 |
--- | +0.255 |
alach | +0.237 |
Temp | +0.236 |
Neg logit contributions | |
corrid | -0.337 |
KS | -0.337 |
Nieto | -0.327 |
Moj | -0.321 |
Okin | -0.316 |
Token | :: |
Token ID | 3712 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
Ult | +1.319 |
uez | +1.277 |
--- | +1.202 |
Temp | +1.103 |
._ | +1.085 |
Neg logit contributions | |
corrid | -1.654 |
KS | -1.582 |
Nieto | -1.550 |
Moj | -1.515 |
Okin | -1.494 |
Token | Measure |
Token ID | 47384 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
corrid | +0.397 |
KS | +0.393 |
Nieto | +0.385 |
Moj | +0.379 |
Okin | +0.372 |
Neg logit contributions | |
Ult | -0.202 |
uez | -0.197 |
--- | -0.177 |
alach | -0.159 |
Olymp | -0.157 |
Token | you |
Token ID | 345 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
KS | +3.142 |
Moj | +3.040 |
Nieto | +3.030 |
Okin | +2.906 |
ico | +2.884 |
Neg logit contributions | |
Ult | -2.072 |
uez | -1.967 |
--- | -1.736 |
alach | -1.698 |
utenberg | -1.676 |
Token | for |
Token ID | 329 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
KS | +2.484 |
Nieto | +2.376 |
Moj | +2.352 |
corrid | +2.281 |
ico | +2.251 |
Neg logit contributions | |
Ult | -3.123 |
uez | -3.028 |
--- | -2.766 |
alach | -2.712 |
Temp | -2.663 |
Token | signing |
Token ID | 8415 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
KS | +1.314 |
Nieto | +1.238 |
corrid | +1.211 |
Moj | +1.185 |
Okin | +1.109 |
Neg logit contributions | |
Ult | -3.552 |
uez | -3.459 |
--- | -3.274 |
alach | -3.209 |
Temp | -3.196 |
Token | up |
Token ID | 510 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Ult | +0.807 |
uez | +0.781 |
--- | +0.724 |
Temp | +0.658 |
alach | +0.650 |
Neg logit contributions | |
corrid | -1.183 |
KS | -1.153 |
Nieto | -1.129 |
Moj | -1.107 |
Okin | -1.091 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
KS | +1.133 |
Nieto | +1.093 |
Moj | +1.079 |
corrid | +1.056 |
ico | +1.048 |
Neg logit contributions | |
Ult | -1.213 |
uez | -1.186 |
--- | -1.081 |
alach | -1.053 |
utenberg | -1.030 |
Token | For |
Token ID | 1114 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
KS | +1.199 |
Nieto | +1.159 |
corrid | +1.142 |
Moj | +1.138 |
Okin | +1.098 |
Neg logit contributions | |
Ult | -1.819 |
uez | -1.796 |
--- | -1.669 |
alach | -1.606 |
utenberg | -1.587 |
Token | more |
Token ID | 517 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
KS | +6.217 |
Moj | +5.963 |
Nieto | +5.942 |
ico | +5.728 |
Okin | +5.457 |
Neg logit contributions | |
Ult | -8.761 |
uez | -8.229 |
alach | -7.548 |
utenberg | -7.540 |
20439 | -7.390 |
Token | from |
Token ID | 422 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
KS | +2.699 |
Nieto | +2.575 |
Moj | +2.540 |
ico | +2.441 |
corrid | +2.432 |
Neg logit contributions | |
Ult | -3.239 |
uez | -3.134 |
--- | -2.830 |
alach | -2.829 |
Temp | -2.780 |
Token | The |
Token ID | 383 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
KS | +0.614 |
corrid | +0.608 |
Nieto | +0.598 |
Moj | +0.585 |
Okin | +0.571 |
Neg logit contributions | |
Ult | -0.633 |
uez | -0.616 |
--- | -0.573 |
Temp | -0.540 |
alach | -0.540 |
Token | Nation |
Token ID | 8741 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
corrid | +0.249 |
KS | +0.239 |
Nieto | +0.230 |
Moj | +0.221 |
Okin | +0.215 |
Neg logit contributions | |
Ult | -0.522 |
uez | -0.512 |
--- | -0.489 |
Temp | -0.464 |
alach | -0.462 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Ult | +1.069 |
uez | +1.040 |
--- | +0.974 |
Temp | +0.906 |
alach | +0.899 |
Neg logit contributions | |
corrid | -1.097 |
KS | -1.074 |
Nieto | -1.047 |
Moj | -1.023 |
Okin | -1.004 |
Token | fast |
Token ID | 7217 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
KS | +1.128 |
corrid | +1.114 |
Nieto | +1.087 |
Moj | +1.073 |
ico | +1.068 |
Neg logit contributions | |
Ult | -1.401 |
uez | -1.360 |
--- | -1.270 |
Temp | -1.206 |
Olymp | -1.194 |
Token | te |
Token ID | 660 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
Ult | +1.133 |
uez | +1.095 |
--- | +1.015 |
Temp | +0.925 |
alach | +0.916 |
Neg logit contributions | |
corrid | -1.622 |
KS | -1.589 |
Nieto | -1.553 |
Moj | -1.523 |
Okin | -1.500 |
Token | legraph |
Token ID | 16606 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Ult | +0.267 |
uez | +0.257 |
--- | +0.239 |
Temp | +0.220 |
alach | +0.218 |
Neg logit contributions | |
corrid | -0.349 |
KS | -0.347 |
Nieto | -0.337 |
Moj | -0.331 |
ico | -0.325 |
Token | . |
Token ID | 13 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
Ult | +0.982 |
uez | +0.955 |
--- | +0.897 |
Temp | +0.828 |
alach | +0.820 |
Neg logit contributions | |
corrid | -1.072 |
KS | -1.040 |
Nieto | -1.016 |
Moj | -0.992 |
Okin | -0.976 |
Token | co |
Token ID | 1073 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
KS | +3.409 |
ico | +3.301 |
Moj | +3.091 |
Nieto | +3.014 |
ikan | +2.850 |
Neg logit contributions | |
Ult | -7.104 |
uez | -6.870 |
alach | -6.521 |
--- | -6.398 |
Olymp | -6.294 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
KS | +3.293 |
Moj | +3.117 |
Nieto | +3.099 |
ico | +3.049 |
Okin | +2.951 |
Neg logit contributions | |
Ult | -3.904 |
uez | -3.835 |
alach | -3.512 |
--- | -3.450 |
20439 | -3.405 |
Token | uk |
Token ID | 2724 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
KS | +5.050 |
ico | +4.659 |
Moj | +4.582 |
Nieto | +4.418 |
ikan | +4.363 |
Neg logit contributions | |
Ult | -8.708 |
uez | -8.532 |
alach | -8.194 |
defic | -8.151 |
20439 | -7.959 |
Token | / |
Token ID | 14 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
KS | +1.558 |
Nieto | +1.490 |
Moj | +1.477 |
ico | +1.440 |
corrid | +1.423 |
Neg logit contributions | |
Ult | -2.125 |
uez | -2.096 |
--- | -1.922 |
alach | -1.891 |
utenberg | -1.854 |
Token | in |
Token ID | 259 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
KS | +2.936 |
corrid | +2.919 |
Nieto | +2.796 |
ico | +2.761 |
Moj | +2.742 |
Neg logit contributions | |
Ult | -3.566 |
uez | -3.474 |
--- | -3.197 |
alach | -3.113 |
Temp | -3.100 |
Token | coming |
Token ID | 4976 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
KS | +1.252 |
corrid | +1.243 |
ico | +1.224 |
Nieto | +1.213 |
Moj | +1.189 |
Neg logit contributions | |
Ult | -1.693 |
uez | -1.678 |
--- | -1.520 |
utenberg | -1.476 |
Temp | -1.467 |
Token | / |
Token ID | 14 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
KS | +1.317 |
Nieto | +1.276 |
corrid | +1.271 |
ico | +1.264 |
Moj | +1.243 |
Neg logit contributions | |
Ult | -2.014 |
uez | -1.915 |
--- | -1.760 |
Temp | -1.718 |
alach | -1.718 |
Token | afraid |
Token ID | 7787 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
Ult | +0.573 |
uez | +0.553 |
--- | +0.502 |
Temp | +0.458 |
alach | +0.458 |
Neg logit contributions | |
corrid | -0.868 |
KS | -0.860 |
Nieto | -0.841 |
Moj | -0.825 |
Okin | -0.814 |
Token | of |
Token ID | 286 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
corrid | +0.369 |
KS | +0.367 |
Nieto | +0.359 |
Moj | +0.351 |
Okin | +0.345 |
Neg logit contributions | |
Ult | -0.308 |
uez | -0.300 |
--- | -0.276 |
alach | -0.257 |
Temp | -0.256 |
Token | that |
Token ID | 326 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
corrid | +0.066 |
KS | +0.065 |
Nieto | +0.063 |
Moj | +0.062 |
Okin | +0.060 |
Neg logit contributions | |
Ult | -0.067 |
uez | -0.065 |
--- | -0.061 |
Temp | -0.057 |
alach | -0.057 |
Token | too |
Token ID | 1165 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
KS | +0.845 |
corrid | +0.830 |
Nieto | +0.817 |
Moj | +0.806 |
Okin | +0.787 |
Neg logit contributions | |
Ult | -0.628 |
uez | -0.607 |
--- | -0.543 |
alach | -0.525 |
20439 | -0.521 |
Token | . |
Token ID | 13 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
KS | +3.455 |
Moj | +3.277 |
Nieto | +3.267 |
ico | +3.153 |
Okin | +3.099 |
Neg logit contributions | |
Ult | -4.211 |
uez | -4.161 |
alach | -3.810 |
utenberg | -3.727 |
20439 | -3.688 |
Token | Last |
Token ID | 4586 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
KS | +2.181 |
corrid | +2.165 |
Nieto | +2.122 |
Moj | +2.073 |
Okin | +2.006 |
Neg logit contributions | |
Ult | -2.937 |
uez | -2.899 |
--- | -2.703 |
alach | -2.578 |
Temp | -2.556 |
Token | week |
Token ID | 1285 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
KS | +4.462 |
Moj | +4.218 |
Nieto | +4.153 |
ico | +3.888 |
corrid | +3.775 |
Neg logit contributions | |
Ult | -9.941 |
uez | -9.645 |
alach | -9.076 |
--- | -8.900 |
20439 | -8.890 |
Token | I |
Token ID | 314 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
corrid | +0.286 |
KS | +0.283 |
Nieto | +0.274 |
Moj | +0.266 |
Okin | +0.260 |
Neg logit contributions | |
Ult | -0.415 |
uez | -0.406 |
--- | -0.384 |
Temp | -0.362 |
alach | -0.362 |
Token | caught |
Token ID | 4978 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
corrid | +1.481 |
KS | +1.450 |
Nieto | +1.418 |
Moj | +1.378 |
Okin | +1.353 |
Neg logit contributions | |
Ult | -1.642 |
uez | -1.596 |
--- | -1.487 |
Temp | -1.402 |
alach | -1.399 |
Token | her |
Token ID | 607 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Ult | +1.295 |
uez | +1.244 |
--- | +1.134 |
Temp | +1.010 |
alach | +0.999 |
Neg logit contributions | |
corrid | -2.495 |
KS | -2.451 |
Nieto | -2.403 |
Moj | -2.362 |
Okin | -2.330 |
Token | re |
Token ID | 302 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
KS | +1.388 |
corrid | +1.376 |
Nieto | +1.345 |
Moj | +1.329 |
Okin | +1.300 |
Neg logit contributions | |
Ult | -1.392 |
uez | -1.332 |
--- | -1.239 |
alach | -1.193 |
Temp | -1.179 |
Token | more |
Token ID | 517 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
KS | +6.217 |
Moj | +5.963 |
Nieto | +5.942 |
ico | +5.728 |
Okin | +5.457 |
Neg logit contributions | |
Ult | -8.761 |
uez | -8.229 |
alach | -7.548 |
utenberg | -7.540 |
20439 | -7.390 |
Token | from |
Token ID | 422 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
KS | +2.699 |
Nieto | +2.575 |
Moj | +2.540 |
ico | +2.441 |
corrid | +2.432 |
Neg logit contributions | |
Ult | -3.239 |
uez | -3.134 |
--- | -2.830 |
alach | -2.829 |
Temp | -2.780 |
Token | The |
Token ID | 383 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
KS | +0.614 |
corrid | +0.608 |
Nieto | +0.598 |
Moj | +0.585 |
Okin | +0.571 |
Neg logit contributions | |
Ult | -0.633 |
uez | -0.616 |
--- | -0.573 |
Temp | -0.540 |
alach | -0.540 |
Token | Nation |
Token ID | 8741 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
corrid | +0.249 |
KS | +0.239 |
Nieto | +0.230 |
Moj | +0.221 |
Okin | +0.215 |
Neg logit contributions | |
Ult | -0.522 |
uez | -0.512 |
--- | -0.489 |
Temp | -0.464 |
alach | -0.462 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Ult | +1.069 |
uez | +1.040 |
--- | +0.974 |
Temp | +0.906 |
alach | +0.899 |
Neg logit contributions | |
corrid | -1.097 |
KS | -1.074 |
Nieto | -1.047 |
Moj | -1.023 |
Okin | -1.004 |
Token | check |
Token ID | 2198 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
KS | +1.506 |
corrid | +1.473 |
Nieto | +1.450 |
Moj | +1.409 |
Okin | +1.363 |
Neg logit contributions | |
Ult | -2.178 |
uez | -2.103 |
--- | -1.957 |
Temp | -1.884 |
alach | -1.879 |
Token | out |
Token ID | 503 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
KS | +7.121 |
Nieto | +6.639 |
Moj | +6.537 |
ico | +6.217 |
Okin | +6.215 |
Neg logit contributions | |
Ult | -6.943 |
uez | -6.417 |
20439 | -6.109 |
alach | -6.046 |
Temp | -5.816 |
Token | our |
Token ID | 674 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
KS | +4.422 |
Nieto | +4.383 |
Moj | +4.238 |
corrid | +4.129 |
ico | +4.070 |
Neg logit contributions | |
Ult | -4.614 |
uez | -4.424 |
--- | -3.986 |
alach | -3.939 |
20439 | -3.868 |
Token | latest |
Token ID | 3452 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
KS | +3.929 |
Nieto | +3.838 |
Moj | +3.792 |
corrid | +3.725 |
ico | +3.694 |
Neg logit contributions | |
Ult | -3.241 |
uez | -3.175 |
--- | -2.786 |
alach | -2.711 |
Temp | -2.673 |
Token | issue |
Token ID | 2071 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
KS | +3.036 |
Nieto | +2.930 |
corrid | +2.871 |
Moj | +2.865 |
ico | +2.787 |
Neg logit contributions | |
Ult | -3.219 |
uez | -3.123 |
--- | -2.846 |
alach | -2.757 |
20439 | -2.757 |
Token |
|
Token ID | 198 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
corrid | +0.325 |
KS | +0.321 |
Nieto | +0.311 |
Moj | +0.302 |
Okin | +0.296 |
Neg logit contributions | |
Ult | -0.444 |
uez | -0.435 |
--- | -0.410 |
Temp | -0.386 |
alach | -0.385 |
Token | ( |
Token ID | 357 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Ult | +0.133 |
uez | +0.131 |
--- | +0.122 |
alach | +0.114 |
Temp | +0.114 |
Neg logit contributions | |
corrid | -0.123 |
KS | -0.119 |
Nieto | -0.117 |
Moj | -0.113 |
Okin | -0.111 |
Token | in |
Token ID | 259 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
corrid | +1.672 |
KS | +1.650 |
Nieto | +1.599 |
Moj | +1.568 |
Okin | +1.552 |
Neg logit contributions | |
Ult | -1.252 |
uez | -1.233 |
--- | -1.119 |
alach | -1.040 |
20439 | -1.029 |
Token | out |
Token ID | 448 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
corrid | +1.365 |
KS | +1.356 |
Nieto | +1.304 |
Moj | +1.282 |
Okin | +1.265 |
Neg logit contributions | |
Ult | -1.278 |
uez | -1.260 |
--- | -1.146 |
alach | -1.079 |
20439 | -1.071 |
Token | app |
Token ID | 598 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Ult | +0.473 |
uez | +0.460 |
--- | +0.429 |
Temp | +0.398 |
alach | +0.395 |
Neg logit contributions | |
corrid | -0.533 |
KS | -0.521 |
Nieto | -0.507 |
Moj | -0.496 |
Okin | -0.489 |
Token | data |
Token ID | 7890 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Ult | +0.592 |
uez | +0.567 |
--- | +0.509 |
Temp | +0.453 |
Olymp | +0.450 |
Neg logit contributions | |
corrid | -1.182 |
KS | -1.160 |
Nieto | -1.136 |
Moj | -1.117 |
Okin | -1.103 |
Token | _ |
Token ID | 62 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
corrid | +2.693 |
KS | +2.672 |
Nieto | +2.586 |
ico | +2.511 |
Moj | +2.503 |
Neg logit contributions | |
Ult | -2.937 |
uez | -2.860 |
--- | -2.634 |
alach | -2.538 |
20439 | -2.482 |
Token | full |
Token ID | 12853 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
ico | +6.006 |
KS | +5.944 |
corrid | +5.784 |
Nieto | +5.672 |
Okin | +5.565 |
Neg logit contributions | |
Ult | -7.085 |
uez | -7.081 |
--- | -6.452 |
Olymp | -6.388 |
20439 | -6.239 |
Token | v |
Token ID | 410 |
Feature activation | -6.35e-03 |
Pos logit contributions | |
corrid | +2.974 |
KS | +2.963 |
Nieto | +2.819 |
Moj | +2.749 |
Okin | +2.744 |
Neg logit contributions | |
Ult | -3.151 |
uez | -3.051 |
--- | -2.802 |
alach | -2.683 |
20439 | -2.672 |
Token | ) |
Token ID | 8 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
corrid | +0.043 |
KS | +0.042 |
Nieto | +0.041 |
Moj | +0.040 |
Okin | +0.039 |
Neg logit contributions | |
Ult | -0.046 |
uez | -0.044 |
--- | -0.042 |
alach | -0.039 |
Temp | -0.039 |
Token | { |
Token ID | 1391 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Ult | +1.021 |
uez | +0.997 |
--- | +0.935 |
Temp | +0.873 |
alach | +0.869 |
Neg logit contributions | |
corrid | -0.942 |
KS | -0.918 |
Nieto | -0.892 |
Moj | -0.870 |
Okin | -0.854 |
Token | v |
Token ID | 410 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
Ult | +1.083 |
uez | +1.053 |
--- | +0.986 |
Temp | +0.911 |
alach | +0.904 |
Neg logit contributions | |
corrid | -1.195 |
KS | -1.165 |
Nieto | -1.136 |
Moj | -1.111 |
Okin | -1.093 |
Token | and |
Token ID | 290 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
corrid | +1.632 |
KS | +1.584 |
Nieto | +1.552 |
Moj | +1.513 |
Okin | +1.479 |
Neg logit contributions | |
Ult | -1.860 |
uez | -1.813 |
--- | -1.688 |
Temp | -1.599 |
alach | -1.590 |
Token | Sh |
Token ID | 911 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Ult | +1.144 |
uez | +1.110 |
--- | +1.035 |
Temp | +0.951 |
alach | +0.943 |
Neg logit contributions | |
corrid | -1.429 |
KS | -1.395 |
Nieto | -1.362 |
Moj | -1.335 |
Okin | -1.314 |
Token | us |
Token ID | 385 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
Ult | +1.979 |
uez | +1.947 |
--- | +1.824 |
Temp | +1.669 |
alach | +1.651 |
Neg logit contributions | |
corrid | -2.325 |
KS | -2.173 |
Nieto | -2.148 |
Moj | -2.089 |
Okin | -2.049 |
Token | aku |
Token ID | 8719 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
corrid | +0.125 |
KS | +0.117 |
Nieto | +0.113 |
Moj | +0.109 |
Okin | +0.106 |
Neg logit contributions | |
Ult | -0.258 |
uez | -0.254 |
--- | -0.243 |
Temp | -0.230 |
alach | -0.228 |
Token | U |
Token ID | 471 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
corrid | +0.458 |
KS | +0.449 |
Nieto | +0.434 |
Moj | +0.423 |
Okin | +0.414 |
Neg logit contributions | |
Ult | -0.746 |
uez | -0.735 |
--- | -0.691 |
Temp | -0.661 |
alach | -0.660 |
Token | ch |
Token ID | 354 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Ult | +0.272 |
uez | +0.262 |
--- | +0.241 |
Temp | +0.221 |
alach | +0.217 |
Neg logit contributions | |
corrid | -0.409 |
KS | -0.404 |
Nieto | -0.394 |
Moj | -0.388 |
Okin | -0.382 |
Token | iy |
Token ID | 7745 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
KS | +2.739 |
ico | +2.576 |
ikan | +2.500 |
Nieto | +2.408 |
Okin | +2.315 |
Neg logit contributions | |
Ult | -11.042 |
uez | -10.468 |
--- | -10.040 |
alach | -9.950 |
20439 | -9.930 |
Token | ama |
Token ID | 1689 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Ult | +0.459 |
uez | +0.451 |
--- | +0.426 |
Temp | +0.396 |
alach | +0.393 |
Neg logit contributions | |
corrid | -0.385 |
KS | -0.364 |
Nieto | -0.355 |
Moj | -0.346 |
Okin | -0.338 |
Token | struck |
Token ID | 7425 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
corrid | +1.049 |
KS | +1.018 |
Nieto | +0.997 |
Moj | +0.970 |
Okin | +0.950 |
Neg logit contributions | |
Ult | -1.172 |
uez | -1.144 |
--- | -1.068 |
Temp | -1.005 |
alach | -0.999 |
Token | gold |
Token ID | 3869 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
corrid | +0.652 |
KS | +0.637 |
Nieto | +0.620 |
Moj | +0.607 |
Okin | +0.596 |
Neg logit contributions | |
Ult | -0.642 |
uez | -0.623 |
--- | -0.583 |
Temp | -0.545 |
alach | -0.544 |
Token | with |
Token ID | 351 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
Ult | +1.301 |
uez | +1.262 |
--- | +1.197 |
Temp | +1.086 |
Olymp | +1.078 |
Neg logit contributions | |
corrid | -1.546 |
KS | -1.505 |
Nieto | -1.463 |
Moj | -1.439 |
Okin | -1.413 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
corrid | +0.023 |
KS | +0.023 |
Nieto | +0.022 |
Moj | +0.022 |
Okin | +0.021 |
Neg logit contributions | |
Ult | -0.032 |
uez | -0.031 |
--- | -0.030 |
Temp | -0.028 |
alach | -0.028 |
Token | news |
Token ID | 1705 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
corrid | +1.010 |
KS | +0.989 |
Nieto | +0.964 |
Moj | +0.944 |
Okin | +0.927 |
Neg logit contributions | |
Ult | -0.893 |
uez | -0.866 |
--- | -0.810 |
Temp | -0.749 |
alach | -0.745 |
Token | pl |
Token ID | 458 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
KS | +1.347 |
corrid | +1.343 |
Nieto | +1.283 |
Moj | +1.275 |
Okin | +1.237 |
Neg logit contributions | |
Ult | -1.601 |
uez | -1.561 |
--- | -1.453 |
alach | -1.385 |
Temp | -1.383 |
Token | s |
Token ID | 82 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Ult | +0.417 |
uez | +0.405 |
--- | +0.379 |
Temp | +0.354 |
alach | +0.353 |
Neg logit contributions | |
KS | -0.411 |
corrid | -0.410 |
Nieto | -0.397 |
Moj | -0.389 |
Okin | -0.381 |
Token | . |
Token ID | 13 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
Ult | +0.977 |
uez | +0.949 |
--- | +0.894 |
Temp | +0.823 |
Olymp | +0.812 |
Neg logit contributions | |
corrid | -1.088 |
KS | -1.047 |
Nieto | -1.024 |
Moj | -0.999 |
Okin | -0.985 |
Token | Good |
Token ID | 4599 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
KS | +3.002 |
Nieto | +2.877 |
Moj | +2.825 |
corrid | +2.681 |
Okin | +2.640 |
Neg logit contributions | |
Ult | -5.607 |
uez | -5.544 |
--- | -5.057 |
alach | -5.034 |
utenberg | -4.958 |
Token | updates |
Token ID | 5992 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
KS | +5.951 |
Nieto | +5.620 |
Moj | +5.579 |
ico | +5.276 |
Okin | +5.133 |
Neg logit contributions | |
Ult | -7.708 |
uez | -7.313 |
alach | -6.962 |
gypt | -6.675 |
Temp | -6.575 |
Token | ? |
Token ID | 30 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
KS | +3.442 |
Nieto | +3.231 |
Moj | +3.196 |
ico | +3.029 |
Lennon | +3.020 |
Neg logit contributions | |
uez | -4.864 |
Ult | -4.846 |
alach | -4.466 |
--- | -4.308 |
utenberg | -4.269 |
Token | No |
Token ID | 1400 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
KS | +2.962 |
Nieto | +2.857 |
Moj | +2.825 |
Okin | +2.690 |
ico | +2.629 |
Neg logit contributions | |
Ult | -3.908 |
uez | -3.896 |
alach | -3.598 |
--- | -3.538 |
utenberg | -3.424 |
Token | more |
Token ID | 517 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
KS | +5.739 |
Moj | +5.476 |
Nieto | +5.366 |
ico | +5.318 |
Lennon | +5.065 |
Neg logit contributions | |
Ult | -7.132 |
uez | -6.691 |
alach | -6.215 |
20439 | -6.064 |
Temp | -6.051 |
Token | bad |
Token ID | 2089 |
Feature activation | -6.61e-03 |
Pos logit contributions | |
Ult | +0.963 |
uez | +0.945 |
--- | +0.904 |
Temp | +0.836 |
._ | +0.831 |
Neg logit contributions | |
corrid | -0.794 |
KS | -0.754 |
Nieto | -0.736 |
Moj | -0.712 |
Okin | -0.705 |
Token | CPUs |
Token ID | 32340 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Ult | +0.404 |
uez | +0.393 |
--- | +0.370 |
Temp | +0.343 |
alach | +0.340 |
Neg logit contributions | |
corrid | -0.415 |
KS | -0.404 |
Nieto | -0.394 |
Moj | -0.385 |
Okin | -0.378 |
Token | and |
Token ID | 290 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
corrid | +1.584 |
KS | +1.569 |
Nieto | +1.514 |
Moj | +1.495 |
Okin | +1.451 |
Neg logit contributions | |
Ult | -1.492 |
uez | -1.449 |
--- | -1.336 |
alach | -1.259 |
Temp | -1.257 |
Token | memory |
Token ID | 4088 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
corrid | +0.437 |
KS | +0.424 |
Nieto | +0.410 |
Moj | +0.401 |
Okin | +0.392 |
Neg logit contributions | |
Ult | -0.573 |
uez | -0.559 |
--- | -0.529 |
Temp | -0.496 |
alach | -0.494 |
Token | ( |
Token ID | 357 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
corrid | +1.008 |
KS | +0.995 |
Nieto | +0.956 |
Moj | +0.946 |
Okin | +0.921 |
Neg logit contributions | |
Ult | -0.964 |
uez | -0.938 |
--- | -0.866 |
alach | -0.816 |
Temp | -0.810 |
Token | Intel |
Token ID | 24123 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
corrid | +0.887 |
KS | +0.869 |
Nieto | +0.842 |
Moj | +0.827 |
Okin | +0.807 |
Neg logit contributions | |
Ult | -0.866 |
uez | -0.848 |
--- | -0.791 |
Temp | -0.734 |
alach | -0.733 |
Token | VT |
Token ID | 32751 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
KS | +3.845 |
corrid | +3.781 |
Nieto | +3.571 |
Moj | +3.568 |
ico | +3.434 |
Neg logit contributions | |
Ult | -4.333 |
uez | -4.268 |
--- | -3.947 |
alach | -3.782 |
20439 | -3.770 |
Token | - |
Token ID | 12 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
KS | +6.653 |
Moj | +6.251 |
corrid | +6.221 |
ico | +6.179 |
Nieto | +6.167 |
Neg logit contributions | |
Ult | -6.889 |
uez | -6.854 |
20439 | -6.606 |
alach | -6.218 |
--- | -6.062 |
Token | x |
Token ID | 87 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
corrid | +1.095 |
KS | +1.063 |
Nieto | +1.042 |
Moj | +1.020 |
Okin | +1.006 |
Neg logit contributions | |
Ult | -0.864 |
uez | -0.837 |
--- | -0.783 |
Temp | -0.719 |
._ | -0.706 |
Token | , |
Token ID | 11 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
corrid | +2.978 |
KS | +2.962 |
Nieto | +2.791 |
Moj | +2.734 |
Okin | +2.645 |
Neg logit contributions | |
Ult | -4.775 |
uez | -4.661 |
--- | -4.420 |
Temp | -4.189 |
alach | -4.164 |
Token | AMD |
Token ID | 10324 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
KS | +2.990 |
corrid | +2.966 |
Nieto | +2.815 |
Moj | +2.798 |
Okin | +2.705 |
Neg logit contributions | |
Ult | -3.688 |
uez | -3.603 |
--- | -3.394 |
alach | -3.201 |
Temp | -3.197 |
Token | - |
Token ID | 12 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
KS | +2.626 |
corrid | +2.602 |
Nieto | +2.474 |
Moj | +2.433 |
Okin | +2.374 |
Neg logit contributions | |
Ult | -3.302 |
uez | -3.281 |
--- | -3.054 |
alach | -2.900 |
Temp | -2.868 |
Token | 20 |
Token ID | 1160 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
corrid | +0.181 |
KS | +0.178 |
Nieto | +0.173 |
Moj | +0.169 |
Okin | +0.164 |
Neg logit contributions | |
Ult | -0.237 |
uez | -0.231 |
--- | -0.218 |
Temp | -0.205 |
alach | -0.205 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
KS | +3.208 |
Nieto | +3.080 |
Moj | +3.052 |
ico | +2.908 |
corrid | +2.900 |
Neg logit contributions | |
Ult | -4.013 |
uez | -3.932 |
alach | -3.644 |
--- | -3.588 |
utenberg | -3.506 |
Token | 07 |
Token ID | 8753 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
KS | +4.204 |
Moj | +3.996 |
Nieto | +3.989 |
corrid | +3.783 |
Okin | +3.746 |
Neg logit contributions | |
Ult | -8.776 |
uez | -8.692 |
alach | -7.963 |
--- | -7.883 |
utenberg | -7.841 |
Token | : |
Token ID | 25 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
KS | +3.199 |
Nieto | +3.037 |
Moj | +3.010 |
ico | +2.947 |
Okin | +2.885 |
Neg logit contributions | |
Ult | -3.590 |
uez | -3.529 |
alach | -3.256 |
--- | -3.126 |
utenberg | -3.126 |
Token | 44 |
Token ID | 2598 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
KS | +3.123 |
Nieto | +2.995 |
Moj | +2.952 |
corrid | +2.926 |
ico | +2.890 |
Neg logit contributions | |
uez | -3.960 |
Ult | -3.955 |
--- | -3.577 |
alach | -3.561 |
utenberg | -3.507 |
Token | Se |
Token ID | 1001 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
KS | +2.143 |
corrid | +2.124 |
Nieto | +2.052 |
Moj | +2.033 |
Okin | +1.974 |
Neg logit contributions | |
Ult | -2.573 |
uez | -2.488 |
--- | -2.344 |
alach | -2.228 |
20439 | -2.218 |
Token | eker |
Token ID | 28233 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
KS | +3.995 |
Nieto | +3.957 |
ikan | +3.898 |
ico | +3.831 |
Moj | +3.664 |
Neg logit contributions | |
Ult | -9.372 |
uez | -9.038 |
--- | -8.672 |
alach | -8.436 |
Olymp | -8.392 |
Token | wrote |
Token ID | 2630 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
KS | +0.709 |
corrid | +0.705 |
Nieto | +0.690 |
Moj | +0.675 |
Okin | +0.663 |
Neg logit contributions | |
Ult | -0.553 |
uez | -0.530 |
--- | -0.490 |
alach | -0.458 |
Temp | -0.452 |
Token | : |
Token ID | 25 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
KS | +1.893 |
Nieto | +1.819 |
Moj | +1.794 |
ico | +1.748 |
corrid | +1.737 |
Neg logit contributions | |
Ult | -1.911 |
uez | -1.857 |
--- | -1.691 |
alach | -1.681 |
utenberg | -1.617 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
KS | +0.793 |
corrid | +0.776 |
Nieto | +0.762 |
Moj | +0.744 |
Okin | +0.724 |
Neg logit contributions | |
Ult | -1.144 |
uez | -1.127 |
--- | -1.053 |
alach | -1.009 |
Temp | -0.997 |
Token |
|
Token ID | 198 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
KS | +1.292 |
Nieto | +1.230 |
Moj | +1.209 |
corrid | +1.204 |
ico | +1.169 |
Neg logit contributions | |
Ult | -1.946 |
uez | -1.920 |
--- | -1.783 |
alach | -1.739 |
20439 | -1.702 |
Token | each |
Token ID | 1123 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
Ult | +0.926 |
uez | +0.902 |
--- | +0.845 |
Temp | +0.774 |
Olymp | +0.767 |
Neg logit contributions | |
corrid | -1.107 |
KS | -1.072 |
Nieto | -1.051 |
Moj | -1.025 |
Okin | -1.013 |
Token | pixel |
Token ID | 17465 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
Ult | +0.112 |
uez | +0.108 |
--- | +0.100 |
Temp | +0.090 |
alach | +0.089 |
Neg logit contributions | |
corrid | -0.174 |
KS | -0.170 |
Nieto | -0.166 |
Moj | -0.163 |
Okin | -0.161 |
Token | and |
Token ID | 290 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
corrid | +0.208 |
KS | +0.202 |
Nieto | +0.197 |
Moj | +0.193 |
Okin | +0.190 |
Neg logit contributions | |
Ult | -0.194 |
uez | -0.189 |
--- | -0.177 |
Temp | -0.164 |
alach | -0.163 |
Token | have |
Token ID | 423 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
Ult | +1.058 |
uez | +1.029 |
--- | +0.970 |
Temp | +0.891 |
Olymp | +0.882 |
Neg logit contributions | |
corrid | -1.166 |
KS | -1.126 |
Nieto | -1.105 |
Moj | -1.076 |
Okin | -1.061 |
Token | j |
Token ID | 474 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Ult | +0.447 |
uez | +0.435 |
--- | +0.409 |
Temp | +0.377 |
Olymp | +0.373 |
Neg logit contributions | |
corrid | -0.490 |
KS | -0.475 |
Nieto | -0.464 |
Moj | -0.454 |
Okin | -0.447 |
Token | agg |
Token ID | 9460 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
corrid | +1.032 |
KS | +1.007 |
Nieto | +0.980 |
Moj | +0.960 |
Okin | +0.941 |
Neg logit contributions | |
Ult | -0.980 |
uez | -0.951 |
--- | -0.893 |
Temp | -0.828 |
alach | -0.820 |
Token | ies |
Token ID | 444 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
KS | +6.452 |
Nieto | +6.193 |
ico | +6.165 |
Moj | +6.025 |
ikan | +5.972 |
Neg logit contributions | |
Ult | -6.764 |
uez | -6.237 |
--- | -5.803 |
Temp | -5.590 |
alach | -5.557 |
Token | but |
Token ID | 475 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
corrid | +1.797 |
KS | +1.775 |
Nieto | +1.721 |
Moj | +1.687 |
Okin | +1.646 |
Neg logit contributions | |
Ult | -1.714 |
uez | -1.670 |
--- | -1.550 |
Temp | -1.454 |
alach | -1.443 |
Token | I |
Token ID | 314 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Ult | +0.896 |
uez | +0.872 |
--- | +0.822 |
Temp | +0.757 |
Olymp | +0.750 |
Neg logit contributions | |
corrid | -0.944 |
KS | -0.912 |
Nieto | -0.895 |
Moj | -0.870 |
Okin | -0.858 |
Token | have |
Token ID | 423 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
corrid | +1.309 |
KS | +1.302 |
Nieto | +1.258 |
Moj | +1.239 |
Okin | +1.212 |
Neg logit contributions | |
Ult | -1.226 |
uez | -1.182 |
--- | -1.100 |
Temp | -1.031 |
alach | -1.020 |
Token | no |
Token ID | 645 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
corrid | +1.319 |
KS | +1.304 |
Nieto | +1.259 |
Moj | +1.240 |
Okin | +1.213 |
Neg logit contributions | |
Ult | -1.266 |
uez | -1.237 |
--- | -1.148 |
alach | -1.075 |
Temp | -1.070 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
corrid | +0.283 |
KS | +0.275 |
Nieto | +0.268 |
Moj | +0.261 |
Okin | +0.256 |
Neg logit contributions | |
Ult | -0.327 |
uez | -0.319 |
--- | -0.301 |
Temp | -0.281 |
alach | -0.279 |
Token | : |
Token ID | 25 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
Ult | +1.090 |
uez | +1.058 |
--- | +1.008 |
Temp | +0.928 |
Olymp | +0.919 |
Neg logit contributions | |
corrid | -1.055 |
KS | -1.012 |
Nieto | -0.993 |
Moj | -0.967 |
Okin | -0.951 |
Token | 0 |
Token ID | 657 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
corrid | +0.278 |
KS | +0.270 |
Nieto | +0.262 |
Moj | +0.255 |
Okin | +0.250 |
Neg logit contributions | |
Ult | -0.359 |
uez | -0.350 |
--- | -0.331 |
Temp | -0.311 |
alach | -0.309 |
Token | 505 |
Token ID | 31654 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Ult | +0.518 |
uez | +0.504 |
--- | +0.472 |
Temp | +0.437 |
alach | +0.434 |
Neg logit contributions | |
corrid | -0.560 |
KS | -0.546 |
Nieto | -0.532 |
Moj | -0.520 |
Okin | -0.511 |
Token | z |
Token ID | 89 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
Ult | +1.487 |
uez | +1.447 |
--- | +1.362 |
Temp | +1.250 |
alach | +1.234 |
Neg logit contributions | |
corrid | -1.701 |
KS | -1.647 |
Nieto | -1.611 |
Moj | -1.573 |
Okin | -1.551 |
Token | BLACK |
Token ID | 31963 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
KS | +2.615 |
corrid | +2.613 |
Nieto | +2.520 |
Moj | +2.477 |
Okin | +2.397 |
Neg logit contributions | |
Ult | -2.985 |
uez | -2.927 |
--- | -2.709 |
alach | -2.575 |
Temp | -2.556 |
Token | FO |
Token ID | 6080 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
KS | +4.636 |
corrid | +4.539 |
Nieto | +4.169 |
Moj | +4.150 |
ico | +3.964 |
Neg logit contributions | |
Ult | -8.348 |
uez | -8.327 |
--- | -7.649 |
alach | -7.562 |
utenberg | -7.390 |
Token | OT |
Token ID | 2394 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
KS | +2.824 |
corrid | +2.728 |
Nieto | +2.697 |
Moj | +2.632 |
Okin | +2.584 |
Neg logit contributions | |
Ult | -3.615 |
uez | -3.567 |
--- | -3.308 |
alach | -3.170 |
utenberg | -3.127 |
Token | T |
Token ID | 309 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
corrid | +1.772 |
KS | +1.765 |
Nieto | +1.685 |
Moj | +1.656 |
Okin | +1.615 |
Neg logit contributions | |
Ult | -2.039 |
uez | -1.995 |
--- | -1.852 |
alach | -1.758 |
Temp | -1.756 |
Token | OC |
Token ID | 4503 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
corrid | +3.184 |
KS | +3.139 |
Nieto | +2.904 |
Moj | +2.852 |
ico | +2.844 |
Neg logit contributions | |
Ult | -5.011 |
uez | -4.935 |
--- | -4.591 |
alach | -4.432 |
Temp | -4.410 |
Token | RE |
Token ID | 4526 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
KS | +4.161 |
corrid | +4.007 |
Nieto | +3.869 |
Moj | +3.831 |
Okin | +3.712 |
Neg logit contributions | |
Ult | -5.516 |
uez | -5.396 |
--- | -4.930 |
alach | -4.865 |
utenberg | -4.822 |
Token |
|
Token ID | 198 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
corrid | +0.538 |
KS | +0.530 |
Nieto | +0.513 |
Moj | +0.499 |
Okin | +0.488 |
Neg logit contributions | |
Ult | -0.728 |
uez | -0.713 |
--- | -0.673 |
Temp | -0.633 |
alach | -0.633 |
Token |
|
Token ID | 198 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
KS | +2.022 |
Nieto | +1.896 |
Moj | +1.891 |
ico | +1.809 |
Okin | +1.794 |
Neg logit contributions | |
Ult | -3.271 |
uez | -3.248 |
alach | -3.000 |
--- | -2.972 |
20439 | -2.916 |
Token | On |
Token ID | 2202 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
KS | +2.422 |
corrid | +2.420 |
Moj | +2.315 |
Nieto | +2.308 |
ico | +2.303 |
Neg logit contributions | |
uez | -2.318 |
Ult | -2.302 |
--- | -2.102 |
alach | -2.034 |
utenberg | -2.003 |
Token | September |
Token ID | 2693 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
KS | +2.864 |
Nieto | +2.761 |
Moj | +2.722 |
corrid | +2.655 |
ico | +2.549 |
Neg logit contributions | |
Ult | -5.453 |
uez | -5.336 |
--- | -5.028 |
alach | -4.905 |
20439 | -4.825 |
Token | 20 |
Token ID | 1160 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
corrid | +0.181 |
KS | +0.178 |
Nieto | +0.173 |
Moj | +0.169 |
Okin | +0.164 |
Neg logit contributions | |
Ult | -0.237 |
uez | -0.231 |
--- | -0.218 |
Temp | -0.205 |
alach | -0.205 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
KS | +3.208 |
Nieto | +3.080 |
Moj | +3.052 |
ico | +2.908 |
corrid | +2.900 |
Neg logit contributions | |
Ult | -4.013 |
uez | -3.932 |
alach | -3.644 |
--- | -3.588 |
utenberg | -3.506 |
Token | 07 |
Token ID | 8753 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
KS | +4.204 |
Moj | +3.996 |
Nieto | +3.989 |
corrid | +3.783 |
Okin | +3.746 |
Neg logit contributions | |
Ult | -8.776 |
uez | -8.692 |
alach | -7.963 |
--- | -7.883 |
utenberg | -7.841 |
Token | : |
Token ID | 25 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
KS | +3.199 |
Nieto | +3.037 |
Moj | +3.010 |
ico | +2.947 |
Okin | +2.885 |
Neg logit contributions | |
Ult | -3.590 |
uez | -3.529 |
alach | -3.256 |
--- | -3.126 |
utenberg | -3.126 |
Token | 44 |
Token ID | 2598 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
KS | +3.123 |
Nieto | +2.995 |
Moj | +2.952 |
corrid | +2.926 |
ico | +2.890 |
Neg logit contributions | |
uez | -3.960 |
Ult | -3.955 |
--- | -3.577 |
alach | -3.561 |
utenberg | -3.507 |
Token | Se |
Token ID | 1001 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
KS | +2.143 |
corrid | +2.124 |
Nieto | +2.052 |
Moj | +2.033 |
Okin | +1.974 |
Neg logit contributions | |
Ult | -2.573 |
uez | -2.488 |
--- | -2.344 |
alach | -2.228 |
20439 | -2.218 |
Token | eker |
Token ID | 28233 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
KS | +3.995 |
Nieto | +3.957 |
ikan | +3.898 |
ico | +3.831 |
Moj | +3.664 |
Neg logit contributions | |
Ult | -9.372 |
uez | -9.038 |
--- | -8.672 |
alach | -8.436 |
Olymp | -8.392 |
Token | 're |
Token ID | 821 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
Ult | +0.233 |
uez | +0.225 |
--- | +0.210 |
Temp | +0.195 |
alach | +0.193 |
Neg logit contributions | |
corrid | -0.266 |
KS | -0.261 |
Nieto | -0.254 |
Moj | -0.248 |
Okin | -0.244 |
Token | not |
Token ID | 407 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
corrid | +0.161 |
KS | +0.158 |
Nieto | +0.153 |
Moj | +0.150 |
Okin | +0.148 |
Neg logit contributions | |
Ult | -0.151 |
uez | -0.147 |
--- | -0.137 |
Temp | -0.128 |
alach | -0.127 |
Token | in |
Token ID | 287 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Ult | +0.333 |
uez | +0.324 |
--- | +0.303 |
Temp | +0.281 |
alach | +0.279 |
Neg logit contributions | |
corrid | -0.354 |
KS | -0.345 |
Nieto | -0.336 |
Moj | -0.329 |
Okin | -0.323 |
Token | the |
Token ID | 262 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Ult | +1.338 |
uez | +1.302 |
--- | +1.223 |
Temp | +1.124 |
alach | +1.117 |
Neg logit contributions | |
corrid | -1.517 |
KS | -1.474 |
Nieto | -1.443 |
Moj | -1.408 |
Okin | -1.386 |
Token | Med |
Token ID | 2019 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
Ult | +1.015 |
uez | +0.988 |
--- | +0.930 |
Temp | +0.859 |
alach | +0.852 |
Neg logit contributions | |
corrid | -1.061 |
KS | -1.030 |
Nieto | -1.006 |
Moj | -0.981 |
Okin | -0.965 |
Token | ig |
Token ID | 328 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
Ult | +0.229 |
uez | +0.224 |
--- | +0.211 |
Temp | +0.197 |
alach | +0.195 |
Neg logit contributions | |
corrid | -0.209 |
KS | -0.203 |
Nieto | -0.197 |
Moj | -0.192 |
Okin | -0.189 |
Token | ap |
Token ID | 499 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ico | +6.173 |
KS | +6.131 |
ikan | +5.903 |
Moj | +5.881 |
corrid | +5.563 |
Neg logit contributions | |
Ult | -6.448 |
uez | -5.913 |
--- | -5.809 |
Temp | -5.641 |
20439 | -5.573 |
Token | business |
Token ID | 1597 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
corrid | +1.433 |
KS | +1.423 |
Nieto | +1.363 |
Moj | +1.347 |
ico | +1.315 |
Neg logit contributions | |
Ult | -1.607 |
uez | -1.560 |
--- | -1.450 |
Temp | -1.381 |
20439 | -1.367 |
Token | ; |
Token ID | 26 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Ult | +1.185 |
uez | +1.151 |
--- | +1.077 |
Temp | +0.995 |
alach | +0.986 |
Neg logit contributions | |
corrid | -1.345 |
KS | -1.312 |
Nieto | -1.280 |
Moj | -1.252 |
Okin | -1.231 |
Token | they |
Token ID | 484 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
Ult | +1.132 |
uez | +1.102 |
--- | +1.036 |
Temp | +0.958 |
alach | +0.950 |
Neg logit contributions | |
corrid | -1.192 |
KS | -1.158 |
Nieto | -1.130 |
Moj | -1.104 |
Okin | -1.085 |
Token | 're |
Token ID | 821 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
Ult | +0.268 |
uez | +0.260 |
--- | +0.243 |
Temp | +0.225 |
alach | +0.222 |
Neg logit contributions | |
corrid | -0.307 |
KS | -0.301 |
Nieto | -0.293 |
Moj | -0.287 |
Okin | -0.282 |
Token | s |
Token ID | 82 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Ult | +0.417 |
uez | +0.405 |
--- | +0.379 |
Temp | +0.354 |
alach | +0.353 |
Neg logit contributions | |
KS | -0.411 |
corrid | -0.410 |
Nieto | -0.397 |
Moj | -0.389 |
Okin | -0.381 |
Token | . |
Token ID | 13 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
Ult | +0.977 |
uez | +0.949 |
--- | +0.894 |
Temp | +0.823 |
Olymp | +0.812 |
Neg logit contributions | |
corrid | -1.088 |
KS | -1.047 |
Nieto | -1.024 |
Moj | -0.999 |
Okin | -0.985 |
Token | Good |
Token ID | 4599 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
KS | +3.002 |
Nieto | +2.877 |
Moj | +2.825 |
corrid | +2.681 |
Okin | +2.640 |
Neg logit contributions | |
Ult | -5.607 |
uez | -5.544 |
--- | -5.057 |
alach | -5.034 |
utenberg | -4.958 |
Token | updates |
Token ID | 5992 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
KS | +5.951 |
Nieto | +5.620 |
Moj | +5.579 |
ico | +5.276 |
Okin | +5.133 |
Neg logit contributions | |
Ult | -7.708 |
uez | -7.313 |
alach | -6.962 |
gypt | -6.675 |
Temp | -6.575 |
Token | ? |
Token ID | 30 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
KS | +3.442 |
Nieto | +3.231 |
Moj | +3.196 |
ico | +3.029 |
Lennon | +3.020 |
Neg logit contributions | |
uez | -4.864 |
Ult | -4.846 |
alach | -4.466 |
--- | -4.308 |
utenberg | -4.269 |
Token | No |
Token ID | 1400 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
KS | +2.962 |
Nieto | +2.857 |
Moj | +2.825 |
Okin | +2.690 |
ico | +2.629 |
Neg logit contributions | |
Ult | -3.908 |
uez | -3.896 |
alach | -3.598 |
--- | -3.538 |
utenberg | -3.424 |
Token | more |
Token ID | 517 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
KS | +5.739 |
Moj | +5.476 |
Nieto | +5.366 |
ico | +5.318 |
Lennon | +5.065 |
Neg logit contributions | |
Ult | -7.132 |
uez | -6.691 |
alach | -6.215 |
20439 | -6.064 |
Temp | -6.051 |
Token | bad |
Token ID | 2089 |
Feature activation | -6.61e-03 |
Pos logit contributions | |
Ult | +0.963 |
uez | +0.945 |
--- | +0.904 |
Temp | +0.836 |
._ | +0.831 |
Neg logit contributions | |
corrid | -0.794 |
KS | -0.754 |
Nieto | -0.736 |
Moj | -0.712 |
Okin | -0.705 |
Token | news |
Token ID | 1705 |
Feature activation | +4.65e-03 |
Pos logit contributions | |
corrid | +0.051 |
KS | +0.049 |
Nieto | +0.048 |
Moj | +0.047 |
Okin | +0.047 |
Neg logit contributions | |
Ult | -0.042 |
uez | -0.041 |
--- | -0.039 |
Temp | -0.035 |
Olymp | -0.035 |
Token | pl |
Token ID | 458 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
Ult | +0.034 |
uez | +0.033 |
--- | +0.031 |
Temp | +0.029 |
alach | +0.029 |
Neg logit contributions | |
corrid | -0.031 |
KS | -0.030 |
Nieto | -0.029 |
Moj | -0.029 |
Okin | -0.028 |
Token | s |
Token ID | 82 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
Ult | +0.572 |
uez | +0.556 |
--- | +0.520 |
alach | +0.485 |
Temp | +0.485 |
Neg logit contributions | |
KS | -0.567 |
corrid | -0.567 |
Nieto | -0.550 |
Moj | -0.539 |
Okin | -0.527 |
Token | ( |
Token ID | 357 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Ult | +1.332 |
uez | +1.289 |
--- | +1.235 |
Temp | +1.142 |
._ | +1.131 |
Neg logit contributions | |
corrid | -1.199 |
KS | -1.139 |
Nieto | -1.119 |
Moj | -1.085 |
Okin | -1.072 |
Token | Photo |
Token ID | 6191 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
corrid | +0.665 |
KS | +0.664 |
Nieto | +0.633 |
Moj | +0.619 |
ico | +0.605 |
Neg logit contributions | |
uez | -0.734 |
Ult | -0.733 |
--- | -0.648 |
alach | -0.648 |
utenberg | -0.641 |
Token | 11 |
Token ID | 1157 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
KS | +1.361 |
corrid | +1.327 |
Nieto | +1.291 |
Moj | +1.286 |
Okin | +1.242 |
Neg logit contributions | |
Ult | -1.305 |
uez | -1.283 |
--- | -1.158 |
20439 | -1.112 |
utenberg | -1.103 |
Token | : |
Token ID | 25 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Ult | +0.563 |
uez | +0.550 |
--- | +0.514 |
alach | +0.482 |
Temp | +0.482 |
Neg logit contributions | |
corrid | -0.467 |
KS | -0.458 |
Nieto | -0.443 |
Moj | -0.433 |
Okin | -0.421 |
Token | SA |
Token ID | 14719 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
corrid | +1.685 |
KS | +1.672 |
Nieto | +1.619 |
Moj | +1.587 |
Okin | +1.547 |
Neg logit contributions | |
Ult | -1.675 |
uez | -1.639 |
--- | -1.523 |
alach | -1.429 |
Temp | -1.420 |
Token | UL |
Token ID | 6239 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
KS | +3.275 |
corrid | +3.217 |
Nieto | +3.130 |
Moj | +3.073 |
Okin | +3.007 |
Neg logit contributions | |
Ult | -2.401 |
uez | -2.324 |
--- | -2.123 |
alach | -1.996 |
20439 | -1.996 |
Token | LO |
Token ID | 17579 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
KS | +0.968 |
Moj | +0.210 |
corrid | +0.139 |
Nieto | +0.079 |
LO | +0.030 |
Neg logit contributions | |
Ult | -12.426 |
uez | -12.151 |
utenberg | -11.699 |
alach | -11.683 |
--- | -11.417 |
Token | EB |
Token ID | 30195 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
Ult | +2.195 |
uez | +2.092 |
--- | +2.004 |
Temp | +1.782 |
._ | +1.763 |
Neg logit contributions | |
corrid | -3.493 |
KS | -3.251 |
Nieto | -3.227 |
Okin | -3.159 |
Moj | -3.156 |
Token | AFP |
Token ID | 8916 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
KS | +2.220 |
Nieto | +2.099 |
corrid | +2.090 |
Moj | +2.019 |
ico | +1.930 |
Neg logit contributions | |
Ult | -2.850 |
uez | -2.786 |
--- | -2.558 |
alach | -2.541 |
utenberg | -2.508 |
Token | / |
Token ID | 14 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
corrid | +0.710 |
KS | +0.705 |
Nieto | +0.676 |
Moj | +0.658 |
Okin | +0.640 |
Neg logit contributions | |
Ult | -0.877 |
uez | -0.853 |
--- | -0.794 |
alach | -0.761 |
Temp | -0.755 |
Token | Getty |
Token ID | 6633 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
KS | +2.390 |
Nieto | +2.307 |
corrid | +2.292 |
Moj | +2.233 |
ico | +2.176 |
Neg logit contributions | |
Ult | -2.880 |
uez | -2.868 |
--- | -2.633 |
alach | -2.595 |
utenberg | -2.553 |
Token | raise |
Token ID | 5298 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
KS | +3.109 |
corrid | +3.041 |
Nieto | +2.965 |
Moj | +2.936 |
Okin | +2.843 |
Neg logit contributions | |
Ult | -3.341 |
uez | -3.200 |
--- | -2.952 |
Temp | -2.829 |
alach | -2.826 |
Token | our |
Token ID | 674 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
KS | +1.587 |
corrid | +1.553 |
Nieto | +1.535 |
Moj | +1.508 |
Okin | +1.485 |
Neg logit contributions | |
Ult | -1.402 |
uez | -1.371 |
--- | -1.255 |
alach | -1.177 |
20439 | -1.170 |
Token | pitch |
Token ID | 7078 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
Ult | +0.611 |
uez | +0.593 |
--- | +0.554 |
Temp | +0.500 |
._ | +0.493 |
Neg logit contributions | |
corrid | -0.924 |
KS | -0.889 |
Nieto | -0.874 |
Moj | -0.855 |
Okin | -0.844 |
Token | for |
Token ID | 1640 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
corrid | +0.582 |
KS | +0.580 |
Nieto | +0.563 |
Moj | +0.553 |
Okin | +0.543 |
Neg logit contributions | |
Ult | -0.488 |
uez | -0.474 |
--- | -0.439 |
Temp | -0.406 |
alach | -0.405 |
Token | ks |
Token ID | 591 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
corrid | +1.047 |
KS | +1.041 |
Nieto | +1.000 |
Moj | +0.974 |
Okin | +0.953 |
Neg logit contributions | |
Ult | -1.444 |
uez | -1.410 |
--- | -1.336 |
Temp | -1.258 |
alach | -1.251 |
Token | over |
Token ID | 625 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
Ult | +0.929 |
uez | +0.906 |
--- | +0.857 |
Temp | +0.794 |
Olymp | +0.787 |
Neg logit contributions | |
corrid | -0.867 |
KS | -0.836 |
Nieto | -0.813 |
Moj | -0.793 |
Okin | -0.780 |
Token | right |
Token ID | 826 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
KS | +2.220 |
Moj | +1.999 |
Nieto | +1.989 |
ico | +1.716 |
Okin | +1.702 |
Neg logit contributions | |
Ult | -10.490 |
uez | -10.184 |
alach | -9.713 |
20439 | -9.672 |
utenberg | -9.545 |
Token | ? |
Token ID | 30 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
KS | +1.483 |
Nieto | +1.411 |
Moj | +1.389 |
corrid | +1.355 |
ico | +1.355 |
Neg logit contributions | |
Ult | -1.841 |
uez | -1.811 |
--- | -1.656 |
alach | -1.630 |
utenberg | -1.591 |
Token | Any |
Token ID | 7149 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
corrid | +0.644 |
KS | +0.628 |
Nieto | +0.614 |
Moj | +0.599 |
Okin | +0.589 |
Neg logit contributions | |
Ult | -0.617 |
uez | -0.605 |
--- | -0.563 |
alach | -0.525 |
Temp | -0.523 |
Token | ways |
Token ID | 1322 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Ult | +2.986 |
uez | +2.938 |
--- | +2.808 |
Temp | +2.605 |
alach | +2.599 |
Neg logit contributions | |
corrid | -2.054 |
KS | -1.907 |
Nieto | -1.864 |
Moj | -1.805 |
Okin | -1.762 |
Token | , |
Token ID | 11 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
Ult | +2.546 |
uez | +2.452 |
--- | +2.371 |
Temp | +2.134 |
._ | +2.123 |
Neg logit contributions | |
corrid | -3.148 |
KS | -2.857 |
Nieto | -2.822 |
Moj | -2.738 |
Okin | -2.720 |
Token | ( |
Token ID | 357 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
Ult | +0.823 |
uez | +0.801 |
--- | +0.762 |
Temp | +0.719 |
alach | +0.715 |
Neg logit contributions | |
corrid | -0.551 |
KS | -0.537 |
Nieto | -0.520 |
Moj | -0.505 |
Okin | -0.491 |
Token | Equ |
Token ID | 23588 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
KS | +0.424 |
corrid | +0.424 |
Nieto | +0.413 |
Moj | +0.405 |
ico | +0.396 |
Neg logit contributions | |
Ult | -0.410 |
uez | -0.406 |
--- | -0.378 |
alach | -0.354 |
utenberg | -0.352 |
Token | ipe |
Token ID | 3757 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
KS | +1.668 |
corrid | +1.640 |
Nieto | +1.637 |
ico | +1.597 |
Moj | +1.594 |
Neg logit contributions | |
Ult | -1.626 |
uez | -1.561 |
--- | -1.476 |
Temp | -1.368 |
alach | -1.365 |
Token | Cycl |
Token ID | 28007 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
KS | +7.355 |
Nieto | +7.097 |
Moj | +7.007 |
Okin | +6.849 |
corrid | +6.795 |
Neg logit contributions | |
Ult | -2.987 |
uez | -2.938 |
--- | -2.492 |
alach | -2.404 |
utenberg | -2.383 |
Token | iste |
Token ID | 40833 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
KS | +1.829 |
ico | +1.730 |
Nieto | +1.615 |
ikan | +1.549 |
Moj | +1.525 |
Neg logit contributions | |
Ult | -7.998 |
uez | -7.788 |
--- | -7.486 |
alach | -7.345 |
20439 | -7.250 |
Token | FD |
Token ID | 30002 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
KS | +2.400 |
corrid | +2.358 |
Nieto | +2.299 |
Moj | +2.205 |
ico | +2.148 |
Neg logit contributions | |
Ult | -3.327 |
uez | -3.280 |
--- | -3.076 |
20439 | -2.955 |
alach | -2.944 |
Token | J |
Token ID | 41 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
KS | +2.975 |
Nieto | +2.712 |
Moj | +2.671 |
ico | +2.578 |
ikan | +2.304 |
Neg logit contributions | |
Ult | -9.602 |
uez | -9.514 |
alach | -9.178 |
utenberg | -9.001 |
--- | -8.828 |
Token | - |
Token ID | 532 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
corrid | +0.412 |
KS | +0.407 |
Nieto | +0.394 |
Moj | +0.383 |
Okin | +0.375 |
Neg logit contributions | |
Ult | -0.546 |
uez | -0.533 |
--- | -0.503 |
Temp | -0.473 |
alach | -0.473 |
Token | Big |
Token ID | 4403 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
KS | +3.824 |
corrid | +3.732 |
Nieto | +3.649 |
Moj | +3.590 |
Okin | +3.376 |
Neg logit contributions | |
Ult | -6.054 |
uez | -6.020 |
--- | -5.712 |
utenberg | -5.414 |
._ | -5.395 |
Token | Mat |
Token ID | 19044 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
KS | +1.801 |
Nieto | +1.759 |
corrid | +1.731 |
Moj | +1.674 |
Okin | +1.588 |
Neg logit contributions | |
uez | -4.640 |
Ult | -4.635 |
--- | -4.349 |
alach | -4.238 |
utenberg | -4.190 |
Token | ) |
Token ID | 8 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
KS | +0.813 |
corrid | +0.812 |
Nieto | +0.782 |
Moj | +0.759 |
Okin | +0.739 |
Neg logit contributions | |
Ult | -1.350 |
uez | -1.320 |
--- | -1.252 |
alach | -1.187 |
Temp | -1.183 |
Token | 66 |
Token ID | 2791 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
corrid | +1.897 |
KS | +1.853 |
Nieto | +1.767 |
Moj | +1.745 |
Okin | +1.685 |
Neg logit contributions | |
Ult | -2.473 |
uez | -2.406 |
--- | -2.241 |
utenberg | -2.155 |
20439 | -2.140 |
Token | IEEE |
Token ID | 40552 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
corrid | +1.198 |
KS | +1.179 |
Nieto | +1.137 |
Moj | +1.116 |
Okin | +1.087 |
Neg logit contributions | |
Ult | -1.412 |
uez | -1.373 |
--- | -1.287 |
alach | -1.222 |
Temp | -1.210 |
Token | 802 |
Token ID | 33121 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
KS | +1.488 |
corrid | +1.484 |
Nieto | +1.433 |
Moj | +1.410 |
Okin | +1.376 |
Neg logit contributions | |
Ult | -1.576 |
uez | -1.532 |
--- | -1.420 |
alach | -1.361 |
utenberg | -1.339 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
KS | +0.700 |
corrid | +0.685 |
Nieto | +0.674 |
Moj | +0.665 |
Okin | +0.647 |
Neg logit contributions | |
Ult | -0.709 |
uez | -0.695 |
--- | -0.639 |
alach | -0.613 |
Temp | -0.601 |
Token | 11 |
Token ID | 1157 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
KS | +2.024 |
corrid | +1.961 |
Nieto | +1.949 |
Moj | +1.895 |
Okin | +1.843 |
Neg logit contributions | |
Ult | -2.957 |
uez | -2.926 |
--- | -2.699 |
alach | -2.644 |
utenberg | -2.585 |
Token | b |
Token ID | 65 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
corrid | +1.326 |
KS | +1.296 |
Nieto | +1.263 |
Moj | +1.246 |
Okin | +1.213 |
Neg logit contributions | |
Ult | -0.975 |
uez | -0.947 |
--- | -0.869 |
alach | -0.801 |
Temp | -0.798 |
Token | gn |
Token ID | 4593 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
KS | +4.417 |
Nieto | +4.100 |
Moj | +4.095 |
ico | +4.068 |
Okin | +3.916 |
Neg logit contributions | |
Ult | -8.223 |
uez | -8.015 |
--- | -7.421 |
Temp | -7.302 |
Olymp | -7.254 |
Token | E |
Token ID | 412 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
corrid | +2.067 |
KS | +2.057 |
Nieto | +1.985 |
Moj | +1.961 |
Okin | +1.905 |
Neg logit contributions | |
Ult | -1.958 |
uez | -1.893 |
--- | -1.740 |
alach | -1.673 |
utenberg | -1.649 |
Token | SS |
Token ID | 5432 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Ult | +0.617 |
uez | +0.596 |
--- | +0.550 |
Temp | +0.499 |
alach | +0.495 |
Neg logit contributions | |
corrid | -0.958 |
KS | -0.939 |
Nieto | -0.918 |
Moj | -0.901 |
Okin | -0.888 |
Token | ID |
Token ID | 2389 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
KS | +2.197 |
Nieto | +2.110 |
corrid | +2.074 |
Moj | +2.036 |
ico | +2.017 |
Neg logit contributions | |
Ult | -3.287 |
uez | -3.233 |
alach | -2.987 |
--- | -2.986 |
utenberg | -2.899 |
Token | : |
Token ID | 25 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
Ult | +2.132 |
uez | +2.077 |
--- | +1.950 |
Temp | +1.787 |
alach | +1.750 |
Neg logit contributions | |
corrid | -2.645 |
KS | -2.570 |
Nieto | -2.522 |
Moj | -2.464 |
Okin | -2.432 |
Token | keys |
Token ID | 13083 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
Ult | +0.697 |
uez | +0.678 |
--- | +0.644 |
Temp | +0.612 |
alach | +0.606 |
Neg logit contributions | |
corrid | -0.411 |
KS | -0.402 |
Nieto | -0.386 |
Moj | -0.376 |
Okin | -0.367 |
Token | and |
Token ID | 290 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
corrid | +0.143 |
KS | +0.140 |
Nieto | +0.136 |
Moj | +0.134 |
Okin | +0.131 |
Neg logit contributions | |
Ult | -0.144 |
uez | -0.140 |
--- | -0.130 |
Temp | -0.122 |
alach | -0.121 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
corrid | +0.650 |
KS | +0.635 |
Nieto | +0.616 |
Moj | +0.607 |
Okin | +0.593 |
Neg logit contributions | |
Ult | -0.657 |
uez | -0.639 |
--- | -0.595 |
Temp | -0.558 |
alach | -0.552 |
Token | ratt |
Token ID | 27263 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Ult | +0.740 |
uez | +0.718 |
--- | +0.671 |
Temp | +0.618 |
alach | +0.612 |
Neg logit contributions | |
corrid | -0.884 |
KS | -0.863 |
Nieto | -0.842 |
Moj | -0.824 |
Okin | -0.811 |
Token | les |
Token ID | 829 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
corrid | +0.819 |
KS | +0.808 |
Nieto | +0.781 |
Moj | +0.775 |
ico | +0.763 |
Neg logit contributions | |
Ult | -0.634 |
uez | -0.592 |
--- | -0.556 |
Temp | -0.520 |
Olymp | -0.511 |
Token | n |
Token ID | 77 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
corrid | +0.313 |
KS | +0.306 |
Nieto | +0.296 |
Moj | +0.289 |
Okin | +0.281 |
Neg logit contributions | |
Ult | -0.431 |
uez | -0.420 |
--- | -0.395 |
Temp | -0.376 |
alach | -0.372 |
Token | akes |
Token ID | 1124 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
KS | +5.143 |
ico | +4.935 |
ikan | +4.767 |
Nieto | +4.726 |
Moj | +4.719 |
Neg logit contributions | |
Ult | -7.339 |
uez | -6.791 |
--- | -6.408 |
Temp | -6.397 |
20439 | -6.385 |
Token | , |
Token ID | 11 |
Feature activation | -7.53e-03 |
Pos logit contributions | |
corrid | +0.252 |
KS | +0.249 |
Nieto | +0.241 |
Moj | +0.237 |
Okin | +0.231 |
Neg logit contributions | |
Ult | -0.257 |
uez | -0.251 |
--- | -0.232 |
Temp | -0.219 |
alach | -0.217 |
Token | we |
Token ID | 356 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
corrid | +0.055 |
KS | +0.054 |
Nieto | +0.053 |
Moj | +0.052 |
Okin | +0.051 |
Neg logit contributions | |
Ult | -0.051 |
uez | -0.049 |
--- | -0.046 |
Temp | -0.043 |
alach | -0.042 |
Token | did |
Token ID | 750 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
Ult | +0.752 |
uez | +0.732 |
--- | +0.688 |
Temp | +0.638 |
alach | +0.632 |
Neg logit contributions | |
corrid | -0.770 |
KS | -0.750 |
Nieto | -0.731 |
Moj | -0.714 |
Okin | -0.702 |
Token | not |
Token ID | 407 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Ult | +0.475 |
uez | +0.461 |
--- | +0.430 |
Temp | +0.398 |
alach | +0.395 |
Neg logit contributions | |
corrid | -0.531 |
KS | -0.520 |
Nieto | -0.506 |
Moj | -0.495 |
Okin | -0.487 |
Token | Star |
Token ID | 2907 |
Feature activation | -1.51e-03 |
Pos logit contributions | |
Ult | +1.929 |
uez | +1.872 |
--- | +1.776 |
Temp | +1.649 |
alach | +1.631 |
Neg logit contributions | |
corrid | -1.801 |
KS | -1.738 |
Nieto | -1.700 |
Moj | -1.653 |
Okin | -1.628 |
Token | Trek |
Token ID | 12338 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
corrid | +0.011 |
KS | +0.011 |
Nieto | +0.011 |
Moj | +0.010 |
Okin | +0.010 |
Neg logit contributions | |
Ult | -0.010 |
uez | -0.010 |
--- | -0.009 |
Temp | -0.008 |
alach | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Ult | +0.223 |
uez | +0.218 |
--- | +0.204 |
Temp | +0.190 |
alach | +0.190 |
Neg logit contributions | |
corrid | -0.214 |
KS | -0.210 |
Nieto | -0.203 |
Moj | -0.199 |
Okin | -0.195 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
KS | +1.035 |
Nieto | +0.986 |
corrid | +0.974 |
Moj | +0.970 |
Okin | +0.937 |
Neg logit contributions | |
Ult | -1.536 |
uez | -1.513 |
--- | -1.405 |
alach | -1.365 |
Temp | -1.340 |
Token | The |
Token ID | 464 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
corrid | +0.852 |
KS | +0.851 |
Nieto | +0.818 |
Moj | +0.809 |
ico | +0.795 |
Neg logit contributions | |
uez | -0.791 |
Ult | -0.787 |
--- | -0.719 |
alach | -0.683 |
Olymp | -0.674 |
Token | Next |
Token ID | 7406 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
Ult | +0.270 |
uez | +0.264 |
--- | +0.248 |
Temp | +0.230 |
alach | +0.229 |
Neg logit contributions | |
corrid | -0.266 |
KS | -0.262 |
Nieto | -0.253 |
Moj | -0.249 |
Okin | -0.244 |
Token | Generation |
Token ID | 16588 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Ult | +3.520 |
uez | +3.343 |
--- | +3.195 |
Olymp | +2.960 |
Temp | +2.876 |
Neg logit contributions | |
corrid | -5.106 |
Nieto | -4.738 |
KS | -4.735 |
Moj | -4.586 |
Okin | -4.586 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Ult | +0.781 |
uez | +0.763 |
--- | +0.719 |
Temp | +0.673 |
alach | +0.671 |
Neg logit contributions | |
corrid | -0.655 |
KS | -0.640 |
Nieto | -0.620 |
Moj | -0.606 |
Okin | -0.593 |
Token |
|
Token ID | 198 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
KS | +0.874 |
Nieto | +0.836 |
corrid | +0.829 |
Moj | +0.820 |
Okin | +0.793 |
Neg logit contributions | |
Ult | -1.292 |
uez | -1.271 |
--- | -1.182 |
alach | -1.145 |
Temp | -1.126 |
Token | Please |
Token ID | 5492 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
KS | +0.669 |
corrid | +0.667 |
Nieto | +0.644 |
Moj | +0.636 |
ico | +0.624 |
Neg logit contributions | |
uez | -0.602 |
Ult | -0.598 |
--- | -0.549 |
alach | -0.520 |
utenberg | -0.511 |
Token | enter |
Token ID | 3802 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Ult | +2.408 |
uez | +2.351 |
--- | +2.223 |
Temp | +2.018 |
Olymp | +2.005 |
Neg logit contributions | |
corrid | -2.844 |
KS | -2.731 |
Nieto | -2.690 |
Moj | -2.612 |
Okin | -2.590 |
Token | pointer |
Token ID | 17562 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Ult | +0.616 |
uez | +0.596 |
--- | +0.554 |
Temp | +0.507 |
alach | +0.502 |
Neg logit contributions | |
corrid | -0.831 |
KS | -0.813 |
Nieto | -0.794 |
Moj | -0.778 |
Okin | -0.766 |
Token | + |
Token ID | 1343 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Ult | +0.867 |
uez | +0.841 |
--- | +0.786 |
Temp | +0.724 |
alach | +0.718 |
Neg logit contributions | |
corrid | -1.026 |
KS | -1.002 |
Nieto | -0.978 |
Moj | -0.958 |
Okin | -0.942 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Ult | +0.358 |
uez | +0.339 |
--- | +0.292 |
Temp | +0.247 |
alach | +0.245 |
Neg logit contributions | |
corrid | -1.126 |
KS | -1.115 |
Nieto | -1.095 |
Moj | -1.080 |
Okin | -1.066 |
Token | --+ |
Token ID | 44785 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Ult | +1.372 |
uez | +1.301 |
--- | +1.164 |
Temp | +0.952 |
._ | +0.925 |
Neg logit contributions | |
corrid | -4.337 |
KS | -4.217 |
Nieto | -4.143 |
Moj | -4.085 |
Okin | -4.032 |
Token | | |
Token ID | 930 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Ult | +2.165 |
uez | +2.099 |
--- | +2.000 |
Temp | +1.821 |
._ | +1.803 |
Neg logit contributions | |
corrid | -2.588 |
KS | -2.428 |
Nieto | -2.390 |
Moj | -2.320 |
Okin | -2.297 |
Token | [ |
Token ID | 685 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
Ult | +4.359 |
uez | +4.273 |
--- | +4.144 |
Temp | +3.863 |
._ | +3.848 |
Neg logit contributions | |
corrid | -2.336 |
KS | -2.105 |
Nieto | -2.064 |
Moj | -1.946 |
Okin | -1.931 |
Token | address |
Token ID | 21975 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Ult | +4.871 |
uez | +4.783 |
--- | +4.628 |
Temp | +4.232 |
._ | +4.184 |
Neg logit contributions | |
corrid | -4.604 |
KS | -4.218 |
Nieto | -4.204 |
Moj | -4.038 |
Okin | -3.969 |
Token | of |
Token ID | 286 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
Ult | +2.749 |
uez | +2.656 |
--- | +2.542 |
Temp | +2.261 |
._ | +2.253 |
Neg logit contributions | |
corrid | -4.208 |
KS | -3.869 |
Nieto | -3.812 |
Moj | -3.716 |
Okin | -3.694 |
Token | " |
Token ID | 366 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
Ult | +3.561 |
uez | +3.472 |
--- | +3.450 |
diff | +3.049 |
._ | +3.019 |
Neg logit contributions | |
corrid | -4.969 |
KS | -4.516 |
Nieto | -4.486 |
Okin | -4.334 |
Moj | -4.320 |
Token | pp |
Token ID | 381 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
Ult | +0.563 |
uez | +0.547 |
--- | +0.514 |
Temp | +0.474 |
alach | +0.470 |
Neg logit contributions | |
corrid | -0.623 |
KS | -0.607 |
Nieto | -0.593 |
Moj | -0.579 |
Okin | -0.569 |
Token | pr |
Token ID | 1050 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
corrid | +4.142 |
KS | +4.074 |
Nieto | +4.009 |
ico | +3.917 |
Moj | +3.852 |
Neg logit contributions | |
Ult | -4.226 |
uez | -4.102 |
--- | -3.717 |
Olymp | -3.623 |
20439 | -3.539 |
Token | и |
Token ID | 18849 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Ult | +0.596 |
uez | +0.577 |
--- | +0.538 |
Temp | +0.493 |
alach | +0.488 |
Neg logit contributions | |
corrid | -0.764 |
KS | -0.746 |
Nieto | -0.729 |
Moj | -0.714 |
Okin | -0.703 |
Token | м |
Token ID | 43108 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Ult | +0.743 |
uez | +0.721 |
--- | +0.671 |
Temp | +0.618 |
alach | +0.612 |
Neg logit contributions | |
corrid | -0.930 |
KS | -0.908 |
Nieto | -0.886 |
Moj | -0.868 |
Okin | -0.854 |
Token | � |
Token ID | 12466 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
Ult | +0.962 |
uez | +0.929 |
--- | +0.858 |
Temp | +0.774 |
alach | +0.765 |
Neg logit contributions | |
corrid | -1.543 |
KS | -1.508 |
Nieto | -1.477 |
Moj | -1.450 |
Okin | -1.429 |
Token | � |
Token ID | 122 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
corrid | +0.438 |
KS | +0.423 |
Nieto | +0.409 |
Moj | +0.396 |
Okin | +0.388 |
Neg logit contributions | |
Ult | -0.652 |
uez | -0.639 |
--- | -0.606 |
Temp | -0.571 |
alach | -0.567 |
Token | � |
Token ID | 140 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
Ult | +0.669 |
uez | +0.648 |
--- | +0.603 |
Temp | +0.552 |
alach | +0.547 |
Neg logit contributions | |
corrid | -0.884 |
KS | -0.863 |
Nieto | -0.844 |
Moj | -0.827 |
Okin | -0.814 |
Token | � |
Token ID | 123 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
Ult | +4.303 |
uez | +4.175 |
--- | +4.037 |
Temp | +3.799 |
Olymp | +3.762 |
Neg logit contributions | |
corrid | -2.258 |
KS | -2.216 |
Nieto | -2.105 |
Moj | -2.055 |
Okin | -1.981 |
Token | о� |
Token ID | 25443 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Ult | +4.768 |
uez | +4.583 |
--- | +4.375 |
._ | +3.924 |
Olymp | +3.887 |
Neg logit contributions | |
corrid | -7.215 |
KS | -6.986 |
Nieto | -6.844 |
Moj | -6.662 |
Okin | -6.653 |
Token | � |
Token ID | 110 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Ult | +3.123 |
uez | +3.043 |
--- | +2.899 |
Temp | +2.706 |
alach | +2.684 |
Neg logit contributions | |
corrid | -2.335 |
KS | -2.268 |
Nieto | -2.200 |
Moj | -2.141 |
Okin | -2.095 |
Token | е |
Token ID | 16843 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
Ult | +1.847 |
uez | +1.783 |
--- | +1.667 |
Temp | +1.504 |
Olymp | +1.494 |
Neg logit contributions | |
corrid | -2.639 |
KS | -2.571 |
Nieto | -2.517 |
Moj | -2.468 |
Okin | -2.431 |
Token | � |
Token ID | 141 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Ult | +3.957 |
uez | +3.768 |
--- | +3.590 |
._ | +3.200 |
Olymp | +3.179 |
Neg logit contributions | |
corrid | -5.949 |
KS | -5.708 |
Nieto | -5.619 |
Moj | -5.516 |
Okin | -5.469 |
Token | � |
Token ID | 231 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
corrid | +1.009 |
KS | +0.980 |
Nieto | +0.942 |
Moj | +0.905 |
Okin | +0.875 |
Neg logit contributions | |
Ult | -2.057 |
uez | -2.016 |
--- | -1.915 |
Temp | -1.829 |
alach | -1.812 |
Token | - |
Token ID | 12 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
Ult | +2.091 |
uez | +2.025 |
--- | +1.893 |
Temp | +1.721 |
Olymp | +1.706 |
Neg logit contributions | |
corrid | -2.849 |
KS | -2.767 |
Nieto | -2.718 |
Moj | -2.663 |
Okin | -2.633 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
Ult | +2.603 |
uez | +2.525 |
--- | +2.388 |
Temp | +2.188 |
Olymp | +2.148 |
Neg logit contributions | |
corrid | -3.007 |
KS | -2.882 |
Nieto | -2.836 |
Moj | -2.775 |
Okin | -2.722 |
Token | - |
Token ID | 12 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Ult | +3.311 |
uez | +3.243 |
--- | +3.039 |
Olymp | +2.726 |
Temp | +2.718 |
Neg logit contributions | |
corrid | -4.941 |
KS | -4.694 |
Nieto | -4.614 |
Moj | -4.563 |
Okin | -4.512 |
Token | 3 |
Token ID | 18 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
Ult | +0.973 |
uez | +0.948 |
--- | +0.891 |
Temp | +0.829 |
alach | +0.825 |
Neg logit contributions | |
corrid | -0.945 |
KS | -0.924 |
Nieto | -0.898 |
Moj | -0.876 |
Okin | -0.861 |
Token | - |
Token ID | 12 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
Ult | +4.101 |
uez | +4.023 |
--- | +3.813 |
Olymp | +3.429 |
Temp | +3.421 |
Neg logit contributions | |
corrid | -5.287 |
KS | -4.990 |
Nieto | -4.883 |
Moj | -4.840 |
Okin | -4.771 |
Token | 1 |
Token ID | 16 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
Ult | +0.212 |
uez | +0.208 |
--- | +0.195 |
alach | +0.184 |
20439 | +0.182 |
Neg logit contributions | |
corrid | -0.187 |
KS | -0.185 |
Nieto | -0.177 |
Moj | -0.172 |
ico | -0.171 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Ult | +4.138 |
uez | +4.066 |
--- | +3.862 |
Temp | +3.490 |
Olymp | +3.481 |
Neg logit contributions | |
corrid | -4.908 |
KS | -4.641 |
Nieto | -4.519 |
Moj | -4.493 |
Okin | -4.420 |
Token | with |
Token ID | 351 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Ult | +1.285 |
uez | +1.250 |
--- | +1.174 |
Temp | +1.082 |
alach | +1.071 |
Neg logit contributions | |
corrid | -1.435 |
KS | -1.391 |
Nieto | -1.359 |
Moj | -1.330 |
Okin | -1.308 |
Token | width |
Token ID | 9647 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
Ult | +1.583 |
uez | +1.542 |
--- | +1.451 |
Temp | +1.347 |
alach | +1.336 |
Neg logit contributions | |
corrid | -1.561 |
KS | -1.517 |
Nieto | -1.478 |
Moj | -1.444 |
Okin | -1.419 |
Token | on |
Token ID | 319 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Ult | +3.320 |
uez | +3.254 |
--- | +3.098 |
Olymp | +2.815 |
Temp | +2.798 |
Neg logit contributions | |
corrid | -3.806 |
KS | -3.642 |
Nieto | -3.560 |
Moj | -3.491 |
Okin | -3.456 |
Token | both |
Token ID | 1111 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Ult | +1.710 |
uez | +1.664 |
--- | +1.558 |
Temp | +1.427 |
Olymp | +1.418 |
Neg logit contributions | |
corrid | -2.029 |
KS | -1.958 |
Nieto | -1.919 |
Moj | -1.884 |
Okin | -1.855 |
Token | old |
Token ID | 1468 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Ult | +0.041 |
uez | +0.039 |
--- | +0.036 |
Temp | +0.034 |
alach | +0.033 |
Neg logit contributions | |
corrid | -0.051 |
KS | -0.051 |
Nieto | -0.050 |
Moj | -0.049 |
Okin | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Ult | +0.832 |
uez | +0.810 |
--- | +0.762 |
Temp | +0.709 |
alach | +0.704 |
Neg logit contributions | |
corrid | -0.801 |
KS | -0.781 |
Nieto | -0.760 |
Moj | -0.742 |
Okin | -0.729 |
Token | once |
Token ID | 1752 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
Ult | +1.197 |
uez | +1.162 |
--- | +1.074 |
Temp | +0.968 |
alach | +0.957 |
Neg logit contributions | |
corrid | -1.840 |
KS | -1.785 |
Nieto | -1.750 |
Moj | -1.718 |
Okin | -1.697 |
Token | I |
Token ID | 314 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
Ult | +0.451 |
uez | +0.441 |
--- | +0.418 |
Temp | +0.393 |
alach | +0.391 |
Neg logit contributions | |
corrid | -0.324 |
KS | -0.315 |
Nieto | -0.305 |
Moj | -0.297 |
Okin | -0.290 |
Token | turn |
Token ID | 1210 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
KS | +2.067 |
corrid | +1.998 |
Nieto | +1.975 |
Moj | +1.958 |
Okin | +1.894 |
Neg logit contributions | |
Ult | -1.660 |
uez | -1.580 |
--- | -1.471 |
alach | -1.400 |
Temp | -1.386 |
Token | AA |
Token ID | 15923 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
Ult | +1.443 |
uez | +1.420 |
--- | +1.362 |
Temp | +1.285 |
Olymp | +1.273 |
Neg logit contributions | |
corrid | -0.728 |
KS | -0.673 |
Nieto | -0.653 |
Moj | -0.626 |
Okin | -0.612 |
Token | on |
Token ID | 319 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Ult | +3.576 |
uez | +3.469 |
--- | +3.330 |
Temp | +2.900 |
._ | +2.868 |
Neg logit contributions | |
corrid | -6.039 |
KS | -5.460 |
Nieto | -5.448 |
Okin | -5.302 |
Moj | -5.267 |
Token | things |
Token ID | 1243 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Ult | +1.376 |
uez | +1.347 |
--- | +1.285 |
Temp | +1.197 |
alach | +1.187 |
Neg logit contributions | |
corrid | -1.022 |
KS | -0.973 |
Nieto | -0.949 |
Moj | -0.919 |
Okin | -0.904 |
Token | slow |
Token ID | 3105 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
KS | +0.790 |
corrid | +0.769 |
Nieto | +0.760 |
Moj | +0.748 |
ico | +0.725 |
Neg logit contributions | |
Ult | -0.618 |
uez | -0.588 |
--- | -0.526 |
alach | -0.503 |
20439 | -0.502 |
Token | down |
Token ID | 866 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
KS | +1.252 |
corrid | +1.217 |
Nieto | +1.198 |
Moj | +1.185 |
Okin | +1.145 |
Neg logit contributions | |
Ult | -0.996 |
uez | -0.953 |
--- | -0.866 |
alach | -0.834 |
20439 | -0.830 |
Token | quite |
Token ID | 2407 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
KS | +0.801 |
corrid | +0.796 |
Nieto | +0.773 |
Moj | +0.762 |
Okin | +0.747 |
Neg logit contributions | |
Ult | -0.706 |
uez | -0.691 |
--- | -0.623 |
alach | -0.596 |
Temp | -0.594 |
Token | and |
Token ID | 290 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
corrid | +0.626 |
KS | +0.613 |
Nieto | +0.598 |
Moj | +0.588 |
Okin | +0.579 |
Neg logit contributions | |
Ult | -0.462 |
uez | -0.448 |
--- | -0.411 |
Temp | -0.380 |
alach | -0.377 |
Token | universally |
Token ID | 26208 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
corrid | +1.731 |
KS | +1.701 |
Nieto | +1.640 |
Moj | +1.613 |
Okin | +1.595 |
Neg logit contributions | |
Ult | -1.689 |
uez | -1.647 |
--- | -1.493 |
Temp | -1.434 |
utenberg | -1.413 |
Token | true |
Token ID | 2081 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Ult | +0.049 |
uez | +0.047 |
--- | +0.044 |
Temp | +0.040 |
alach | +0.040 |
Neg logit contributions | |
corrid | -0.065 |
KS | -0.064 |
Nieto | -0.062 |
Moj | -0.061 |
Okin | -0.060 |
Token | ' |
Token ID | 6 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
corrid | +1.849 |
KS | +1.817 |
Nieto | +1.754 |
Moj | +1.713 |
Okin | +1.676 |
Neg logit contributions | |
Ult | -2.412 |
uez | -2.335 |
--- | -2.185 |
Temp | -2.088 |
alach | -2.075 |
Token | under |
Token ID | 739 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
corrid | +1.185 |
KS | +1.173 |
Nieto | +1.135 |
Moj | +1.108 |
Okin | +1.087 |
Neg logit contributions | |
Ult | -1.257 |
uez | -1.218 |
--- | -1.123 |
Temp | -1.072 |
alach | -1.065 |
Token | some |
Token ID | 617 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
corrid | +0.149 |
KS | +0.146 |
Nieto | +0.143 |
Moj | +0.140 |
Okin | +0.137 |
Neg logit contributions | |
Ult | -0.127 |
uez | -0.124 |
--- | -0.115 |
Temp | -0.107 |
alach | -0.105 |
Token | interpretation |
Token ID | 10794 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
Ult | +0.357 |
uez | +0.347 |
--- | +0.323 |
Temp | +0.297 |
alach | +0.295 |
Neg logit contributions | |
corrid | -0.446 |
KS | -0.436 |
Nieto | -0.425 |
Moj | -0.417 |
Okin | -0.410 |
Token | of |
Token ID | 286 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
corrid | +0.477 |
KS | +0.468 |
Nieto | +0.456 |
Moj | +0.448 |
Okin | +0.439 |
Neg logit contributions | |
Ult | -0.409 |
uez | -0.396 |
--- | -0.367 |
Temp | -0.342 |
alach | -0.340 |
Token | these |
Token ID | 777 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
corrid | +1.830 |
KS | +1.807 |
Nieto | +1.754 |
Moj | +1.716 |
Okin | +1.693 |
Neg logit contributions | |
Ult | -1.759 |
uez | -1.717 |
--- | -1.594 |
Temp | -1.503 |
alach | -1.484 |
Token | terms |
Token ID | 2846 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
corrid | +1.112 |
KS | +1.095 |
Nieto | +1.062 |
Moj | +1.042 |
Okin | +1.028 |
Neg logit contributions | |
Ult | -0.915 |
uez | -0.888 |
--- | -0.824 |
Temp | -0.769 |
alach | -0.764 |
Token | ( |
Token ID | 357 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
corrid | +0.824 |
KS | +0.817 |
Nieto | +0.791 |
Moj | +0.775 |
Okin | +0.760 |
Neg logit contributions | |
Ult | -0.847 |
uez | -0.816 |
--- | -0.756 |
Temp | -0.719 |
alach | -0.713 |
Token | o |
Token ID | 78 |
Feature activation | +2.97e-03 |
Pos logit contributions | |
Ult | +0.311 |
uez | +0.302 |
--- | +0.283 |
Temp | +0.262 |
alach | +0.260 |
Neg logit contributions | |
corrid | -0.334 |
KS | -0.327 |
Nieto | -0.318 |
Moj | -0.312 |
Okin | -0.306 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
Ult | +0.020 |
uez | +0.020 |
--- | +0.018 |
Temp | +0.017 |
alach | +0.017 |
Neg logit contributions | |
corrid | -0.021 |
KS | -0.021 |
Nieto | -0.020 |
Moj | -0.020 |
Okin | -0.020 |
Token | or |
Token ID | 393 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
corrid | +0.225 |
KS | +0.220 |
Nieto | +0.214 |
Moj | +0.209 |
Okin | +0.205 |
Neg logit contributions | |
Ult | -0.220 |
uez | -0.214 |
--- | -0.200 |
Temp | -0.186 |
alach | -0.185 |
Token | w |
Token ID | 266 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
corrid | +0.469 |
KS | +0.459 |
Nieto | +0.444 |
Moj | +0.436 |
Okin | +0.428 |
Neg logit contributions | |
Ult | -0.478 |
uez | -0.463 |
--- | -0.436 |
Temp | -0.406 |
alach | -0.405 |
Token | lan |
Token ID | 9620 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
corrid | +0.234 |
KS | +0.228 |
Nieto | +0.222 |
Moj | +0.217 |
Okin | +0.213 |
Neg logit contributions | |
Ult | -0.222 |
uez | -0.216 |
--- | -0.202 |
Temp | -0.188 |
alach | -0.186 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Ult | +1.644 |
uez | +1.587 |
--- | +1.488 |
Temp | +1.355 |
._ | +1.331 |
Neg logit contributions | |
corrid | -2.177 |
KS | -2.123 |
Nieto | -2.087 |
Moj | -2.036 |
Okin | -2.016 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Ult | +0.801 |
uez | +0.780 |
--- | +0.734 |
Temp | +0.679 |
alach | +0.672 |
Neg logit contributions | |
corrid | -0.824 |
KS | -0.801 |
Nieto | -0.781 |
Moj | -0.763 |
Okin | -0.750 |
Token | Mine |
Token ID | 11517 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
corrid | +1.362 |
KS | +1.339 |
Nieto | +1.299 |
Moj | +1.274 |
Okin | +1.245 |
Neg logit contributions | |
Ult | -1.564 |
uez | -1.523 |
--- | -1.432 |
alach | -1.341 |
Temp | -1.340 |
Token | just |
Token ID | 655 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
corrid | +1.064 |
KS | +1.046 |
Nieto | +1.021 |
Moj | +1.001 |
Okin | +0.977 |
Neg logit contributions | |
Ult | -0.953 |
uez | -0.921 |
--- | -0.857 |
alach | -0.798 |
Temp | -0.795 |
Token | happens |
Token ID | 4325 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
corrid | +1.008 |
KS | +0.993 |
Nieto | +0.967 |
Moj | +0.950 |
Okin | +0.930 |
Neg logit contributions | |
Ult | -0.847 |
uez | -0.816 |
--- | -0.759 |
alach | -0.706 |
Temp | -0.703 |
Token | to |
Token ID | 284 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
corrid | +1.098 |
KS | +1.062 |
Nieto | +1.035 |
Moj | +1.009 |
Okin | +0.985 |
Neg logit contributions | |
Ult | -1.276 |
uez | -1.241 |
--- | -1.168 |
Temp | -1.095 |
alach | -1.094 |
Token | social |
Token ID | 14557 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
corrid | +0.102 |
KS | +0.100 |
Nieto | +0.098 |
Moj | +0.096 |
Okin | +0.094 |
Neg logit contributions | |
Ult | -0.092 |
uez | -0.090 |
--- | -0.084 |
Temp | -0.078 |
alach | -0.077 |
Token | probation |
Token ID | 19660 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
corrid | +0.501 |
KS | +0.487 |
Nieto | +0.469 |
Moj | +0.459 |
Okin | +0.449 |
Neg logit contributions | |
Ult | -0.645 |
uez | -0.632 |
--- | -0.589 |
20439 | -0.560 |
Temp | -0.557 |
Token | � |
Token ID | 447 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
Ult | +0.585 |
uez | +0.569 |
--- | +0.535 |
Temp | +0.498 |
alach | +0.494 |
Neg logit contributions | |
corrid | -0.574 |
KS | -0.559 |
Nieto | -0.545 |
Moj | -0.532 |
Okin | -0.522 |
Token | � |
Token ID | 251 |
Feature activation | -9.76e-02 |
Pos logit contributions | |
Ult | +0.482 |
uez | +0.471 |
--- | +0.445 |
Temp | +0.421 |
alach | +0.418 |
Neg logit contributions | |
corrid | -0.318 |
KS | -0.306 |
Nieto | -0.297 |
Moj | -0.287 |
Okin | -0.280 |
Token | until |
Token ID | 1566 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
corrid | +0.683 |
KS | +0.670 |
Nieto | +0.653 |
Moj | +0.638 |
Okin | +0.625 |
Neg logit contributions | |
Ult | -0.685 |
uez | -0.666 |
--- | -0.618 |
Temp | -0.580 |
alach | -0.575 |
Token | March |
Token ID | 2805 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Ult | +1.337 |
uez | +1.304 |
--- | +1.233 |
Temp | +1.135 |
Olymp | +1.131 |
Neg logit contributions | |
corrid | -1.363 |
KS | -1.315 |
Nieto | -1.282 |
Moj | -1.251 |
Okin | -1.232 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Ult | +0.800 |
uez | +0.780 |
--- | +0.736 |
Temp | +0.686 |
alach | +0.681 |
Neg logit contributions | |
corrid | -0.718 |
KS | -0.698 |
Nieto | -0.679 |
Moj | -0.662 |
Okin | -0.650 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Ult | +0.769 |
uez | +0.748 |
--- | +0.703 |
Temp | +0.650 |
alach | +0.645 |
Neg logit contributions | |
corrid | -0.815 |
KS | -0.794 |
Nieto | -0.774 |
Moj | -0.757 |
Okin | -0.744 |
Token | and |
Token ID | 290 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
corrid | +0.846 |
KS | +0.841 |
Nieto | +0.819 |
Moj | +0.802 |
Okin | +0.780 |
Neg logit contributions | |
Ult | -0.844 |
uez | -0.819 |
--- | -0.757 |
Temp | -0.714 |
alach | -0.712 |
Token | must |
Token ID | 1276 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
corrid | +1.310 |
KS | +1.293 |
Nieto | +1.262 |
Moj | +1.232 |
Okin | +1.210 |
Neg logit contributions | |
Ult | -1.226 |
uez | -1.186 |
--- | -1.104 |
Temp | -1.034 |
alach | -1.032 |
Token | participate |
Token ID | 8277 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Ult | +0.492 |
uez | +0.476 |
--- | +0.442 |
Temp | +0.413 |
alach | +0.408 |
Neg logit contributions | |
corrid | -0.555 |
KS | -0.548 |
Nieto | -0.533 |
Moj | -0.522 |
Okin | -0.512 |
Token | to |
Token ID | 284 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
corrid | +0.258 |
KS | +0.253 |
Nieto | +0.245 |
Moj | +0.240 |
Okin | +0.235 |
Neg logit contributions | |
Ult | -0.265 |
uez | -0.258 |
--- | -0.241 |
Temp | -0.226 |
alach | -0.225 |
Token | fit |
Token ID | 4197 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Ult | +0.224 |
uez | +0.216 |
--- | +0.200 |
Temp | +0.188 |
alach | +0.185 |
Neg logit contributions | |
corrid | -0.262 |
KS | -0.259 |
Nieto | -0.251 |
Moj | -0.247 |
Okin | -0.242 |
Token | in |
Token ID | 287 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
corrid | +1.631 |
KS | +1.602 |
Nieto | +1.564 |
Moj | +1.535 |
Okin | +1.492 |
Neg logit contributions | |
Ult | -1.521 |
uez | -1.468 |
--- | -1.349 |
Temp | -1.279 |
20439 | -1.270 |
Token | . |
Token ID | 13 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
corrid | +1.645 |
KS | +1.631 |
Nieto | +1.582 |
Moj | +1.559 |
Okin | +1.516 |
Neg logit contributions | |
Ult | -1.726 |
uez | -1.664 |
--- | -1.528 |
Temp | -1.467 |
alach | -1.447 |
Token | However |
Token ID | 2102 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
corrid | +0.217 |
KS | +0.213 |
Nieto | +0.207 |
Moj | +0.202 |
Okin | +0.198 |
Neg logit contributions | |
Ult | -0.254 |
uez | -0.248 |
--- | -0.234 |
Temp | -0.219 |
alach | -0.218 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
corrid | +0.616 |
KS | +0.602 |
Nieto | +0.586 |
Moj | +0.570 |
Okin | +0.559 |
Neg logit contributions | |
Ult | -0.648 |
uez | -0.624 |
--- | -0.582 |
Temp | -0.552 |
alach | -0.546 |
Token | gender |
Token ID | 5279 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Ult | +0.816 |
uez | +0.791 |
--- | +0.740 |
Temp | +0.685 |
alach | +0.679 |
Neg logit contributions | |
corrid | -0.925 |
KS | -0.903 |
Nieto | -0.881 |
Moj | -0.862 |
Okin | -0.848 |
Token | non |
Token ID | 1729 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
corrid | +1.301 |
KS | +1.283 |
Nieto | +1.243 |
Moj | +1.217 |
Okin | +1.193 |
Neg logit contributions | |
Ult | -1.357 |
uez | -1.295 |
--- | -1.206 |
Temp | -1.152 |
alach | -1.150 |
Token | con |
Token ID | 1102 |
Feature activation | -9.66e-03 |
Pos logit contributions | |
Ult | +2.587 |
uez | +2.522 |
--- | +2.394 |
Temp | +2.215 |
alach | +2.201 |
Neg logit contributions | |
corrid | -2.343 |
KS | -2.271 |
Nieto | -2.213 |
Moj | -2.155 |
Okin | -2.118 |
Token | forming |
Token ID | 15464 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
corrid | +0.082 |
KS | +0.081 |
Nieto | +0.078 |
Moj | +0.077 |
Okin | +0.076 |
Neg logit contributions | |
Ult | -0.053 |
uez | -0.051 |
--- | -0.047 |
Temp | -0.043 |
alach | -0.042 |
Token | ( |
Token ID | 357 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
Ult | +0.549 |
uez | +0.532 |
--- | +0.498 |
Temp | +0.460 |
alach | +0.456 |
Neg logit contributions | |
corrid | -0.639 |
KS | -0.624 |
Nieto | -0.609 |
Moj | -0.596 |
Okin | -0.586 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
corrid | +1.048 |
KS | +1.030 |
Nieto | +1.005 |
Moj | +0.989 |
Okin | +0.979 |
Neg logit contributions | |
Ult | -1.000 |
uez | -0.964 |
--- | -0.899 |
Temp | -0.845 |
20439 | -0.839 |
Token | Mong |
Token ID | 18428 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
corrid | +1.164 |
KS | +1.144 |
Nieto | +1.117 |
Moj | +1.104 |
Okin | +1.091 |
Neg logit contributions | |
Ult | -0.935 |
uez | -0.902 |
--- | -0.835 |
Temp | -0.780 |
20439 | -0.772 |
Token | ols |
Token ID | 10220 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
corrid | +0.039 |
KS | +0.038 |
Nieto | +0.037 |
Moj | +0.036 |
Okin | +0.035 |
Neg logit contributions | |
Ult | -0.072 |
uez | -0.070 |
--- | -0.067 |
Temp | -0.064 |
20439 | -0.064 |
Token | ( |
Token ID | 357 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
corrid | +0.568 |
KS | +0.558 |
Nieto | +0.544 |
Moj | +0.533 |
Okin | +0.526 |
Neg logit contributions | |
Ult | -0.511 |
uez | -0.495 |
--- | -0.457 |
Temp | -0.430 |
20439 | -0.423 |
Token | un |
Token ID | 403 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
corrid | +1.330 |
KS | +1.315 |
Nieto | +1.270 |
Moj | +1.256 |
Okin | +1.236 |
Neg logit contributions | |
Ult | -1.197 |
uez | -1.185 |
--- | -1.095 |
20439 | -1.008 |
alach | -1.007 |
Token | like |
Token ID | 2339 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
Ult | +1.756 |
uez | +1.691 |
--- | +1.599 |
Temp | +1.451 |
alach | +1.445 |
Neg logit contributions | |
corrid | -2.291 |
KS | -2.207 |
Nieto | -2.169 |
Moj | -2.114 |
Okin | -2.076 |
Token | their |
Token ID | 511 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Ult | +3.027 |
uez | +2.948 |
--- | +2.795 |
Olymp | +2.562 |
Temp | +2.547 |
Neg logit contributions | |
corrid | -3.405 |
KS | -3.268 |
Nieto | -3.212 |
Moj | -3.121 |
Okin | -3.059 |
Token | southern |
Token ID | 8372 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Ult | +1.925 |
uez | +1.874 |
--- | +1.769 |
Olymp | +1.627 |
Temp | +1.626 |
Neg logit contributions | |
corrid | -2.084 |
KS | -2.014 |
Nieto | -1.972 |
Moj | -1.914 |
Okin | -1.879 |
Token | neighbours |
Token ID | 23788 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Ult | +1.283 |
uez | +1.248 |
--- | +1.170 |
Temp | +1.072 |
Olymp | +1.064 |
Neg logit contributions | |
corrid | -1.523 |
KS | -1.478 |
Nieto | -1.447 |
Moj | -1.411 |
Okin | -1.388 |
Token | , |
Token ID | 11 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
Ult | +1.000 |
uez | +0.977 |
--- | +0.927 |
Temp | +0.870 |
alach | +0.864 |
Neg logit contributions | |
corrid | -0.721 |
KS | -0.698 |
Nieto | -0.676 |
Moj | -0.657 |
Okin | -0.643 |
Token | the |
Token ID | 262 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
Ult | +0.155 |
uez | +0.150 |
--- | +0.140 |
Temp | +0.131 |
alach | +0.129 |
Neg logit contributions | |
corrid | -0.169 |
KS | -0.167 |
Nieto | -0.161 |
Moj | -0.159 |
Okin | -0.157 |
Token | a |
Token ID | 257 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Ult | +0.045 |
uez | +0.044 |
--- | +0.041 |
Temp | +0.038 |
alach | +0.038 |
Neg logit contributions | |
corrid | -0.051 |
KS | -0.049 |
Nieto | -0.048 |
Moj | -0.047 |
Okin | -0.046 |
Token | lack |
Token ID | 3092 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
Ult | +1.424 |
uez | +1.385 |
--- | +1.298 |
Temp | +1.182 |
alach | +1.173 |
Neg logit contributions | |
corrid | -1.796 |
KS | -1.746 |
Nieto | -1.710 |
Moj | -1.673 |
Okin | -1.654 |
Token | of |
Token ID | 286 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
corrid | +0.725 |
KS | +0.716 |
Nieto | +0.699 |
Moj | +0.684 |
Okin | +0.673 |
Neg logit contributions | |
Ult | -0.587 |
uez | -0.571 |
--- | -0.529 |
Temp | -0.488 |
alach | -0.485 |
Token | accountability |
Token ID | 18241 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Ult | +1.459 |
uez | +1.417 |
--- | +1.329 |
Temp | +1.210 |
Olymp | +1.205 |
Neg logit contributions | |
corrid | -1.845 |
KS | -1.792 |
Nieto | -1.752 |
Moj | -1.716 |
Okin | -1.691 |
Token | from |
Token ID | 422 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
corrid | +0.974 |
KS | +0.958 |
Nieto | +0.935 |
Moj | +0.911 |
Okin | +0.892 |
Neg logit contributions | |
Ult | -1.022 |
uez | -0.993 |
--- | -0.921 |
Temp | -0.868 |
alach | -0.865 |
Token | regulatory |
Token ID | 11344 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
corrid | +0.017 |
KS | +0.017 |
Nieto | +0.017 |
Moj | +0.016 |
Okin | +0.016 |
Neg logit contributions | |
Ult | -0.014 |
uez | -0.014 |
--- | -0.013 |
Temp | -0.012 |
alach | -0.012 |
Token | bodies |
Token ID | 5920 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
corrid | +0.674 |
KS | +0.661 |
Nieto | +0.645 |
Moj | +0.634 |
Okin | +0.621 |
Neg logit contributions | |
Ult | -0.552 |
uez | -0.534 |
--- | -0.495 |
alach | -0.461 |
Temp | -0.460 |
Token | creating |
Token ID | 4441 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
corrid | +0.504 |
KS | +0.494 |
Nieto | +0.482 |
Moj | +0.470 |
Okin | +0.460 |
Neg logit contributions | |
Ult | -0.504 |
uez | -0.490 |
--- | -0.456 |
Temp | -0.428 |
alach | -0.425 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
corrid | +0.170 |
KS | +0.167 |
Nieto | +0.162 |
Moj | +0.159 |
Okin | +0.155 |
Neg logit contributions | |
Ult | -0.158 |
uez | -0.152 |
--- | -0.142 |
Temp | -0.132 |
alach | -0.131 |
Token | black |
Token ID | 2042 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Ult | +0.083 |
uez | +0.081 |
--- | +0.076 |
Temp | +0.070 |
alach | +0.070 |
Neg logit contributions | |
corrid | -0.095 |
KS | -0.093 |
Nieto | -0.090 |
Moj | -0.088 |
Okin | -0.087 |
Token | lists |
Token ID | 20713 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
corrid | +1.012 |
KS | +0.983 |
Nieto | +0.952 |
Moj | +0.930 |
Okin | +0.906 |
Neg logit contributions | |
Ult | -1.124 |
uez | -1.095 |
--- | -1.030 |
Temp | -0.964 |
alach | -0.959 |
Token | Best |
Token ID | 13014 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
corrid | +0.125 |
KS | +0.123 |
Nieto | +0.119 |
Moj | +0.116 |
Okin | +0.114 |
Neg logit contributions | |
Ult | -0.129 |
uez | -0.126 |
--- | -0.118 |
Temp | -0.109 |
alach | -0.109 |
Token |
|
Token ID | 198 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
corrid | +0.380 |
KS | +0.372 |
Nieto | +0.361 |
Moj | +0.353 |
Okin | +0.347 |
Neg logit contributions | |
Ult | -0.417 |
uez | -0.409 |
--- | -0.385 |
Temp | -0.357 |
alach | -0.357 |
Token |
|
Token ID | 198 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
KS | +0.209 |
corrid | +0.206 |
Nieto | +0.201 |
Moj | +0.196 |
Okin | +0.191 |
Neg logit contributions | |
Ult | -0.296 |
uez | -0.290 |
--- | -0.273 |
alach | -0.259 |
Temp | -0.258 |
Token | Tree |
Token ID | 27660 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
corrid | +0.309 |
KS | +0.303 |
Nieto | +0.294 |
Moj | +0.289 |
Okin | +0.284 |
Neg logit contributions | |
Ult | -0.297 |
uez | -0.291 |
--- | -0.272 |
alach | -0.252 |
Temp | -0.251 |
Token |
|
Token ID | 198 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
Ult | +0.049 |
uez | +0.048 |
--- | +0.045 |
alach | +0.042 |
Temp | +0.042 |
Neg logit contributions | |
corrid | -0.045 |
KS | -0.044 |
Nieto | -0.043 |
Moj | -0.042 |
Okin | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
KS | +0.401 |
corrid | +0.396 |
Nieto | +0.386 |
Moj | +0.378 |
Okin | +0.368 |
Neg logit contributions | |
Ult | -0.569 |
uez | -0.558 |
--- | -0.524 |
alach | -0.498 |
Temp | -0.495 |
Token | k |
Token ID | 74 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
corrid | +0.661 |
KS | +0.649 |
Nieto | +0.629 |
Moj | +0.618 |
Okin | +0.607 |
Neg logit contributions | |
Ult | -0.633 |
uez | -0.622 |
--- | -0.581 |
alach | -0.538 |
Olymp | -0.535 |
Token | As |
Token ID | 1722 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
Ult | +0.886 |
uez | +0.862 |
--- | +0.811 |
Temp | +0.754 |
alach | +0.747 |
Neg logit contributions | |
corrid | -0.881 |
KS | -0.852 |
Nieto | -0.832 |
Moj | -0.810 |
Okin | -0.797 |
Token | yu |
Token ID | 24767 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Ult | +2.135 |
uez | +2.072 |
--- | +1.956 |
Temp | +1.825 |
alach | +1.797 |
Neg logit contributions | |
corrid | -2.020 |
KS | -1.944 |
Nieto | -1.901 |
Moj | -1.852 |
Okin | -1.816 |
Token |
|
Token ID | 198 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
Ult | +0.857 |
uez | +0.835 |
--- | +0.789 |
Temp | +0.738 |
alach | +0.729 |
Neg logit contributions | |
corrid | -0.724 |
KS | -0.697 |
Nieto | -0.681 |
Moj | -0.660 |
Okin | -0.648 |
Token |
|
Token ID | 198 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
KS | +0.163 |
corrid | +0.162 |
Nieto | +0.157 |
Moj | +0.153 |
Okin | +0.150 |
Neg logit contributions | |
Ult | -0.229 |
uez | -0.224 |
--- | -0.211 |
alach | -0.199 |
Temp | -0.199 |
Token | adult |
Token ID | 4044 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
corrid | +0.127 |
KS | +0.124 |
Nieto | +0.120 |
Moj | +0.118 |
Okin | +0.116 |
Neg logit contributions | |
Ult | -0.127 |
uez | -0.124 |
--- | -0.116 |
Temp | -0.108 |
alach | -0.107 |
Token | Buddh |
Token ID | 20921 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Ult | +1.721 |
uez | +1.679 |
--- | +1.590 |
Temp | +1.463 |
Olymp | +1.461 |
Neg logit contributions | |
corrid | -1.719 |
KS | -1.663 |
Nieto | -1.620 |
Moj | -1.583 |
Okin | -1.556 |
Token | ists |
Token ID | 1023 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
corrid | +0.622 |
KS | +0.603 |
Nieto | +0.581 |
Moj | +0.566 |
Okin | +0.556 |
Neg logit contributions | |
Ult | -0.924 |
uez | -0.901 |
--- | -0.854 |
Temp | -0.803 |
alach | -0.798 |
Token | in |
Token ID | 287 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
Ult | +0.405 |
uez | +0.394 |
--- | +0.371 |
Temp | +0.344 |
alach | +0.341 |
Neg logit contributions | |
corrid | -0.407 |
KS | -0.396 |
Nieto | -0.386 |
Moj | -0.377 |
Okin | -0.370 |
Token | Colorado |
Token ID | 7492 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
corrid | +0.609 |
KS | +0.602 |
Nieto | +0.581 |
Moj | +0.570 |
Okin | +0.553 |
Neg logit contributions | |
Ult | -0.675 |
uez | -0.659 |
--- | -0.615 |
Temp | -0.581 |
20439 | -0.574 |
Token | , |
Token ID | 11 |
Feature activation | +6.90e-04 |
Pos logit contributions | |
corrid | +0.299 |
KS | +0.291 |
Nieto | +0.284 |
Moj | +0.277 |
Okin | +0.271 |
Neg logit contributions | |
Ult | -0.332 |
uez | -0.324 |
--- | -0.304 |
Temp | -0.285 |
alach | -0.283 |
Token | according |
Token ID | 1864 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Ult | +0.005 |
uez | +0.005 |
--- | +0.004 |
Temp | +0.004 |
alach | +0.004 |
Neg logit contributions | |
corrid | -0.005 |
KS | -0.005 |
Nieto | -0.005 |
Moj | -0.004 |
Okin | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
KS | +1.295 |
corrid | +1.259 |
Nieto | +1.247 |
Moj | +1.218 |
Okin | +1.183 |
Neg logit contributions | |
Ult | -1.610 |
uez | -1.580 |
--- | -1.470 |
alach | -1.403 |
Temp | -1.391 |
Token | Pew |
Token ID | 21805 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
corrid | +0.474 |
KS | +0.465 |
Nieto | +0.452 |
Moj | +0.443 |
Okin | +0.432 |
Neg logit contributions | |
Ult | -0.470 |
uez | -0.457 |
--- | -0.427 |
Temp | -0.399 |
alach | -0.394 |
Token | survey |
Token ID | 5526 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
Ult | +1.862 |
uez | +1.816 |
--- | +1.740 |
Temp | +1.611 |
alach | +1.588 |
Neg logit contributions | |
corrid | -1.704 |
KS | -1.642 |
Nieto | -1.596 |
Moj | -1.554 |
Okin | -1.533 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
corrid | +0.440 |
KS | +0.430 |
Nieto | +0.420 |
Moj | +0.409 |
Okin | +0.400 |
Neg logit contributions | |
Ult | -0.479 |
uez | -0.468 |
--- | -0.437 |
Temp | -0.410 |
alach | -0.406 |
Token | Japan |
Token ID | 2869 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
corrid | +0.817 |
KS | +0.795 |
Nieto | +0.763 |
Moj | +0.737 |
Okin | +0.728 |
Neg logit contributions | |
Ult | -1.547 |
uez | -1.516 |
--- | -1.439 |
Temp | -1.374 |
alach | -1.361 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
corrid | +0.236 |
KS | +0.230 |
Nieto | +0.226 |
Moj | +0.220 |
Okin | +0.216 |
Neg logit contributions | |
Ult | -0.235 |
uez | -0.229 |
--- | -0.214 |
Temp | -0.200 |
alach | -0.198 |
Token | In |
Token ID | 554 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
corrid | +0.955 |
KS | +0.936 |
Nieto | +0.910 |
Moj | +0.888 |
Okin | +0.873 |
Neg logit contributions | |
Ult | -1.095 |
uez | -1.069 |
--- | -1.006 |
Temp | -0.942 |
alach | -0.938 |
Token | a |
Token ID | 257 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
Ult | +0.716 |
uez | +0.697 |
--- | +0.656 |
Temp | +0.606 |
alach | +0.601 |
Neg logit contributions | |
corrid | -0.738 |
KS | -0.716 |
Nieto | -0.698 |
Moj | -0.682 |
Okin | -0.669 |
Token | nation |
Token ID | 3277 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
corrid | +0.674 |
KS | +0.658 |
Nieto | +0.641 |
Moj | +0.627 |
Okin | +0.616 |
Neg logit contributions | |
Ult | -0.633 |
uez | -0.615 |
--- | -0.576 |
Temp | -0.535 |
alach | -0.531 |
Token | of |
Token ID | 286 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
corrid | +0.973 |
KS | +0.954 |
Nieto | +0.934 |
Moj | +0.910 |
Okin | +0.894 |
Neg logit contributions | |
Ult | -0.916 |
uez | -0.891 |
--- | -0.822 |
Temp | -0.772 |
alach | -0.766 |
Token | roughly |
Token ID | 7323 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
corrid | +0.397 |
KS | +0.387 |
Nieto | +0.378 |
Moj | +0.368 |
Okin | +0.363 |
Neg logit contributions | |
Ult | -0.410 |
uez | -0.399 |
--- | -0.374 |
Temp | -0.349 |
alach | -0.346 |
Token | 127 |
Token ID | 18112 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
Ult | +0.127 |
uez | +0.123 |
--- | +0.116 |
Temp | +0.108 |
alach | +0.107 |
Neg logit contributions | |
corrid | -0.121 |
KS | -0.117 |
Nieto | -0.114 |
Moj | -0.111 |
Okin | -0.109 |
Token | million |
Token ID | 1510 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
Ult | +0.548 |
uez | +0.535 |
--- | +0.507 |
Temp | +0.473 |
Olymp | +0.469 |
Neg logit contributions | |
corrid | -0.453 |
KS | -0.439 |
Nieto | -0.427 |
Moj | -0.415 |
Okin | -0.407 |
Token | people |
Token ID | 661 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
corrid | +0.112 |
KS | +0.109 |
Nieto | +0.106 |
Moj | +0.103 |
Okin | +0.102 |
Neg logit contributions | |
Ult | -0.110 |
uez | -0.107 |
--- | -0.100 |
Temp | -0.093 |
alach | -0.092 |
Token | , |
Token ID | 11 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
corrid | +0.522 |
KS | +0.510 |
Nieto | +0.498 |
Moj | +0.485 |
Okin | +0.478 |
Neg logit contributions | |
Ult | -0.516 |
uez | -0.500 |
--- | -0.465 |
Temp | -0.437 |
alach | -0.433 |
Token | in |
Token ID | 287 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Ult | +0.330 |
uez | +0.321 |
--- | +0.301 |
Temp | +0.278 |
alach | +0.276 |
Neg logit contributions | |
corrid | -0.356 |
KS | -0.347 |
Nieto | -0.338 |
Moj | -0.331 |
Okin | -0.325 |
Token | voicing |
Token ID | 47640 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
corrid | +1.522 |
KS | +1.488 |
Nieto | +1.447 |
Moj | +1.403 |
Okin | +1.383 |
Neg logit contributions | |
Ult | -1.625 |
uez | -1.584 |
--- | -1.479 |
Temp | -1.392 |
alach | -1.391 |
Token | his |
Token ID | 465 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
corrid | +0.779 |
KS | +0.762 |
Nieto | +0.744 |
Moj | +0.724 |
Okin | +0.717 |
Neg logit contributions | |
Ult | -0.787 |
uez | -0.765 |
--- | -0.718 |
Temp | -0.669 |
alach | -0.667 |
Token | racism |
Token ID | 10713 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
corrid | +0.879 |
KS | +0.860 |
Nieto | +0.839 |
Moj | +0.822 |
Okin | +0.810 |
Neg logit contributions | |
Ult | -0.762 |
uez | -0.741 |
--- | -0.690 |
Temp | -0.639 |
alach | -0.634 |
Token | and |
Token ID | 290 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
corrid | +0.168 |
KS | +0.164 |
Nieto | +0.160 |
Moj | +0.156 |
Okin | +0.153 |
Neg logit contributions | |
Ult | -0.168 |
uez | -0.164 |
--- | -0.154 |
Temp | -0.143 |
alach | -0.142 |
Token | antis |
Token ID | 33064 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
corrid | +0.188 |
KS | +0.184 |
Nieto | +0.179 |
Moj | +0.176 |
Okin | +0.174 |
Neg logit contributions | |
Ult | -0.134 |
uez | -0.130 |
--- | -0.121 |
Temp | -0.110 |
alach | -0.109 |
Token | em |
Token ID | 368 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
corrid | +1.564 |
KS | +1.540 |
Nieto | +1.500 |
Moj | +1.463 |
ico | +1.434 |
Neg logit contributions | |
Ult | -1.695 |
uez | -1.673 |
--- | -1.539 |
Olymp | -1.454 |
Temp | -1.452 |
Token | itism |
Token ID | 18937 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
corrid | +1.366 |
KS | +1.356 |
Nieto | +1.302 |
Moj | +1.275 |
ico | +1.254 |
Neg logit contributions | |
Ult | -1.805 |
uez | -1.753 |
--- | -1.655 |
Temp | -1.568 |
alach | -1.551 |
Token | than |
Token ID | 621 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
corrid | +0.771 |
KS | +0.753 |
Nieto | +0.736 |
Moj | +0.717 |
Okin | +0.705 |
Neg logit contributions | |
Ult | -0.781 |
uez | -0.761 |
--- | -0.709 |
Temp | -0.665 |
alach | -0.660 |
Token | his |
Token ID | 465 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
KS | +2.371 |
corrid | +2.364 |
Nieto | +2.316 |
Moj | +2.250 |
Okin | +2.215 |
Neg logit contributions | |
Ult | -2.569 |
uez | -2.523 |
--- | -2.320 |
Temp | -2.211 |
alach | -2.208 |
Token | contemporaries |
Token ID | 46028 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
Ult | +0.129 |
uez | +0.126 |
--- | +0.117 |
Temp | +0.109 |
alach | +0.108 |
Neg logit contributions | |
corrid | -0.146 |
KS | -0.143 |
Nieto | -0.140 |
Moj | -0.137 |
Okin | -0.135 |
Token | afraid |
Token ID | 7787 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
Ult | +0.573 |
uez | +0.553 |
--- | +0.502 |
Temp | +0.458 |
alach | +0.458 |
Neg logit contributions | |
corrid | -0.868 |
KS | -0.860 |
Nieto | -0.841 |
Moj | -0.825 |
Okin | -0.814 |
Token | of |
Token ID | 286 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
corrid | +0.369 |
KS | +0.367 |
Nieto | +0.359 |
Moj | +0.351 |
Okin | +0.345 |
Neg logit contributions | |
Ult | -0.308 |
uez | -0.300 |
--- | -0.276 |
alach | -0.257 |
Temp | -0.256 |
Token | that |
Token ID | 326 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
corrid | +0.066 |
KS | +0.065 |
Nieto | +0.063 |
Moj | +0.062 |
Okin | +0.060 |
Neg logit contributions | |
Ult | -0.067 |
uez | -0.065 |
--- | -0.061 |
Temp | -0.057 |
alach | -0.057 |
Token | too |
Token ID | 1165 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
KS | +0.845 |
corrid | +0.830 |
Nieto | +0.817 |
Moj | +0.806 |
Okin | +0.787 |
Neg logit contributions | |
Ult | -0.628 |
uez | -0.607 |
--- | -0.543 |
alach | -0.525 |
20439 | -0.521 |
Token | . |
Token ID | 13 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
KS | +3.455 |
Moj | +3.277 |
Nieto | +3.267 |
ico | +3.153 |
Okin | +3.099 |
Neg logit contributions | |
Ult | -4.211 |
uez | -4.161 |
alach | -3.810 |
utenberg | -3.727 |
20439 | -3.688 |
Token | Last |
Token ID | 4586 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
KS | +2.181 |
corrid | +2.165 |
Nieto | +2.122 |
Moj | +2.073 |
Okin | +2.006 |
Neg logit contributions | |
Ult | -2.937 |
uez | -2.899 |
--- | -2.703 |
alach | -2.578 |
Temp | -2.556 |
Token | week |
Token ID | 1285 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
KS | +4.462 |
Moj | +4.218 |
Nieto | +4.153 |
ico | +3.888 |
corrid | +3.775 |
Neg logit contributions | |
Ult | -9.941 |
uez | -9.645 |
alach | -9.076 |
--- | -8.900 |
20439 | -8.890 |
Token | I |
Token ID | 314 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
corrid | +0.286 |
KS | +0.283 |
Nieto | +0.274 |
Moj | +0.266 |
Okin | +0.260 |
Neg logit contributions | |
Ult | -0.415 |
uez | -0.406 |
--- | -0.384 |
Temp | -0.362 |
alach | -0.362 |
Token | caught |
Token ID | 4978 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
corrid | +1.481 |
KS | +1.450 |
Nieto | +1.418 |
Moj | +1.378 |
Okin | +1.353 |
Neg logit contributions | |
Ult | -1.642 |
uez | -1.596 |
--- | -1.487 |
Temp | -1.402 |
alach | -1.399 |
Token | her |
Token ID | 607 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Ult | +1.295 |
uez | +1.244 |
--- | +1.134 |
Temp | +1.010 |
alach | +0.999 |
Neg logit contributions | |
corrid | -2.495 |
KS | -2.451 |
Nieto | -2.403 |
Moj | -2.362 |
Okin | -2.330 |
Token | re |
Token ID | 302 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
KS | +1.388 |
corrid | +1.376 |
Nieto | +1.345 |
Moj | +1.329 |
Okin | +1.300 |
Neg logit contributions | |
Ult | -1.392 |
uez | -1.332 |
--- | -1.239 |
alach | -1.193 |
Temp | -1.179 |
Token | , |
Token ID | 11 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
corrid | +1.335 |
KS | +1.307 |
Nieto | +1.273 |
Moj | +1.239 |
Okin | +1.218 |
Neg logit contributions | |
Ult | -1.509 |
uez | -1.469 |
--- | -1.369 |
Temp | -1.290 |
alach | -1.286 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
corrid | +1.415 |
KS | +1.394 |
Nieto | +1.352 |
Moj | +1.330 |
Okin | +1.308 |
Neg logit contributions | |
Ult | -1.296 |
uez | -1.260 |
--- | -1.168 |
Temp | -1.089 |
alach | -1.084 |
Token | show |
Token ID | 905 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
corrid | +0.841 |
KS | +0.826 |
Nieto | +0.802 |
Moj | +0.789 |
Okin | +0.778 |
Neg logit contributions | |
Ult | -0.747 |
uez | -0.725 |
--- | -0.671 |
Temp | -0.627 |
alach | -0.622 |
Token | them |
Token ID | 606 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
corrid | +0.990 |
KS | +0.969 |
Nieto | +0.945 |
Moj | +0.924 |
Okin | +0.913 |
Neg logit contributions | |
Ult | -0.972 |
uez | -0.943 |
--- | -0.881 |
Temp | -0.824 |
alach | -0.816 |
Token | we |
Token ID | 356 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
corrid | +2.350 |
KS | +2.324 |
Nieto | +2.254 |
Moj | +2.211 |
Okin | +2.194 |
Neg logit contributions | |
Ult | -2.451 |
uez | -2.367 |
--- | -2.185 |
Temp | -2.083 |
utenberg | -2.067 |
Token | mean |
Token ID | 1612 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
corrid | +1.440 |
KS | +1.426 |
Nieto | +1.387 |
Moj | +1.361 |
Okin | +1.345 |
Neg logit contributions | |
Ult | -1.324 |
uez | -1.274 |
--- | -1.179 |
Temp | -1.113 |
20439 | -1.105 |
Token | business |
Token ID | 1597 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
KS | +3.431 |
corrid | +3.416 |
Nieto | +3.287 |
Moj | +3.251 |
Okin | +3.150 |
Neg logit contributions | |
Ult | -4.643 |
uez | -4.410 |
20439 | -4.061 |
--- | -4.060 |
utenberg | -4.021 |
Token | .' |
Token ID | 2637 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
Ult | +1.039 |
uez | +1.009 |
--- | +0.947 |
Temp | +0.868 |
alach | +0.861 |
Neg logit contributions | |
corrid | -1.239 |
KS | -1.206 |
Nieto | -1.178 |
Moj | -1.153 |
Okin | -1.134 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
KS | +2.198 |
corrid | +2.193 |
Nieto | +2.119 |
Moj | +2.063 |
Okin | +2.028 |
Neg logit contributions | |
Ult | -3.230 |
uez | -3.171 |
--- | -2.975 |
Temp | -2.835 |
alach | -2.831 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
corrid | +0.099 |
KS | +0.098 |
Nieto | +0.095 |
Moj | +0.093 |
Okin | +0.090 |
Neg logit contributions | |
Ult | -0.137 |
uez | -0.134 |
--- | -0.126 |
alach | -0.119 |
Temp | -0.119 |
Token | New |
Token ID | 3791 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
KS | +1.158 |
corrid | +1.156 |
Nieto | +1.123 |
Moj | +1.101 |
Okin | +1.084 |
Neg logit contributions | |
Ult | -1.066 |
uez | -1.060 |
--- | -0.972 |
alach | -0.923 |
utenberg | -0.904 |
Token | x |
Token ID | 87 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Ult | +1.485 |
uez | +1.437 |
--- | +1.353 |
Temp | +1.233 |
alach | +1.219 |
Neg logit contributions | |
corrid | -1.893 |
KS | -1.842 |
Nieto | -1.804 |
Moj | -1.761 |
Okin | -1.737 |
Token | . |
Token ID | 13 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Ult | +1.832 |
uez | +1.776 |
--- | +1.688 |
Temp | +1.542 |
._ | +1.532 |
Neg logit contributions | |
corrid | -2.159 |
KS | -2.028 |
Nieto | -1.992 |
Moj | -1.935 |
Okin | -1.916 |
Token | x |
Token ID | 87 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Ult | +0.989 |
uez | +0.960 |
--- | +0.896 |
Temp | +0.824 |
alach | +0.817 |
Neg logit contributions | |
corrid | -1.206 |
KS | -1.177 |
Nieto | -1.149 |
Moj | -1.125 |
Okin | -1.107 |
Token | . |
Token ID | 13 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
Ult | +1.541 |
uez | +1.497 |
--- | +1.408 |
Temp | +1.299 |
alach | +1.283 |
Neg logit contributions | |
corrid | -1.698 |
KS | -1.641 |
Nieto | -1.603 |
Moj | -1.565 |
Okin | -1.542 |
Token | 80 |
Token ID | 1795 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
corrid | +0.452 |
KS | +0.445 |
Nieto | +0.433 |
Moj | +0.426 |
ico | +0.423 |
Neg logit contributions | |
Ult | -0.329 |
uez | -0.322 |
--- | -0.291 |
alach | -0.270 |
Temp | -0.269 |
Token | 106 |
Token ID | 15696 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
Ult | +0.780 |
uez | +0.759 |
--- | +0.726 |
Temp | +0.677 |
Olymp | +0.671 |
Neg logit contributions | |
corrid | -0.617 |
KS | -0.588 |
Nieto | -0.576 |
Moj | -0.558 |
Okin | -0.548 |
Token | 27 |
Token ID | 1983 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
KS | +3.919 |
Nieto | +3.729 |
corrid | +3.729 |
Moj | +3.690 |
ico | +3.586 |
Neg logit contributions | |
uez | -4.041 |
Ult | -4.035 |
--- | -3.594 |
alach | -3.566 |
utenberg | -3.448 |
Token | 66 |
Token ID | 2791 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
corrid | +0.879 |
KS | +0.866 |
Nieto | +0.841 |
Moj | +0.824 |
Okin | +0.808 |
Neg logit contributions | |
Ult | -0.867 |
uez | -0.845 |
--- | -0.788 |
alach | -0.735 |
Temp | -0.734 |
Token | x |
Token ID | 2124 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
Ult | +3.358 |
uez | +3.249 |
--- | +3.147 |
Temp | +2.924 |
diff | +2.909 |
Neg logit contributions | |
corrid | -2.662 |
KS | -2.513 |
Nieto | -2.499 |
Moj | -2.389 |
Okin | -2.382 |
Token | . |
Token ID | 13 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Ult | +0.257 |
uez | +0.250 |
--- | +0.233 |
alach | +0.217 |
Temp | +0.217 |
Neg logit contributions | |
corrid | -0.266 |
KS | -0.264 |
Nieto | -0.257 |
Moj | -0.251 |
Okin | -0.246 |
Token | x |
Token ID | 87 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Ult | +2.349 |
uez | +2.268 |
--- | +2.162 |
Temp | +1.939 |
._ | +1.923 |
Neg logit contributions | |
corrid | -3.313 |
KS | -3.074 |
Nieto | -3.035 |
Moj | -2.943 |
Okin | -2.915 |
Token | card |
Token ID | 2657 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
corrid | +0.379 |
KS | +0.368 |
Nieto | +0.347 |
Moj | +0.341 |
Okin | +0.325 |
Neg logit contributions | |
Ult | -0.828 |
uez | -0.810 |
--- | -0.770 |
Temp | -0.737 |
alach | -0.734 |
Token | companies |
Token ID | 2706 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Ult | +0.274 |
uez | +0.266 |
--- | +0.248 |
Temp | +0.231 |
alach | +0.229 |
Neg logit contributions | |
corrid | -0.297 |
KS | -0.291 |
Nieto | -0.283 |
Moj | -0.277 |
Okin | -0.272 |
Token | ; |
Token ID | 26 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
corrid | +0.865 |
KS | +0.854 |
Nieto | +0.829 |
Moj | +0.815 |
Okin | +0.793 |
Neg logit contributions | |
Ult | -0.834 |
uez | -0.808 |
--- | -0.744 |
Temp | -0.701 |
alach | -0.697 |
Token | now |
Token ID | 783 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
KS | +2.384 |
corrid | +2.373 |
Nieto | +2.292 |
Moj | +2.260 |
Okin | +2.188 |
Neg logit contributions | |
Ult | -2.590 |
uez | -2.494 |
--- | -2.328 |
Temp | -2.225 |
20439 | -2.222 |
Token | i |
Token ID | 1312 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
corrid | +0.871 |
KS | +0.864 |
Nieto | +0.836 |
Moj | +0.825 |
Okin | +0.803 |
Neg logit contributions | |
Ult | -0.794 |
uez | -0.764 |
--- | -0.711 |
Temp | -0.670 |
alach | -0.659 |
Token | ... |
Token ID | 986 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
Ult | +0.475 |
uez | +0.461 |
--- | +0.433 |
Temp | +0.399 |
alach | +0.396 |
Neg logit contributions | |
corrid | -0.533 |
KS | -0.519 |
Nieto | -0.507 |
Moj | -0.496 |
Okin | -0.488 |
Token |
|
Token ID | 198 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
KS | +3.289 |
corrid | +3.269 |
Nieto | +3.145 |
Moj | +3.082 |
ico | +2.971 |
Neg logit contributions | |
Ult | -4.745 |
uez | -4.683 |
--- | -4.350 |
Temp | -4.201 |
alach | -4.137 |
Token |
|
Token ID | 198 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
KS | +1.433 |
Nieto | +1.357 |
Moj | +1.342 |
ico | +1.294 |
Okin | +1.290 |
Neg logit contributions | |
Ult | -2.234 |
uez | -2.208 |
--- | -2.029 |
alach | -2.009 |
20439 | -1.965 |
Token | Although |
Token ID | 7003 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
corrid | +0.500 |
KS | +0.495 |
Nieto | +0.481 |
Moj | +0.472 |
Okin | +0.462 |
Neg logit contributions | |
Ult | -0.466 |
uez | -0.458 |
--- | -0.422 |
alach | -0.396 |
Temp | -0.392 |
Token | this |
Token ID | 428 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
corrid | +0.560 |
KS | +0.551 |
Nieto | +0.536 |
Moj | +0.524 |
Okin | +0.513 |
Neg logit contributions | |
Ult | -0.578 |
uez | -0.560 |
--- | -0.523 |
Temp | -0.492 |
alach | -0.487 |
Token | one |
Token ID | 530 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
Ult | +0.111 |
uez | +0.107 |
--- | +0.099 |
Temp | +0.092 |
alach | +0.092 |
Neg logit contributions | |
corrid | -0.128 |
KS | -0.126 |
Nieto | -0.123 |
Moj | -0.120 |
Okin | -0.118 |
Token | 12 |
Token ID | 1065 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
corrid | +0.786 |
KS | +0.785 |
Nieto | +0.759 |
Moj | +0.743 |
Okin | +0.728 |
Neg logit contributions | |
Ult | -0.803 |
uez | -0.784 |
--- | -0.727 |
alach | -0.684 |
Temp | -0.681 |
Token | , |
Token ID | 11 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Ult | +1.820 |
uez | +1.767 |
--- | +1.673 |
Temp | +1.540 |
alach | +1.528 |
Neg logit contributions | |
corrid | -1.901 |
KS | -1.834 |
Nieto | -1.799 |
Moj | -1.752 |
Okin | -1.723 |
Token | India |
Token ID | 3794 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Ult | +1.807 |
uez | +1.761 |
--- | +1.663 |
Temp | +1.546 |
alach | +1.534 |
Neg logit contributions | |
corrid | -1.692 |
KS | -1.635 |
Nieto | -1.597 |
Moj | -1.556 |
Okin | -1.529 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Ult | +1.713 |
uez | +1.669 |
--- | +1.593 |
Temp | +1.483 |
alach | +1.475 |
Neg logit contributions | |
corrid | -1.376 |
KS | -1.325 |
Nieto | -1.290 |
Moj | -1.255 |
Okin | -1.234 |
Token |
|
Token ID | 198 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
KS | +0.924 |
Nieto | +0.883 |
corrid | +0.874 |
Moj | +0.866 |
Okin | +0.839 |
Neg logit contributions | |
Ult | -1.359 |
uez | -1.336 |
--- | -1.243 |
alach | -1.204 |
Temp | -1.184 |
Token | Read |
Token ID | 5569 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
KS | +2.350 |
corrid | +2.314 |
Nieto | +2.228 |
Moj | +2.168 |
ico | +2.149 |
Neg logit contributions | |
uez | -3.889 |
Ult | -3.852 |
--- | -3.570 |
alach | -3.491 |
utenberg | -3.460 |
Token | More |
Token ID | 3125 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
KS | +3.895 |
Nieto | +3.743 |
Moj | +3.687 |
Okin | +3.511 |
corrid | +3.489 |
Neg logit contributions | |
Ult | -5.864 |
uez | -5.731 |
--- | -5.289 |
alach | -5.145 |
utenberg | -5.103 |
Token | Ab |
Token ID | 2275 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Ult | +0.440 |
uez | +0.428 |
--- | +0.406 |
Temp | +0.379 |
Olymp | +0.375 |
Neg logit contributions | |
corrid | -0.381 |
KS | -0.366 |
Nieto | -0.356 |
Moj | -0.347 |
Okin | -0.341 |
Token | ut |
Token ID | 315 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Ult | +1.446 |
uez | +1.408 |
--- | +1.317 |
Temp | +1.216 |
alach | +1.209 |
Neg logit contributions | |
corrid | -1.650 |
KS | -1.601 |
Nieto | -1.568 |
Moj | -1.533 |
Okin | -1.507 |
Token | Sun |
Token ID | 3825 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
corrid | +1.796 |
KS | +1.795 |
Nieto | +1.744 |
Moj | +1.711 |
ico | +1.679 |
Neg logit contributions | |
Ult | -1.410 |
uez | -1.375 |
--- | -1.270 |
Temp | -1.169 |
20439 | -1.158 |
Token | Temple |
Token ID | 10857 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Ult | +2.527 |
uez | +2.426 |
--- | +2.286 |
Temp | +2.083 |
Olymp | +2.037 |
Neg logit contributions | |
corrid | -3.726 |
KS | -3.579 |
Nieto | -3.513 |
Moj | -3.442 |
Okin | -3.404 |