Token | ghost |
Token ID | 10905 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
orian | +3.911 |
orb | +3.750 |
kson | +3.649 |
tale | +3.602 |
arious | +3.571 |
Neg logit contributions | |
Random | -3.349 |
Sham | -3.332 |
dump | -3.307 |
nam | -3.247 |
ASA | -3.160 |
Token | invasion |
Token ID | 11796 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
orian | +3.079 |
orb | +2.870 |
kson | +2.760 |
rupal | +2.675 |
tale | +2.635 |
Neg logit contributions | |
Random | -6.288 |
dump | -6.252 |
Sham | -6.225 |
nam | -6.145 |
ASA | -5.989 |
Token | of |
Token ID | 286 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
orian | +1.198 |
orb | +1.137 |
kson | +1.136 |
rupal | +1.099 |
oulos | +1.095 |
Neg logit contributions | |
dump | -1.072 |
Random | -1.070 |
Sham | -1.061 |
nam | -1.049 |
ASA | -1.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
orian | +2.228 |
orb | +2.123 |
kson | +2.118 |
rupal | +2.055 |
oulos | +2.046 |
Neg logit contributions | |
dump | -1.716 |
Random | -1.710 |
Sham | -1.694 |
nam | -1.673 |
ASA | -1.598 |
Token | big |
Token ID | 1263 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
orian | +1.955 |
orb | +1.905 |
kson | +1.845 |
arious | +1.813 |
tale | +1.808 |
Neg logit contributions | |
Random | -1.620 |
dump | -1.617 |
Sham | -1.602 |
nam | -1.571 |
ASA | -1.523 |
Token | Apple |
Token ID | 4196 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
orian | +1.927 |
orb | +1.832 |
kson | +1.763 |
oulos | +1.710 |
rupal | +1.705 |
Neg logit contributions | |
dump | -3.118 |
Sham | -3.101 |
Random | -3.094 |
nam | -3.074 |
ASA | -2.967 |
Token | . |
Token ID | 13 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
orian | +5.922 |
orb | +5.632 |
kson | +5.549 |
tale | +5.401 |
rupal | +5.269 |
Neg logit contributions | |
dump | -8.399 |
Random | -8.293 |
Sham | -8.194 |
nam | -8.180 |
ASA | -8.009 |
Token |
|
Token ID | 198 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
orian | +2.510 |
orb | +2.407 |
kson | +2.307 |
tale | +2.258 |
rupal | +2.247 |
Neg logit contributions | |
dump | -2.947 |
Sham | -2.900 |
Random | -2.899 |
nam | -2.873 |
ASA | -2.799 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
orian | +0.711 |
orb | +0.673 |
kson | +0.672 |
rupal | +0.651 |
oulos | +0.650 |
Neg logit contributions | |
dump | -0.670 |
Random | -0.670 |
Sham | -0.665 |
nam | -0.658 |
ASA | -0.627 |
Token | To |
Token ID | 2514 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
dump | +0.055 |
Random | +0.055 |
Sham | +0.054 |
nam | +0.054 |
ASA | +0.051 |
Neg logit contributions | |
orian | -0.089 |
orb | -0.085 |
kson | -0.085 |
rupal | -0.082 |
oulos | -0.082 |
Token | make |
Token ID | 787 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
dump | +0.114 |
Random | +0.113 |
Sham | +0.113 |
nam | +0.111 |
ASA | +0.106 |
Neg logit contributions | |
orian | -0.139 |
orb | -0.132 |
kson | -0.132 |
rupal | -0.128 |
oulos | -0.128 |
Token | land |
Token ID | 1044 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
orian | +0.885 |
orb | +0.837 |
kson | +0.835 |
rupal | +0.805 |
oulos | +0.802 |
Neg logit contributions | |
dump | -0.928 |
Random | -0.927 |
Sham | -0.920 |
nam | -0.908 |
ASA | -0.874 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
orian | +2.807 |
orb | +2.642 |
kson | +2.639 |
rupal | +2.549 |
oulos | +2.529 |
Neg logit contributions | |
Random | -2.960 |
dump | -2.960 |
Sham | -2.937 |
nam | -2.878 |
ASA | -2.796 |
Token | By |
Token ID | 3886 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
orian | +3.906 |
orb | +3.765 |
kson | +3.656 |
tale | +3.599 |
rupal | +3.589 |
Neg logit contributions | |
Sham | -2.550 |
dump | -2.487 |
nam | -2.425 |
ASA | -2.416 |
Random | -2.404 |
Token | Sam |
Token ID | 3409 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
orian | +0.016 |
orb | +0.015 |
kson | +0.015 |
rupal | +0.015 |
oulos | +0.015 |
Neg logit contributions | |
dump | -0.014 |
Random | -0.014 |
Sham | -0.014 |
nam | -0.014 |
ASA | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
orian | +4.067 |
orb | +3.881 |
kson | +3.865 |
rupal | +3.746 |
oulos | +3.746 |
Neg logit contributions | |
dump | -2.714 |
Random | -2.706 |
nam | -2.600 |
Sham | -2.564 |
unres | -2.514 |
Token | updated |
Token ID | 6153 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
orian | +0.572 |
orb | +0.543 |
kson | +0.543 |
rupal | +0.526 |
oulos | +0.524 |
Neg logit contributions | |
dump | -0.466 |
Random | -0.464 |
Sham | -0.459 |
nam | -0.454 |
ASA | -0.433 |
Token | on |
Token ID | 319 |
Feature activation | +6.65e+00 |
Pos logit contributions | |
orian | +6.282 |
orb | +5.884 |
kson | +5.807 |
oulos | +5.646 |
rupal | +5.630 |
Neg logit contributions | |
dump | -7.327 |
Random | -7.203 |
nam | -7.161 |
Sham | -7.041 |
� | -6.781 |
Token | 15 |
Token ID | 1315 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
orian | +4.327 |
orb | +4.090 |
kson | +4.079 |
rupal | +3.942 |
oulos | +3.910 |
Neg logit contributions | |
dump | -4.665 |
Random | -4.640 |
nam | -4.535 |
Sham | -4.475 |
� | -4.298 |
Token | July |
Token ID | 2901 |
Feature activation | +7.85e+00 |
Pos logit contributions | |
orian | +2.065 |
orb | +1.957 |
kson | +1.945 |
rupal | +1.889 |
oulos | +1.874 |
Neg logit contributions | |
dump | -1.948 |
Random | -1.944 |
Sham | -1.919 |
nam | -1.897 |
ASA | -1.822 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
orian | +4.728 |
orb | +4.472 |
kson | +4.452 |
oulos | +4.315 |
rupal | +4.299 |
Neg logit contributions | |
dump | -5.766 |
Random | -5.731 |
Sham | -5.610 |
nam | -5.600 |
ASA | -5.326 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
orian | +2.512 |
orb | +2.374 |
kson | +2.360 |
rupal | +2.285 |
oulos | +2.274 |
Neg logit contributions | |
dump | -2.608 |
Random | -2.597 |
Sham | -2.568 |
nam | -2.542 |
ASA | -2.431 |
Token | Half |
Token ID | 31305 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
orian | +2.382 |
orb | +2.276 |
kson | +2.236 |
oulos | +2.161 |
arious | +2.155 |
Neg logit contributions | |
dump | -2.186 |
Random | -2.170 |
Sham | -2.167 |
nam | -2.133 |
ASA | -2.074 |
Token | Ac |
Token ID | 4013 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
orian | +0.807 |
orb | +0.769 |
kson | +0.768 |
rupal | +0.744 |
oulos | +0.741 |
Neg logit contributions | |
dump | -0.632 |
Random | -0.630 |
Sham | -0.625 |
nam | -0.617 |
ASA | -0.589 |
Token | re |
Token ID | 260 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
orian | +2.992 |
orb | +2.771 |
kson | +2.758 |
arious | +2.611 |
rupal | +2.606 |
Neg logit contributions | |
dump | -3.548 |
Random | -3.496 |
Sham | -3.470 |
nam | -3.440 |
unres | -3.325 |
Token | collaboration |
Token ID | 12438 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
orian | +1.734 |
kson | +1.651 |
orb | +1.649 |
oulos | +1.592 |
rupal | +1.592 |
Neg logit contributions | |
dump | -1.361 |
Random | -1.355 |
Sham | -1.333 |
nam | -1.326 |
ASA | -1.258 |
Token | An |
Token ID | 1052 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
orian | +0.389 |
orb | +0.369 |
kson | +0.369 |
rupal | +0.358 |
oulos | +0.356 |
Neg logit contributions | |
dump | -0.339 |
Random | -0.338 |
Sham | -0.337 |
nam | -0.332 |
ASA | -0.318 |
Token | ic |
Token ID | 291 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
dump | +0.744 |
Random | +0.742 |
Sham | +0.741 |
nam | +0.741 |
ASA | +0.699 |
Neg logit contributions | |
orian | -0.838 |
orb | -0.796 |
kson | -0.795 |
rupal | -0.774 |
oulos | -0.766 |
Token | ca |
Token ID | 6888 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
orian | +7.607 |
orb | +7.165 |
kson | +7.068 |
arious | +6.966 |
uria | +6.834 |
Neg logit contributions | |
Random | -6.190 |
dump | -6.077 |
nam | -5.911 |
Sham | -5.897 |
unres | -5.848 |
Token | . |
Token ID | 13 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
orian | +1.037 |
orb | +0.988 |
kson | +0.986 |
rupal | +0.952 |
oulos | +0.950 |
Neg logit contributions | |
dump | -0.859 |
Random | -0.855 |
Sham | -0.844 |
nam | -0.838 |
ASA | -0.798 |
Token | Brew |
Token ID | 9702 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
orian | +0.459 |
orb | +0.437 |
kson | +0.436 |
rupal | +0.424 |
oulos | +0.422 |
Neg logit contributions | |
Random | -0.353 |
dump | -0.353 |
Sham | -0.352 |
nam | -0.346 |
ASA | -0.331 |
Token | ed |
Token ID | 276 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
orian | +0.727 |
orb | +0.681 |
kson | +0.680 |
rupal | +0.652 |
oulos | +0.648 |
Neg logit contributions | |
dump | -1.009 |
Random | -1.007 |
Sham | -1.001 |
nam | -0.991 |
ASA | -0.956 |
Token | with |
Token ID | 351 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Sham | +2.083 |
Random | +2.042 |
dump | +2.035 |
nam | +2.014 |
ASA | +1.937 |
Neg logit contributions | |
orian | -2.320 |
orb | -2.194 |
kson | -2.191 |
rupal | -2.161 |
oulos | -2.146 |
Token | . |
Token ID | 13 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
orian | +2.889 |
orb | +2.754 |
kson | +2.719 |
rupal | +2.635 |
oulos | +2.626 |
Neg logit contributions | |
dump | -2.894 |
Random | -2.892 |
nam | -2.833 |
Sham | -2.809 |
ASA | -2.721 |
Token | Oklahoma |
Token ID | 10433 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
orian | +0.346 |
orb | +0.330 |
kson | +0.328 |
rupal | +0.319 |
oulos | +0.317 |
Neg logit contributions | |
dump | -0.273 |
Random | -0.273 |
Sham | -0.272 |
nam | -0.267 |
ASA | -0.256 |
Token | , |
Token ID | 11 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
dump | +0.739 |
Random | +0.736 |
Sham | +0.732 |
nam | +0.722 |
ASA | +0.691 |
Neg logit contributions | |
orian | -0.923 |
orb | -0.880 |
kson | -0.877 |
rupal | -0.851 |
oulos | -0.847 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
dump | +0.112 |
Random | +0.112 |
Sham | +0.111 |
nam | +0.109 |
ASA | +0.105 |
Neg logit contributions | |
orian | -0.150 |
orb | -0.143 |
kson | -0.143 |
rupal | -0.139 |
oulos | -0.138 |
Token | seism |
Token ID | 30518 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
orian | +0.808 |
kson | +0.768 |
orb | +0.768 |
rupal | +0.743 |
oulos | +0.742 |
Neg logit contributions | |
Random | -0.603 |
dump | -0.603 |
Sham | -0.592 |
nam | -0.588 |
ASA | -0.558 |
Token | ically |
Token ID | 1146 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
orian | +3.807 |
orb | +3.398 |
kson | +3.120 |
arious | +3.081 |
uitive | +2.936 |
Neg logit contributions | |
Random | -8.278 |
Sham | -8.155 |
dump | -8.083 |
nam | -8.036 |
ASA | -7.876 |
Token | inactive |
Token ID | 28621 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
orian | +6.054 |
orb | +5.870 |
kson | +5.811 |
rupal | +5.527 |
oulos | +5.506 |
Neg logit contributions | |
Random | -6.506 |
dump | -6.489 |
nam | -6.073 |
Sham | -6.040 |
ASA | -5.870 |
Token | area |
Token ID | 1989 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
orian | +3.675 |
kson | +3.509 |
orb | +3.482 |
arious | +3.332 |
oulos | +3.330 |
Neg logit contributions | |
Random | -3.239 |
dump | -3.203 |
nam | -3.103 |
Sham | -3.078 |
ASA | -2.895 |
Token | before |
Token ID | 878 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
orian | +1.165 |
kson | +1.106 |
orb | +1.105 |
rupal | +1.069 |
oulos | +1.058 |
Neg logit contributions | |
Random | -1.043 |
dump | -1.042 |
Sham | -1.027 |
nam | -1.016 |
ASA | -0.975 |
Token | gas |
Token ID | 3623 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
orian | +2.936 |
kson | +2.779 |
orb | +2.770 |
oulos | +2.707 |
rupal | +2.697 |
Neg logit contributions | |
Random | -2.454 |
dump | -2.446 |
nam | -2.390 |
Sham | -2.361 |
ASA | -2.248 |
Token | fracking |
Token ID | 25441 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
orian | +0.850 |
orb | +0.810 |
kson | +0.805 |
oulos | +0.781 |
rupal | +0.778 |
Neg logit contributions | |
Random | -0.732 |
dump | -0.726 |
Sham | -0.719 |
nam | -0.713 |
ASA | -0.679 |
Token | best |
Token ID | 1266 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
dump | +0.318 |
Random | +0.317 |
Sham | +0.314 |
nam | +0.310 |
ASA | +0.295 |
Neg logit contributions | |
orian | -0.421 |
orb | -0.402 |
kson | -0.401 |
rupal | -0.389 |
oulos | -0.387 |
Token | , |
Token ID | 11 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
dump | +1.303 |
Random | +1.299 |
Sham | +1.287 |
nam | +1.272 |
ASA | +1.215 |
Neg logit contributions | |
orian | -1.589 |
orb | -1.513 |
kson | -1.510 |
rupal | -1.463 |
oulos | -1.457 |
Token | such |
Token ID | 884 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
dump | +0.930 |
Random | +0.924 |
Sham | +0.922 |
nam | +0.906 |
ASA | +0.869 |
Neg logit contributions | |
orian | -1.217 |
orb | -1.159 |
kson | -1.156 |
rupal | -1.123 |
oulos | -1.118 |
Token | an |
Token ID | 281 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
dump | +0.247 |
Random | +0.246 |
Sham | +0.244 |
nam | +0.241 |
ASA | +0.230 |
Neg logit contributions | |
orian | -0.317 |
orb | -0.302 |
kson | -0.302 |
rupal | -0.293 |
oulos | -0.292 |
Token | approach |
Token ID | 3164 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
dump | +1.497 |
Sham | +1.492 |
Random | +1.492 |
nam | +1.472 |
ASA | +1.424 |
Neg logit contributions | |
orian | -1.921 |
kson | -1.810 |
orb | -1.806 |
rupal | -1.765 |
agascar | -1.750 |
Token | alien |
Token ID | 8756 |
Feature activation | +9.18e+00 |
Pos logit contributions | |
dump | +0.560 |
Random | +0.558 |
Sham | +0.556 |
nam | +0.549 |
ASA | +0.522 |
Neg logit contributions | |
orian | -0.650 |
orb | -0.617 |
kson | -0.614 |
rupal | -0.597 |
oulos | -0.594 |
Token | ates |
Token ID | 689 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
orian | +4.523 |
orb | +4.206 |
kson | +3.958 |
oulos | +3.948 |
arious | +3.930 |
Neg logit contributions | |
dump | -7.824 |
Random | -7.804 |
Sham | -7.553 |
ASA | -7.542 |
nam | -7.428 |
Token | young |
Token ID | 1862 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
orian | +3.120 |
kson | +2.979 |
orb | +2.954 |
rupal | +2.873 |
arious | +2.839 |
Neg logit contributions | |
dump | -2.777 |
Random | -2.764 |
nam | -2.689 |
Sham | -2.674 |
ASA | -2.542 |
Token | voters |
Token ID | 4446 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
Sham | +1.568 |
dump | +1.559 |
Random | +1.555 |
nam | +1.536 |
ASA | +1.460 |
Neg logit contributions | |
orian | -2.573 |
orb | -2.461 |
kson | -2.447 |
oulos | -2.385 |
rupal | -2.382 |
Token | , |
Token ID | 11 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
dump | +0.475 |
Sham | +0.473 |
Random | +0.472 |
nam | +0.465 |
ASA | +0.442 |
Neg logit contributions | |
orian | -0.566 |
orb | -0.537 |
kson | -0.537 |
rupal | -0.520 |
oulos | -0.518 |
Token | says |
Token ID | 1139 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
dump | +0.184 |
Random | +0.184 |
Sham | +0.182 |
nam | +0.180 |
ASA | +0.172 |
Neg logit contributions | |
orian | -0.230 |
orb | -0.219 |
kson | -0.218 |
rupal | -0.212 |
oulos | -0.211 |
Token | debt |
Token ID | 5057 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
Sham | +0.860 |
dump | +0.860 |
Random | +0.858 |
nam | +0.856 |
ASA | +0.806 |
Neg logit contributions | |
orian | -1.139 |
orb | -1.092 |
kson | -1.081 |
rupal | -1.048 |
oulos | -1.048 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
dump | +2.027 |
Sham | +2.019 |
Random | +2.013 |
nam | +2.007 |
ASA | +1.895 |
Neg logit contributions | |
orian | -2.468 |
orb | -2.352 |
kson | -2.347 |
rupal | -2.279 |
arious | -2.263 |
Token | which |
Token ID | 543 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
dump | +1.152 |
Random | +1.148 |
Sham | +1.144 |
nam | +1.131 |
ASA | +1.081 |
Neg logit contributions | |
orian | -1.257 |
kson | -1.201 |
orb | -1.198 |
rupal | -1.155 |
arious | -1.149 |
Token | has |
Token ID | 468 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
dump | +1.314 |
Random | +1.308 |
Sham | +1.307 |
nam | +1.288 |
ASA | +1.231 |
Neg logit contributions | |
orian | -1.627 |
orb | -1.551 |
kson | -1.541 |
rupal | -1.503 |
oulos | -1.492 |
Token | an |
Token ID | 281 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
orian | +0.119 |
orb | +0.112 |
kson | +0.112 |
rupal | +0.108 |
oulos | +0.108 |
Neg logit contributions | |
dump | -0.115 |
Random | -0.115 |
Sham | -0.113 |
nam | -0.112 |
ASA | -0.108 |
Token | impact |
Token ID | 2928 |
Feature activation | +9.05e+00 |
Pos logit contributions | |
orian | +0.447 |
orb | +0.425 |
kson | +0.424 |
rupal | +0.410 |
oulos | +0.409 |
Neg logit contributions | |
dump | -0.399 |
Random | -0.398 |
Sham | -0.394 |
nam | -0.390 |
ASA | -0.373 |
Token | on |
Token ID | 319 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
orian | +4.529 |
kson | +4.137 |
orb | +4.090 |
tale | +3.920 |
agascar | +3.915 |
Neg logit contributions | |
dump | -7.696 |
Random | -7.559 |
Sham | -7.427 |
ASA | -7.286 |
nam | -7.261 |
Token | students |
Token ID | 2444 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
orian | +3.339 |
kson | +3.166 |
orb | +3.115 |
rupal | +3.022 |
oulos | +3.000 |
Neg logit contributions | |
dump | -3.266 |
Random | -3.239 |
Sham | -3.174 |
nam | -3.133 |
ASA | -2.986 |
Token | � |
Token ID | 447 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
orian | +0.990 |
orb | +0.941 |
kson | +0.940 |
rupal | +0.913 |
oulos | +0.910 |
Neg logit contributions | |
dump | -0.735 |
Random | -0.730 |
Sham | -0.723 |
nam | -0.711 |
ASA | -0.681 |
Token | � |
Token ID | 247 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
orian | +1.706 |
orb | +1.629 |
kson | +1.628 |
rupal | +1.583 |
oulos | +1.579 |
Neg logit contributions | |
dump | -1.120 |
Random | -1.116 |
Sham | -1.103 |
nam | -1.091 |
ASA | -1.034 |
Token | life |
Token ID | 1204 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
orian | +2.087 |
kson | +1.985 |
orb | +1.984 |
rupal | +1.924 |
oulos | +1.919 |
Neg logit contributions | |
dump | -1.848 |
Random | -1.843 |
Sham | -1.815 |
nam | -1.796 |
ASA | -1.719 |
Token | New |
Token ID | 968 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
orian | +2.029 |
kson | +1.931 |
orb | +1.922 |
rupal | +1.861 |
oulos | +1.860 |
Neg logit contributions | |
Random | -1.550 |
dump | -1.536 |
nam | -1.477 |
Sham | -1.453 |
ASA | -1.400 |
Token | York |
Token ID | 1971 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
orian | +0.499 |
orb | +0.473 |
kson | +0.472 |
rupal | +0.458 |
oulos | +0.457 |
Neg logit contributions | |
Random | -0.388 |
dump | -0.388 |
Sham | -0.378 |
nam | -0.374 |
ASA | -0.360 |
Token | branch |
Token ID | 8478 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
orian | +2.345 |
kson | +2.206 |
orb | +2.197 |
rupal | +2.127 |
tale | +2.114 |
Neg logit contributions | |
Random | -2.024 |
dump | -2.019 |
nam | -1.956 |
Sham | -1.947 |
ASA | -1.878 |
Token | of |
Token ID | 286 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
orian | +2.247 |
kson | +2.103 |
orb | +2.096 |
rupal | +2.029 |
arious | +2.015 |
Neg logit contributions | |
dump | -2.228 |
Random | -2.221 |
nam | -2.113 |
Sham | -2.107 |
ASA | -2.064 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
orian | +1.723 |
orb | +1.641 |
kson | +1.632 |
rupal | +1.596 |
arious | +1.583 |
Neg logit contributions | |
dump | -1.080 |
Random | -1.065 |
nam | -1.006 |
Sham | -1.001 |
ASA | -0.963 |
Token | Foot |
Token ID | 7870 |
Feature activation | +9.04e+00 |
Pos logit contributions | |
orian | +1.656 |
orb | +1.570 |
kson | +1.564 |
rupal | +1.520 |
arious | +1.518 |
Neg logit contributions | |
dump | -1.120 |
Random | -1.117 |
nam | -1.067 |
Sham | -1.047 |
ASA | -1.001 |
Token | into |
Token ID | 656 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
orian | +6.107 |
orb | +5.514 |
kson | +5.506 |
tale | +5.352 |
rupal | +5.314 |
Neg logit contributions | |
dump | -6.116 |
Random | -6.051 |
ASA | -5.669 |
nam | -5.653 |
Sham | -5.623 |
Token | a |
Token ID | 257 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
dump | +0.953 |
Random | +0.950 |
Sham | +0.932 |
nam | +0.924 |
ASA | +0.880 |
Neg logit contributions | |
orian | -1.337 |
orb | -1.276 |
kson | -1.273 |
rupal | -1.236 |
oulos | -1.231 |
Token | criminal |
Token ID | 4301 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Sham | +1.380 |
dump | +1.379 |
Random | +1.371 |
nam | +1.358 |
ASA | +1.283 |
Neg logit contributions | |
orian | -2.013 |
kson | -1.929 |
orb | -1.929 |
rupal | -1.875 |
oulos | -1.868 |
Token | powerhouse |
Token ID | 34886 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
orian | +1.087 |
orb | +1.035 |
kson | +1.026 |
rupal | +1.002 |
arious | +0.995 |
Neg logit contributions | |
Random | -0.765 |
dump | -0.757 |
nam | -0.738 |
Sham | -0.736 |
ASA | -0.703 |
Token | involved |
Token ID | 2950 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
orian | +0.079 |
orb | +0.075 |
kson | +0.075 |
rupal | +0.073 |
oulos | +0.072 |
Neg logit contributions | |
dump | -0.069 |
Random | -0.069 |
Sham | -0.068 |
nam | -0.068 |
ASA | -0.065 |
Token | under |
Token ID | 739 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
dump | +0.591 |
Random | +0.588 |
Sham | +0.587 |
nam | +0.577 |
ASA | +0.548 |
Neg logit contributions | |
orian | -0.893 |
orb | -0.852 |
kson | -0.850 |
rupal | -0.830 |
oulos | -0.825 |
Token | study |
Token ID | 44517 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
orian | +1.982 |
orb | +1.903 |
kson | +1.882 |
oulos | +1.830 |
rupal | +1.829 |
Neg logit contributions | |
Random | -1.180 |
dump | -1.174 |
Sham | -1.156 |
nam | -1.134 |
ASA | -1.084 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Sham | +2.074 |
dump | +2.027 |
Random | +2.015 |
nam | +2.009 |
ASA | +1.909 |
Neg logit contributions | |
orian | -2.526 |
orb | -2.406 |
kson | -2.381 |
rupal | -2.353 |
oulos | -2.323 |
Token | Norm |
Token ID | 11220 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Sham | +1.168 |
dump | +1.163 |
Random | +1.160 |
nam | +1.143 |
ASA | +1.096 |
Neg logit contributions | |
orian | -1.305 |
orb | -1.243 |
kson | -1.234 |
rupal | -1.204 |
oulos | -1.192 |
Token | Van |
Token ID | 6656 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
orian | +1.072 |
orb | +1.020 |
kson | +1.020 |
rupal | +0.987 |
oulos | +0.985 |
Neg logit contributions | |
dump | -0.813 |
Random | -0.812 |
Sham | -0.799 |
nam | -0.791 |
ASA | -0.758 |
Token | Brock |
Token ID | 20501 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
Sham | +2.410 |
Random | +2.392 |
dump | +2.390 |
nam | +2.337 |
ASA | +2.220 |
Neg logit contributions | |
orian | -3.274 |
orb | -3.091 |
kson | -3.059 |
oulos | -3.053 |
rupal | -3.047 |
Token | lin |
Token ID | 2815 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
orian | +4.785 |
orb | +4.441 |
kson | +4.387 |
tale | +4.174 |
oulos | +4.073 |
Neg logit contributions | |
Random | -7.423 |
Sham | -7.355 |
dump | -7.278 |
nam | -7.019 |
ASA | -6.994 |
Token | . |
Token ID | 13 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
orian | +0.211 |
orb | +0.200 |
kson | +0.200 |
rupal | +0.193 |
oulos | +0.192 |
Neg logit contributions | |
dump | -0.196 |
Random | -0.195 |
Sham | -0.194 |
nam | -0.191 |
ASA | -0.184 |
Token |
|
Token ID | 198 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
orian | +0.390 |
orb | +0.371 |
kson | +0.370 |
rupal | +0.361 |
oulos | +0.359 |
Neg logit contributions | |
dump | -0.291 |
Random | -0.291 |
Sham | -0.291 |
nam | -0.285 |
ASA | -0.273 |
Token |
|
Token ID | 198 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
orian | +0.643 |
orb | +0.608 |
kson | +0.608 |
rupal | +0.588 |
oulos | +0.587 |
Neg logit contributions | |
dump | -0.608 |
Random | -0.608 |
Sham | -0.603 |
nam | -0.597 |
ASA | -0.570 |
Token | Far |
Token ID | 21428 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
orian | +0.588 |
orb | +0.565 |
kson | +0.560 |
rupal | +0.544 |
arious | +0.541 |
Neg logit contributions | |
dump | -0.376 |
Sham | -0.372 |
Random | -0.372 |
nam | -0.366 |
ASA | -0.351 |
Token | of |
Token ID | 286 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
orian | +2.440 |
kson | +2.313 |
orb | +2.310 |
rupal | +2.231 |
oulos | +2.217 |
Neg logit contributions | |
dump | -2.153 |
Random | -2.150 |
Sham | -2.108 |
nam | -2.093 |
ASA | -1.999 |
Token | the |
Token ID | 262 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
orian | +2.679 |
kson | +2.553 |
orb | +2.542 |
rupal | +2.467 |
agascar | +2.445 |
Neg logit contributions | |
Random | -2.282 |
dump | -2.270 |
Sham | -2.180 |
nam | -2.176 |
ASA | -2.072 |
Token | limestone |
Token ID | 48520 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
orian | +2.114 |
kson | +2.012 |
orb | +2.004 |
rupal | +1.943 |
oulos | +1.934 |
Neg logit contributions | |
dump | -1.456 |
Random | -1.450 |
Sham | -1.406 |
nam | -1.401 |
ASA | -1.325 |
Token | surrounding |
Token ID | 7346 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
orian | +2.923 |
kson | +2.789 |
orb | +2.782 |
rupal | +2.703 |
oulos | +2.663 |
Neg logit contributions | |
Random | -2.519 |
dump | -2.500 |
Sham | -2.458 |
nam | -2.453 |
ASA | -2.337 |
Token | the |
Token ID | 262 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
dump | +0.614 |
Random | +0.611 |
Sham | +0.607 |
nam | +0.599 |
ASA | +0.571 |
Neg logit contributions | |
orian | -0.832 |
orb | -0.793 |
kson | -0.792 |
rupal | -0.768 |
oulos | -0.766 |
Token | fossils |
Token ID | 34066 |
Feature activation | +8.94e+00 |
Pos logit contributions | |
orian | +1.407 |
kson | +1.337 |
orb | +1.329 |
rupal | +1.287 |
oulos | +1.280 |
Neg logit contributions | |
Random | -1.314 |
dump | -1.309 |
Sham | -1.281 |
nam | -1.277 |
ASA | -1.220 |
Token | , |
Token ID | 11 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
orian | +5.833 |
kson | +5.538 |
orb | +5.435 |
rupal | +5.306 |
oulos | +5.267 |
Neg logit contributions | |
Random | -6.251 |
dump | -6.127 |
nam | -5.989 |
Sham | -5.983 |
ASA | -5.778 |
Token | said |
Token ID | 531 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
orian | +1.213 |
kson | +1.137 |
orb | +1.131 |
rupal | +1.083 |
oulos | +1.079 |
Neg logit contributions | |
dump | -1.647 |
Random | -1.646 |
Sham | -1.622 |
nam | -1.607 |
ASA | -1.553 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
dump | +0.682 |
Random | +0.680 |
Sham | +0.678 |
nam | +0.670 |
ASA | +0.641 |
Neg logit contributions | |
orian | -0.770 |
orb | -0.732 |
kson | -0.731 |
rupal | -0.708 |
oulos | -0.705 |
Token | question |
Token ID | 1808 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
orian | +1.028 |
orb | +0.974 |
kson | +0.974 |
rupal | +0.941 |
oulos | +0.937 |
Neg logit contributions | |
dump | -0.839 |
Random | -0.836 |
Sham | -0.820 |
nam | -0.814 |
ASA | -0.777 |
Token | of |
Token ID | 286 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
dump | +1.099 |
Random | +1.096 |
Sham | +1.088 |
nam | +1.075 |
ASA | +1.029 |
Neg logit contributions | |
orian | -1.276 |
orb | -1.212 |
kson | -1.210 |
rupal | -1.172 |
oulos | -1.167 |
Token | " |
Token ID | 366 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Sham | +0.741 |
Random | +0.739 |
dump | +0.735 |
nam | +0.722 |
ASA | +0.696 |
Neg logit contributions | |
orian | -0.923 |
orb | -0.881 |
kson | -0.870 |
rupal | -0.854 |
oulos | -0.843 |
Token | A |
Token ID | 32 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Random | +1.305 |
dump | +1.283 |
Sham | +1.264 |
nam | +1.255 |
ASA | +1.178 |
Neg logit contributions | |
orian | -1.951 |
kson | -1.863 |
orb | -1.859 |
rupal | -1.817 |
oulos | -1.812 |
Token | movement |
Token ID | 3356 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
dump | +0.660 |
Random | +0.655 |
Sham | +0.652 |
nam | +0.647 |
ASA | +0.611 |
Neg logit contributions | |
orian | -0.885 |
kson | -0.842 |
orb | -0.841 |
rupal | -0.820 |
oulos | -0.811 |
Token | is |
Token ID | 318 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
orian | +2.236 |
orb | +2.120 |
kson | +2.113 |
rupal | +2.041 |
oulos | +2.037 |
Neg logit contributions | |
dump | -1.979 |
Random | -1.976 |
Sham | -1.952 |
nam | -1.936 |
ASA | -1.856 |
Token | a |
Token ID | 257 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
orian | +0.286 |
orb | +0.273 |
kson | +0.273 |
rupal | +0.265 |
oulos | +0.264 |
Neg logit contributions | |
dump | -0.200 |
Random | -0.199 |
Sham | -0.198 |
nam | -0.195 |
ASA | -0.186 |
Token | foot |
Token ID | 5898 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
orian | +0.164 |
orb | +0.156 |
kson | +0.155 |
rupal | +0.150 |
oulos | +0.150 |
Neg logit contributions | |
dump | -0.154 |
Random | -0.154 |
Sham | -0.153 |
nam | -0.151 |
ASA | -0.144 |
Token | that |
Token ID | 326 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
orian | +5.687 |
orb | +5.333 |
kson | +5.204 |
oulos | +5.118 |
arious | +5.075 |
Neg logit contributions | |
Random | -6.170 |
dump | -6.145 |
nam | -5.926 |
Sham | -5.832 |
ASA | -5.773 |
Token | must |
Token ID | 1276 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
orian | +1.512 |
kson | +1.439 |
orb | +1.436 |
rupal | +1.382 |
oulos | +1.381 |
Neg logit contributions | |
Random | -1.273 |
dump | -1.269 |
Sham | -1.244 |
nam | -1.235 |
ASA | -1.183 |
Token | not |
Token ID | 407 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
orian | +1.803 |
orb | +1.728 |
kson | +1.701 |
rupal | +1.660 |
oulos | +1.659 |
Neg logit contributions | |
Random | -1.498 |
dump | -1.486 |
Sham | -1.467 |
nam | -1.442 |
ASA | -1.387 |
Token | fade |
Token ID | 22100 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
orian | +0.201 |
orb | +0.192 |
kson | +0.191 |
rupal | +0.186 |
oulos | +0.186 |
Neg logit contributions | |
Random | -0.141 |
dump | -0.141 |
Sham | -0.139 |
nam | -0.137 |
ASA | -0.131 |
Token | away |
Token ID | 1497 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
Sham | +1.833 |
Random | +1.819 |
dump | +1.817 |
nam | +1.812 |
unres | +1.703 |
Neg logit contributions | |
orian | -2.659 |
kson | -2.554 |
orb | -2.550 |
rupal | -2.497 |
oulos | -2.459 |
Token | earthquakes |
Token ID | 29781 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
dump | +0.279 |
Sham | +0.277 |
Random | +0.277 |
nam | +0.274 |
ASA | +0.263 |
Neg logit contributions | |
orian | -0.289 |
orb | -0.275 |
kson | -0.272 |
rupal | -0.264 |
oulos | -0.263 |
Token | . |
Token ID | 13 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
orian | +2.889 |
orb | +2.754 |
kson | +2.719 |
rupal | +2.635 |
oulos | +2.626 |
Neg logit contributions | |
dump | -2.894 |
Random | -2.892 |
nam | -2.833 |
Sham | -2.809 |
ASA | -2.721 |
Token | Oklahoma |
Token ID | 10433 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
orian | +0.346 |
orb | +0.330 |
kson | +0.328 |
rupal | +0.319 |
oulos | +0.317 |
Neg logit contributions | |
dump | -0.273 |
Random | -0.273 |
Sham | -0.272 |
nam | -0.267 |
ASA | -0.256 |
Token | , |
Token ID | 11 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
dump | +0.739 |
Random | +0.736 |
Sham | +0.732 |
nam | +0.722 |
ASA | +0.691 |
Neg logit contributions | |
orian | -0.923 |
orb | -0.880 |
kson | -0.877 |
rupal | -0.851 |
oulos | -0.847 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
dump | +0.112 |
Random | +0.112 |
Sham | +0.111 |
nam | +0.109 |
ASA | +0.105 |
Neg logit contributions | |
orian | -0.150 |
orb | -0.143 |
kson | -0.143 |
rupal | -0.139 |
oulos | -0.138 |
Token | seism |
Token ID | 30518 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
orian | +0.808 |
kson | +0.768 |
orb | +0.768 |
rupal | +0.743 |
oulos | +0.742 |
Neg logit contributions | |
Random | -0.603 |
dump | -0.603 |
Sham | -0.592 |
nam | -0.588 |
ASA | -0.558 |
Token | ically |
Token ID | 1146 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
orian | +3.807 |
orb | +3.398 |
kson | +3.120 |
arious | +3.081 |
uitive | +2.936 |
Neg logit contributions | |
Random | -8.278 |
Sham | -8.155 |
dump | -8.083 |
nam | -8.036 |
ASA | -7.876 |
Token | inactive |
Token ID | 28621 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
orian | +6.054 |
orb | +5.870 |
kson | +5.811 |
rupal | +5.527 |
oulos | +5.506 |
Neg logit contributions | |
Random | -6.506 |
dump | -6.489 |
nam | -6.073 |
Sham | -6.040 |
ASA | -5.870 |
Token | area |
Token ID | 1989 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
orian | +3.675 |
kson | +3.509 |
orb | +3.482 |
arious | +3.332 |
oulos | +3.330 |
Neg logit contributions | |
Random | -3.239 |
dump | -3.203 |
nam | -3.103 |
Sham | -3.078 |
ASA | -2.895 |
Token | before |
Token ID | 878 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
orian | +1.165 |
kson | +1.106 |
orb | +1.105 |
rupal | +1.069 |
oulos | +1.058 |
Neg logit contributions | |
Random | -1.043 |
dump | -1.042 |
Sham | -1.027 |
nam | -1.016 |
ASA | -0.975 |
Token | gas |
Token ID | 3623 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
orian | +2.936 |
kson | +2.779 |
orb | +2.770 |
oulos | +2.707 |
rupal | +2.697 |
Neg logit contributions | |
Random | -2.454 |
dump | -2.446 |
nam | -2.390 |
Sham | -2.361 |
ASA | -2.248 |
Token | not |
Token ID | 1662 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
orian | +2.788 |
orb | +2.686 |
kson | +2.590 |
tale | +2.541 |
rupal | +2.528 |
Neg logit contributions | |
Sham | -2.333 |
dump | -2.318 |
Random | -2.315 |
nam | -2.261 |
ASA | -2.212 |
Token | ch |
Token ID | 354 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
orian | +0.480 |
kson | +0.455 |
orb | +0.453 |
rupal | +0.438 |
oulos | +0.437 |
Neg logit contributions | |
dump | -0.476 |
Random | -0.471 |
nam | -0.471 |
Sham | -0.465 |
ASA | -0.439 |
Token | studio |
Token ID | 8034 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
orian | +0.945 |
kson | +0.898 |
orb | +0.896 |
rupal | +0.867 |
oulos | +0.864 |
Neg logit contributions | |
dump | -0.718 |
Random | -0.716 |
Sham | -0.703 |
nam | -0.695 |
ASA | -0.664 |
Token | specializing |
Token ID | 40847 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
Sham | +2.170 |
dump | +2.155 |
nam | +2.143 |
Random | +2.137 |
ASA | +2.025 |
Neg logit contributions | |
orian | -2.667 |
orb | -2.558 |
kson | -2.529 |
rupal | -2.484 |
oulos | -2.471 |
Token | in |
Token ID | 287 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
dump | +0.453 |
Random | +0.452 |
Sham | +0.444 |
nam | +0.439 |
ASA | +0.422 |
Neg logit contributions | |
orian | -0.547 |
kson | -0.521 |
orb | -0.520 |
rupal | -0.503 |
oulos | -0.501 |
Token | ecc |
Token ID | 21399 |
Feature activation | +8.61e+00 |
Pos logit contributions | |
orian | +0.284 |
kson | +0.270 |
orb | +0.270 |
rupal | +0.261 |
oulos | +0.260 |
Neg logit contributions | |
dump | -0.217 |
Random | -0.217 |
Sham | -0.213 |
nam | -0.210 |
ASA | -0.201 |
Token | les |
Token ID | 829 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
orian | +4.346 |
orb | +3.782 |
arious | +3.664 |
kson | +3.607 |
rupal | +3.517 |
Neg logit contributions | |
Sham | -7.572 |
Random | -7.557 |
dump | -7.543 |
ASA | -7.373 |
unres | -7.302 |
Token | ial |
Token ID | 498 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
orian | +0.425 |
orb | +0.404 |
kson | +0.403 |
rupal | +0.391 |
oulos | +0.389 |
Neg logit contributions | |
dump | -0.353 |
Random | -0.352 |
Sham | -0.349 |
nam | -0.345 |
ASA | -0.330 |
Token | art |
Token ID | 1242 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
dump | +0.529 |
Random | +0.528 |
Sham | +0.527 |
nam | +0.521 |
ASA | +0.493 |
Neg logit contributions | |
orian | -0.760 |
orb | -0.729 |
kson | -0.726 |
rupal | -0.706 |
oulos | -0.703 |
Token | had |
Token ID | 550 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
orian | +0.454 |
orb | +0.431 |
kson | +0.430 |
rupal | +0.417 |
oulos | +0.415 |
Neg logit contributions | |
dump | -0.397 |
Random | -0.396 |
Sham | -0.392 |
nam | -0.387 |
ASA | -0.371 |
Token | drawn |
Token ID | 7428 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
dump | +1.039 |
Random | +1.037 |
Sham | +1.036 |
nam | +1.029 |
ASA | +0.976 |
Neg logit contributions | |
orian | -1.290 |
orb | -1.226 |
kson | -1.218 |
rupal | -1.189 |
oulos | -1.183 |
Token | The |
Token ID | 383 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
orian | +0.649 |
orb | +0.618 |
kson | +0.615 |
rupal | +0.598 |
oulos | +0.594 |
Neg logit contributions | |
Random | -0.537 |
dump | -0.535 |
Sham | -0.535 |
nam | -0.526 |
ASA | -0.504 |
Token | electric |
Token ID | 5186 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
orian | +0.598 |
orb | +0.569 |
kson | +0.567 |
oulos | +0.547 |
rupal | +0.547 |
Neg logit contributions | |
dump | -0.526 |
Random | -0.522 |
Sham | -0.513 |
nam | -0.511 |
ASA | -0.486 |
Token | applause |
Token ID | 28445 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
orian | +2.002 |
orb | +1.910 |
kson | +1.899 |
rupal | +1.840 |
arious | +1.838 |
Neg logit contributions | |
dump | -1.552 |
Random | -1.548 |
Sham | -1.528 |
nam | -1.508 |
ASA | -1.438 |
Token | inside |
Token ID | 2641 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
dump | +2.987 |
Sham | +2.984 |
Random | +2.962 |
nam | +2.902 |
unres | +2.777 |
Neg logit contributions | |
orian | -3.615 |
orb | -3.430 |
kson | -3.424 |
rupal | -3.374 |
natureconservancy | -3.366 |
Token | the |
Token ID | 262 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
dump | +0.110 |
Random | +0.110 |
Sham | +0.109 |
nam | +0.107 |
ASA | +0.102 |
Neg logit contributions | |
orian | -0.146 |
orb | -0.139 |
kson | -0.139 |
rupal | -0.135 |
oulos | -0.134 |
Token | Ecc |
Token ID | 38308 |
Feature activation | +8.58e+00 |
Pos logit contributions | |
orian | +0.757 |
kson | +0.720 |
orb | +0.719 |
rupal | +0.692 |
oulos | +0.692 |
Neg logit contributions | |
dump | -0.611 |
Random | -0.608 |
nam | -0.594 |
Sham | -0.593 |
ASA | -0.561 |
Token | les |
Token ID | 829 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
orian | +5.789 |
orb | +5.430 |
kson | +5.284 |
arious | +5.183 |
rupal | +5.112 |
Neg logit contributions | |
dump | -6.036 |
Random | -5.950 |
Sham | -5.917 |
nam | -5.748 |
ASA | -5.694 |
Token | after |
Token ID | 706 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
orian | +0.711 |
orb | +0.680 |
kson | +0.679 |
rupal | +0.661 |
oulos | +0.658 |
Neg logit contributions | |
Random | -0.509 |
dump | -0.509 |
Sham | -0.506 |
nam | -0.500 |
ASA | -0.474 |
Token | � |
Token ID | 564 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Sham | +1.473 |
Random | +1.472 |
dump | +1.468 |
nam | +1.443 |
ASA | +1.378 |
Neg logit contributions | |
orian | -1.923 |
kson | -1.830 |
orb | -1.828 |
rupal | -1.778 |
oulos | -1.764 |
Token | � |
Token ID | 250 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
orian | +1.612 |
orb | +1.539 |
kson | +1.526 |
rupal | +1.480 |
arious | +1.471 |
Neg logit contributions | |
dump | -1.110 |
Random | -1.100 |
Sham | -1.099 |
nam | -1.074 |
ASA | -1.031 |
Token | Manchester |
Token ID | 40744 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
orian | +0.209 |
orb | +0.201 |
kson | +0.200 |
rupal | +0.195 |
oulos | +0.194 |
Neg logit contributions | |
dump | -0.107 |
Random | -0.106 |
Sham | -0.105 |
nam | -0.103 |
ASA | -0.098 |
Token | all |
Token ID | 439 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
orian | +2.731 |
orb | +2.583 |
kson | +2.542 |
rupal | +2.444 |
tale | +2.426 |
Neg logit contributions | |
Random | -3.065 |
Sham | -3.041 |
dump | -3.038 |
nam | -2.998 |
ASA | -2.930 |
Token | that |
Token ID | 326 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
orian | +0.995 |
orb | +0.943 |
kson | +0.939 |
rupal | +0.914 |
oulos | +0.906 |
Neg logit contributions | |
dump | -0.884 |
Random | -0.883 |
Sham | -0.871 |
nam | -0.862 |
ASA | -0.830 |
Token | stuff |
Token ID | 3404 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
orian | +1.392 |
kson | +1.323 |
orb | +1.321 |
rupal | +1.278 |
oulos | +1.272 |
Neg logit contributions | |
Random | -1.215 |
dump | -1.210 |
Sham | -1.193 |
nam | -1.186 |
ASA | -1.136 |
Token | has |
Token ID | 468 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Random | +0.127 |
dump | +0.127 |
Sham | +0.125 |
nam | +0.124 |
ASA | +0.119 |
Neg logit contributions | |
orian | -0.140 |
orb | -0.133 |
kson | -0.133 |
rupal | -0.128 |
oulos | -0.127 |
Token | an |
Token ID | 281 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
orian | +0.876 |
kson | +0.837 |
orb | +0.833 |
rupal | +0.802 |
oulos | +0.799 |
Neg logit contributions | |
dump | -0.805 |
Random | -0.805 |
Sham | -0.790 |
nam | -0.786 |
ASA | -0.756 |
Token | impact |
Token ID | 2928 |
Feature activation | +8.50e+00 |
Pos logit contributions | |
orian | +0.230 |
orb | +0.218 |
kson | +0.218 |
rupal | +0.210 |
oulos | +0.210 |
Neg logit contributions | |
dump | -0.227 |
Random | -0.226 |
Sham | -0.224 |
nam | -0.222 |
ASA | -0.213 |
Token | on |
Token ID | 319 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
orian | +4.590 |
kson | +4.316 |
orb | +4.277 |
rupal | +4.073 |
tale | +4.066 |
Neg logit contributions | |
dump | -6.803 |
Random | -6.799 |
Sham | -6.573 |
ASA | -6.536 |
nam | -6.510 |
Token | our |
Token ID | 674 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
orian | +2.497 |
kson | +2.362 |
orb | +2.341 |
rupal | +2.277 |
oulos | +2.266 |
Neg logit contributions | |
dump | -2.116 |
Random | -2.104 |
Sham | -2.049 |
nam | -2.040 |
ASA | -1.953 |
Token | long |
Token ID | 890 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
orian | +1.165 |
kson | +1.109 |
orb | +1.105 |
rupal | +1.068 |
oulos | +1.068 |
Neg logit contributions | |
dump | -0.903 |
Random | -0.899 |
Sham | -0.885 |
nam | -0.874 |
ASA | -0.834 |
Token | - |
Token ID | 12 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
dump | +0.267 |
Random | +0.266 |
Sham | +0.264 |
nam | +0.261 |
ASA | +0.248 |
Neg logit contributions | |
orian | -0.373 |
orb | -0.356 |
kson | -0.355 |
rupal | -0.346 |
oulos | -0.344 |
Token | term |
Token ID | 4354 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
orian | +0.989 |
orb | +0.935 |
kson | +0.919 |
rupal | +0.888 |
arious | +0.886 |
Neg logit contributions | |
Random | -1.115 |
dump | -1.109 |
Sham | -1.103 |
nam | -1.087 |
ASA | -1.053 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
orian | +1.108 |
orb | +1.054 |
kson | +1.049 |
rupal | +1.012 |
oulos | +1.010 |
Neg logit contributions | |
Random | -1.035 |
dump | -1.032 |
Sham | -1.018 |
nam | -1.014 |
ASA | -0.970 |
Token | as |
Token ID | 355 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
orian | +0.853 |
orb | +0.811 |
kson | +0.809 |
rupal | +0.782 |
oulos | +0.781 |
Neg logit contributions | |
dump | -0.677 |
Random | -0.676 |
Sham | -0.667 |
nam | -0.662 |
ASA | -0.632 |
Token | Toronto |
Token ID | 6586 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
orian | +0.944 |
orb | +0.898 |
kson | +0.898 |
rupal | +0.866 |
oulos | +0.866 |
Neg logit contributions | |
dump | -0.783 |
Random | -0.781 |
Sham | -0.769 |
nam | -0.766 |
ASA | -0.733 |
Token | Police |
Token ID | 4287 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
orian | +2.023 |
orb | +1.907 |
kson | +1.906 |
oulos | +1.849 |
rupal | +1.847 |
Neg logit contributions | |
Random | -1.634 |
dump | -1.633 |
Sham | -1.600 |
nam | -1.591 |
ASA | -1.527 |
Token | Chief |
Token ID | 5953 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
orian | +2.343 |
orb | +2.210 |
kson | +2.192 |
oulos | +2.122 |
rupal | +2.121 |
Neg logit contributions | |
dump | -1.969 |
Random | -1.969 |
Sham | -1.917 |
nam | -1.910 |
ASA | -1.821 |
Token | Bill |
Token ID | 3941 |
Feature activation | +8.47e+00 |
Pos logit contributions | |
orian | +1.700 |
kson | +1.590 |
orb | +1.588 |
rupal | +1.519 |
oulos | +1.518 |
Neg logit contributions | |
dump | -2.437 |
Random | -2.427 |
Sham | -2.401 |
nam | -2.386 |
ASA | -2.309 |
Token | Blair |
Token ID | 18520 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
orian | +5.879 |
kson | +5.742 |
arious | +5.606 |
tale | +5.474 |
orb | +5.454 |
Neg logit contributions | |
nam | -5.505 |
dump | -5.483 |
Random | -5.406 |
unres | -5.261 |
ASA | -5.187 |
Token | confirmed |
Token ID | 4999 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
orian | +0.667 |
orb | +0.632 |
kson | +0.630 |
rupal | +0.610 |
oulos | +0.606 |
Neg logit contributions | |
dump | -0.669 |
Random | -0.667 |
Sham | -0.662 |
nam | -0.656 |
ASA | -0.628 |
Token | in |
Token ID | 287 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
orian | +1.808 |
orb | +1.711 |
kson | +1.706 |
oulos | +1.645 |
rupal | +1.645 |
Neg logit contributions | |
dump | -1.689 |
Random | -1.688 |
Sham | -1.666 |
nam | -1.656 |
ASA | -1.589 |
Token | October |
Token ID | 3267 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
orian | +0.725 |
orb | +0.686 |
kson | +0.685 |
rupal | +0.665 |
arious | +0.663 |
Neg logit contributions | |
Random | -0.599 |
dump | -0.599 |
Sham | -0.588 |
nam | -0.586 |
ASA | -0.559 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
orian | +1.655 |
kson | +1.562 |
orb | +1.560 |
rupal | +1.507 |
oulos | +1.500 |
Neg logit contributions | |
dump | -1.754 |
Random | -1.750 |
Sham | -1.731 |
nam | -1.714 |
ASA | -1.651 |
Token | experiences |
Token ID | 6461 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
orian | +1.690 |
kson | +1.610 |
orb | +1.595 |
oulos | +1.546 |
rupal | +1.537 |
Neg logit contributions | |
dump | -1.415 |
Random | -1.412 |
Sham | -1.375 |
nam | -1.366 |
ASA | -1.286 |
Token | of |
Token ID | 286 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
orian | +2.377 |
kson | +2.230 |
orb | +2.213 |
rupal | +2.159 |
oulos | +2.138 |
Neg logit contributions | |
dump | -2.445 |
Random | -2.421 |
Sham | -2.380 |
nam | -2.361 |
ASA | -2.276 |
Token | college |
Token ID | 4152 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
orian | +1.745 |
kson | +1.660 |
orb | +1.647 |
rupal | +1.598 |
oulos | +1.594 |
Neg logit contributions | |
dump | -1.563 |
Random | -1.551 |
Sham | -1.522 |
nam | -1.518 |
ASA | -1.434 |
Token | students |
Token ID | 2444 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
orian | +0.927 |
orb | +0.880 |
kson | +0.879 |
rupal | +0.853 |
oulos | +0.850 |
Neg logit contributions | |
dump | -0.802 |
Random | -0.797 |
Sham | -0.787 |
nam | -0.778 |
ASA | -0.744 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
orian | +0.079 |
orb | +0.075 |
kson | +0.074 |
rupal | +0.071 |
oulos | +0.071 |
Neg logit contributions | |
dump | -0.093 |
Random | -0.092 |
Sham | -0.092 |
nam | -0.091 |
ASA | -0.088 |
Token | first |
Token ID | 717 |
Feature activation | +8.42e+00 |
Pos logit contributions | |
orian | +1.136 |
orb | +1.077 |
kson | +1.077 |
rupal | +1.044 |
oulos | +1.042 |
Neg logit contributions | |
dump | -0.962 |
Random | -0.958 |
Sham | -0.945 |
nam | -0.936 |
ASA | -0.895 |
Token | year |
Token ID | 614 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
orian | +5.668 |
orb | +5.369 |
kson | +5.248 |
oulos | +5.245 |
rupal | +5.206 |
Neg logit contributions | |
dump | -5.658 |
Random | -5.593 |
Sham | -5.306 |
nam | -5.272 |
ASA | -5.048 |
Token | students |
Token ID | 2444 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
orian | +1.232 |
orb | +1.169 |
kson | +1.167 |
rupal | +1.129 |
oulos | +1.126 |
Neg logit contributions | |
dump | -1.095 |
Random | -1.090 |
Sham | -1.076 |
nam | -1.067 |
ASA | -1.017 |
Token | on |
Token ID | 319 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
orian | +1.552 |
orb | +1.465 |
kson | +1.464 |
rupal | +1.414 |
oulos | +1.408 |
Neg logit contributions | |
dump | -1.629 |
Random | -1.621 |
Sham | -1.602 |
nam | -1.587 |
ASA | -1.526 |
Token | this |
Token ID | 428 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
orian | +1.823 |
kson | +1.721 |
orb | +1.717 |
rupal | +1.666 |
oulos | +1.656 |
Neg logit contributions | |
dump | -1.730 |
Random | -1.712 |
nam | -1.681 |
Sham | -1.679 |
ASA | -1.594 |
Token | campus |
Token ID | 7611 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
orian | +0.259 |
orb | +0.245 |
kson | +0.245 |
rupal | +0.237 |
oulos | +0.236 |
Neg logit contributions | |
dump | -0.258 |
Random | -0.257 |
Sham | -0.255 |
nam | -0.253 |
ASA | -0.243 |
Token | Jeff |
Token ID | 5502 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
orian | +0.948 |
kson | +0.904 |
orb | +0.902 |
oulos | +0.874 |
rupal | +0.873 |
Neg logit contributions | |
dump | -0.699 |
Random | -0.699 |
Sham | -0.688 |
nam | -0.683 |
ASA | -0.648 |
Token | Baker |
Token ID | 14372 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
orian | +2.485 |
kson | +2.369 |
orb | +2.344 |
rupal | +2.265 |
arious | +2.254 |
Neg logit contributions | |
dump | -2.496 |
Random | -2.463 |
Sham | -2.430 |
nam | -2.427 |
ASA | -2.341 |
Token | , |
Token ID | 11 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
orian | +0.741 |
kson | +0.703 |
orb | +0.703 |
rupal | +0.679 |
oulos | +0.679 |
Neg logit contributions | |
dump | -0.655 |
Random | -0.652 |
Sham | -0.647 |
nam | -0.639 |
ASA | -0.612 |
Token | chief |
Token ID | 4039 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
orian | +0.183 |
orb | +0.174 |
kson | +0.174 |
rupal | +0.168 |
oulos | +0.168 |
Neg logit contributions | |
dump | -0.143 |
Random | -0.142 |
Sham | -0.141 |
nam | -0.140 |
ASA | -0.133 |
Token | of |
Token ID | 286 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
orian | +1.286 |
orb | +1.220 |
kson | +1.218 |
rupal | +1.180 |
oulos | +1.179 |
Neg logit contributions | |
dump | -1.118 |
Random | -1.111 |
Sham | -1.100 |
nam | -1.092 |
ASA | -1.038 |
Token | police |
Token ID | 1644 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
orian | +2.363 |
orb | +2.258 |
kson | +2.244 |
rupal | +2.178 |
oulos | +2.177 |
Neg logit contributions | |
dump | -1.943 |
Random | -1.938 |
Sham | -1.897 |
nam | -1.893 |
ASA | -1.784 |
Token | , |
Token ID | 11 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
orian | +5.375 |
orb | +5.122 |
kson | +4.902 |
oulos | +4.837 |
helicop | +4.794 |
Neg logit contributions | |
dump | -5.857 |
Random | -5.810 |
nam | -5.665 |
Sham | -5.659 |
ASA | -5.390 |
Token | said |
Token ID | 531 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
orian | +2.460 |
kson | +2.327 |
orb | +2.321 |
oulos | +2.256 |
rupal | +2.234 |
Neg logit contributions | |
dump | -2.413 |
Random | -2.397 |
Sham | -2.359 |
nam | -2.352 |
ASA | -2.243 |
Token | the |
Token ID | 262 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
orian | +0.535 |
orb | +0.510 |
kson | +0.509 |
rupal | +0.494 |
oulos | +0.492 |
Neg logit contributions | |
dump | -0.406 |
Random | -0.404 |
Sham | -0.401 |
nam | -0.396 |
ASA | -0.378 |
Token | man |
Token ID | 582 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
orian | +0.990 |
kson | +0.945 |
orb | +0.943 |
oulos | +0.914 |
rupal | +0.913 |
Neg logit contributions | |
dump | -0.706 |
Random | -0.702 |
Sham | -0.693 |
nam | -0.687 |
ASA | -0.651 |
Token | was |
Token ID | 373 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
dump | +0.619 |
Random | +0.619 |
Sham | +0.617 |
nam | +0.608 |
ASA | +0.581 |
Neg logit contributions | |
orian | -0.724 |
orb | -0.689 |
kson | -0.684 |
rupal | -0.665 |
arious | -0.661 |
Token | a |
Token ID | 257 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
orian | +1.504 |
kson | +1.428 |
orb | +1.421 |
rupal | +1.369 |
arious | +1.364 |
Neg logit contributions | |
dump | -1.372 |
Random | -1.361 |
Sham | -1.338 |
nam | -1.333 |
ASA | -1.272 |
Token | new |
Token ID | 649 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
orian | +0.500 |
kson | +0.478 |
orb | +0.478 |
rupal | +0.463 |
oulos | +0.462 |
Neg logit contributions | |
dump | -0.328 |
Random | -0.324 |
Sham | -0.320 |
nam | -0.318 |
ASA | -0.302 |
Token | study |
Token ID | 2050 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
Random | +2.018 |
Sham | +2.010 |
dump | +1.950 |
nam | +1.892 |
ASA | +1.837 |
Neg logit contributions | |
orian | -4.833 |
orb | -4.663 |
kson | -4.635 |
rupal | -4.607 |
oulos | -4.539 |
Token | Sven |
Token ID | 44611 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
Sham | +3.699 |
Random | +3.658 |
dump | +3.612 |
nam | +3.586 |
ASA | +3.417 |
Neg logit contributions | |
orian | -5.287 |
orb | -5.044 |
kson | -5.033 |
arious | -4.985 |
rupal | -4.979 |
Token | D |
Token ID | 360 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
orian | +0.456 |
kson | +0.436 |
orb | +0.435 |
rupal | +0.420 |
oulos | +0.419 |
Neg logit contributions | |
dump | -0.347 |
Random | -0.346 |
Sham | -0.342 |
nam | -0.338 |
ASA | -0.323 |
Token | ref |
Token ID | 5420 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
dump | +0.415 |
Random | +0.414 |
Sham | +0.411 |
nam | +0.407 |
ASA | +0.390 |
Neg logit contributions | |
orian | -0.432 |
orb | -0.409 |
kson | -0.409 |
rupal | -0.396 |
oulos | -0.393 |
Token | ahl |
Token ID | 15668 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
orian | +6.036 |
kson | +5.724 |
orb | +5.722 |
oulos | +5.464 |
arious | +5.372 |
Neg logit contributions | |
Random | -5.554 |
dump | -5.430 |
Sham | -5.316 |
ASA | -5.148 |
unres | -5.104 |
Token | from |
Token ID | 422 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
dump | +0.961 |
Random | +0.960 |
Sham | +0.953 |
nam | +0.942 |
ASA | +0.900 |
Neg logit contributions | |
orian | -1.132 |
orb | -1.076 |
kson | -1.072 |
rupal | -1.043 |
oulos | -1.036 |
Token | the |
Token ID | 262 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
dump | +0.168 |
Random | +0.167 |
Sham | +0.165 |
nam | +0.163 |
ASA | +0.155 |
Neg logit contributions | |
orian | -0.229 |
orb | -0.218 |
kson | -0.218 |
rupal | -0.211 |
oulos | -0.211 |
Token | Max |
Token ID | 5436 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
dump | +0.516 |
Random | +0.513 |
Sham | +0.506 |
nam | +0.502 |
ASA | +0.476 |
Neg logit contributions | |
orian | -0.735 |
orb | -0.701 |
kson | -0.701 |
rupal | -0.678 |
oulos | -0.677 |
Token | Plan |
Token ID | 5224 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
orian | +0.287 |
orb | +0.273 |
kson | +0.272 |
rupal | +0.261 |
oulos | +0.260 |
Neg logit contributions | |
dump | -0.277 |
Random | -0.276 |
Sham | -0.272 |
nam | -0.272 |
ASA | -0.261 |
Token | Far |
Token ID | 6755 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
orian | +1.942 |
orb | +1.861 |
kson | +1.859 |
rupal | +1.811 |
oulos | +1.805 |
Neg logit contributions | |
dump | -1.064 |
Random | -1.062 |
Sham | -1.052 |
nam | -1.033 |
ASA | -0.975 |
Token | rah |
Token ID | 11392 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
dump | +0.141 |
nam | +0.138 |
Random | +0.138 |
Sham | +0.138 |
ASA | +0.119 |
Neg logit contributions | |
orian | -0.379 |
kson | -0.370 |
orb | -0.365 |
helicop | -0.365 |
oulos | -0.362 |
Token | W |
Token ID | 370 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
orian | +2.183 |
orb | +2.097 |
kson | +2.093 |
rupal | +2.044 |
oulos | +2.038 |
Neg logit contributions | |
dump | -1.013 |
Random | -1.009 |
Sham | -1.000 |
nam | -0.978 |
ASA | -0.917 |
Token | ether |
Token ID | 6750 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
orian | +1.112 |
kson | +1.066 |
orb | +1.055 |
rupal | +1.038 |
oulos | +1.032 |
Neg logit contributions | |
dump | -0.682 |
Random | -0.673 |
nam | -0.665 |
Sham | -0.664 |
ASA | -0.618 |
Token | s |
Token ID | 82 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
orian | +2.779 |
kson | +2.660 |
orb | +2.654 |
rupal | +2.555 |
oulos | +2.541 |
Neg logit contributions | |
Random | -2.193 |
dump | -2.189 |
Sham | -2.170 |
nam | -2.117 |
ASA | -2.061 |
Token | Mysteries |
Token ID | 28298 |
Feature activation | +8.37e+00 |
Pos logit contributions | |
orian | +3.342 |
kson | +3.185 |
orb | +3.178 |
rupal | +3.083 |
oulos | +3.068 |
Neg logit contributions | |
dump | -2.284 |
Random | -2.267 |
Sham | -2.239 |
nam | -2.216 |
ASA | -2.115 |
Token | , |
Token ID | 11 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
orian | +5.438 |
orb | +5.176 |
kson | +5.138 |
tale | +4.956 |
rupal | +4.910 |
Neg logit contributions | |
dump | -5.852 |
Random | -5.723 |
Sham | -5.685 |
nam | -5.637 |
unres | -5.448 |
Token | comic |
Token ID | 9048 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
orian | +1.845 |
orb | +1.716 |
kson | +1.713 |
rupal | +1.644 |
oulos | +1.613 |
Neg logit contributions | |
dump | -2.722 |
Random | -2.699 |
Sham | -2.685 |
nam | -2.667 |
ASA | -2.575 |
Token | book |
Token ID | 1492 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
orian | +3.093 |
orb | +2.934 |
kson | +2.896 |
rupal | +2.808 |
tale | +2.802 |
Neg logit contributions | |
Random | -3.157 |
dump | -3.154 |
Sham | -3.103 |
nam | -3.064 |
ASA | -2.960 |
Token | short |
Token ID | 1790 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
orian | +3.806 |
orb | +3.636 |
kson | +3.622 |
rupal | +3.528 |
oulos | +3.506 |
Neg logit contributions | |
dump | -2.342 |
Random | -2.329 |
Sham | -2.281 |
nam | -2.263 |
ASA | -2.150 |
Token | stories |
Token ID | 3923 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
orian | +1.640 |
kson | +1.560 |
orb | +1.545 |
rupal | +1.489 |
tale | +1.474 |
Neg logit contributions | |
dump | -2.003 |
Random | -1.995 |
Sham | -1.957 |
nam | -1.946 |
ASA | -1.882 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
orian | +0.902 |
orb | +0.855 |
kson | +0.853 |
rupal | +0.819 |
arious | +0.811 |
Neg logit contributions | |
dump | -1.007 |
Random | -1.003 |
Sham | -0.982 |
nam | -0.976 |
ASA | -0.937 |
Token | and |
Token ID | 290 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
orian | +1.290 |
orb | +1.228 |
kson | +1.221 |
rupal | +1.184 |
oulos | +1.182 |
Neg logit contributions | |
dump | -1.188 |
Random | -1.187 |
Sham | -1.163 |
nam | -1.147 |
ASA | -1.089 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
orian | +1.214 |
kson | +1.156 |
orb | +1.155 |
rupal | +1.114 |
oulos | +1.113 |
Neg logit contributions | |
dump | -1.014 |
Random | -1.011 |
Sham | -0.990 |
nam | -0.982 |
ASA | -0.930 |
Token | , |
Token ID | 11 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
dump | +0.446 |
Random | +0.445 |
Sham | +0.440 |
nam | +0.435 |
ASA | +0.415 |
Neg logit contributions | |
orian | -0.507 |
orb | -0.482 |
kson | -0.481 |
rupal | -0.466 |
oulos | -0.464 |
Token | the |
Token ID | 262 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
orian | +0.491 |
kson | +0.466 |
orb | +0.466 |
rupal | +0.452 |
oulos | +0.449 |
Neg logit contributions | |
dump | -0.423 |
Random | -0.421 |
Sham | -0.415 |
nam | -0.411 |
ASA | -0.390 |
Token | Geological |
Token ID | 34246 |
Feature activation | +8.37e+00 |
Pos logit contributions | |
orian | +0.934 |
kson | +0.893 |
orb | +0.892 |
oulos | +0.862 |
rupal | +0.859 |
Neg logit contributions | |
dump | -0.707 |
Random | -0.705 |
Sham | -0.688 |
nam | -0.686 |
ASA | -0.638 |
Token | Society |
Token ID | 7023 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
orian | +5.550 |
kson | +5.352 |
orb | +5.188 |
rupal | +5.010 |
tale | +4.985 |
Neg logit contributions | |
dump | -5.917 |
Random | -5.805 |
nam | -5.665 |
Sham | -5.582 |
� | -5.419 |
Token | of |
Token ID | 286 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
orian | +3.433 |
orb | +3.277 |
kson | +3.221 |
rupal | +3.128 |
oulos | +3.062 |
Neg logit contributions | |
dump | -3.671 |
Random | -3.597 |
Sham | -3.554 |
nam | -3.516 |
Gh | -3.335 |
Token | America |
Token ID | 2253 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
dump | +0.137 |
Random | +0.136 |
Sham | +0.134 |
nam | +0.133 |
ASA | +0.126 |
Neg logit contributions | |
orian | -0.204 |
orb | -0.195 |
kson | -0.195 |
rupal | -0.189 |
oulos | -0.188 |
Token | in |
Token ID | 287 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
dump | +0.117 |
Random | +0.117 |
Sham | +0.116 |
nam | +0.114 |
ASA | +0.109 |
Neg logit contributions | |
orian | -0.145 |
orb | -0.138 |
kson | -0.138 |
rupal | -0.134 |
oulos | -0.133 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
orian | +1.090 |
orb | +1.023 |
kson | +1.020 |
rupal | +0.975 |
oulos | +0.970 |
Neg logit contributions | |
dump | -1.519 |
Random | -1.514 |
Sham | -1.499 |
nam | -1.487 |
ASA | -1.436 |
Token | open |
Token ID | 1280 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
dump | +1.701 |
Sham | +1.671 |
nam | +1.653 |
Random | +1.644 |
ASA | +1.577 |
Neg logit contributions | |
orian | -1.862 |
kson | -1.777 |
orb | -1.747 |
rupal | -1.727 |
oulos | -1.718 |
Token | my |
Token ID | 616 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
dump | +1.578 |
Sham | +1.575 |
Random | +1.574 |
nam | +1.548 |
ASA | +1.488 |
Neg logit contributions | |
orian | -1.725 |
kson | -1.644 |
orb | -1.638 |
rupal | -1.589 |
oulos | -1.585 |
Token | mouth |
Token ID | 5422 |
Feature activation | -8.15e+00 |
Pos logit contributions | |
Sham | +2.040 |
dump | +2.037 |
Random | +2.033 |
nam | +1.999 |
ASA | +1.892 |
Neg logit contributions | |
orian | -3.366 |
kson | -3.236 |
orb | -3.220 |
rupal | -3.162 |
oulos | -3.146 |
Token | and |
Token ID | 290 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
dump | +4.638 |
nam | +4.619 |
Sham | +4.594 |
Random | +4.563 |
unres | +4.485 |
Neg logit contributions | |
orian | -6.323 |
kson | -6.165 |
rupal | -6.039 |
oulos | -5.994 |
orb | -5.948 |
Token | her |
Token ID | 607 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
dump | +1.948 |
Sham | +1.934 |
Random | +1.898 |
nam | +1.889 |
ASA | +1.818 |
Neg logit contributions | |
orian | -2.318 |
kson | -2.224 |
orb | -2.205 |
rupal | -2.166 |
oulos | -2.141 |
Token | tongue |
Token ID | 11880 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
dump | +1.340 |
Random | +1.335 |
Sham | +1.333 |
nam | +1.321 |
ASA | +1.255 |
Neg logit contributions | |
orian | -1.634 |
kson | -1.557 |
orb | -1.554 |
rupal | -1.516 |
oulos | -1.506 |
Token | sl |
Token ID | 1017 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
nam | +6.587 |
Sham | +6.512 |
dump | +6.424 |
unres | +6.195 |
Random | +6.145 |
Neg logit contributions | |
orian | -8.100 |
kson | -7.825 |
agascar | -7.688 |
orb | -7.567 |
rupal | -7.562 |
Token | ither |
Token ID | 1555 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
dump | +2.903 |
nam | +2.874 |
Sham | +2.861 |
Random | +2.842 |
ASA | +2.663 |
Neg logit contributions | |
orian | -3.047 |
kson | -2.943 |
orb | -2.865 |
agascar | -2.841 |
helicop | -2.825 |
Token | s |
Token ID | 82 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
dump | +1.237 |
Sham | +1.227 |
nam | +1.225 |
Random | +1.225 |
ASA | +1.136 |
Neg logit contributions | |
orian | -1.849 |
kson | -1.768 |
orb | -1.761 |
rupal | -1.721 |
oulos | -1.715 |
Token | into |
Token ID | 656 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
dump | +0.543 |
Random | +0.542 |
Sham | +0.539 |
nam | +0.533 |
ASA | +0.508 |
Neg logit contributions | |
orian | -0.660 |
kson | -0.628 |
orb | -0.627 |
rupal | -0.609 |
oulos | -0.606 |
Token | mine |
Token ID | 6164 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
Sham | +2.980 |
dump | +2.960 |
Random | +2.945 |
nam | +2.908 |
ASA | +2.791 |
Neg logit contributions | |
orian | -3.389 |
kson | -3.252 |
orb | -3.247 |
oulos | -3.147 |
rupal | -3.146 |
Token | of |
Token ID | 286 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
dump | +1.334 |
Random | +1.334 |
Sham | +1.327 |
nam | +1.304 |
ASA | +1.255 |
Neg logit contributions | |
orian | -1.535 |
kson | -1.462 |
orb | -1.455 |
rupal | -1.412 |
oulos | -1.405 |
Token | the |
Token ID | 262 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
dump | +0.755 |
Random | +0.752 |
Sham | +0.745 |
nam | +0.736 |
ASA | +0.700 |
Neg logit contributions | |
orian | -1.067 |
orb | -1.018 |
kson | -1.017 |
rupal | -0.987 |
oulos | -0.983 |
Token | manga |
Token ID | 15911 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
dump | +0.230 |
Random | +0.229 |
Sham | +0.225 |
nam | +0.225 |
ASA | +0.213 |
Neg logit contributions | |
orian | -0.267 |
orb | -0.254 |
kson | -0.253 |
rupal | -0.245 |
oulos | -0.245 |
Token | series |
Token ID | 2168 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
orian | +0.127 |
orb | +0.121 |
kson | +0.121 |
rupal | +0.116 |
oulos | +0.116 |
Neg logit contributions | |
dump | -0.119 |
Random | -0.118 |
Sham | -0.116 |
nam | -0.116 |
ASA | -0.111 |
Token | have |
Token ID | 423 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
orian | +0.227 |
orb | +0.216 |
kson | +0.214 |
oulos | +0.207 |
rupal | +0.206 |
Neg logit contributions | |
dump | -0.214 |
Random | -0.213 |
Sham | -0.210 |
nam | -0.209 |
ASA | -0.199 |
Token | cum |
Token ID | 10973 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
Random | +1.901 |
dump | +1.896 |
Sham | +1.895 |
nam | +1.867 |
ASA | +1.794 |
Neg logit contributions | |
orian | -2.383 |
kson | -2.270 |
orb | -2.266 |
rupal | -2.204 |
oulos | -2.189 |
Token | ul |
Token ID | 377 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
dump | +6.071 |
Random | +5.848 |
nam | +5.841 |
Sham | +5.761 |
ASA | +5.378 |
Neg logit contributions | |
kson | -8.618 |
orian | -8.442 |
orb | -8.022 |
rupal | -7.988 |
natureconservancy | -7.931 |
Token | atively |
Token ID | 9404 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
nam | +4.762 |
Random | +4.652 |
Sham | +4.615 |
dump | +4.574 |
ASA | +4.287 |
Neg logit contributions | |
kson | -4.466 |
orian | -4.466 |
orb | -4.352 |
oulos | -4.327 |
rupal | -4.302 |
Token | sold |
Token ID | 2702 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
dump | +0.504 |
Random | +0.502 |
Sham | +0.497 |
nam | +0.491 |
ASA | +0.469 |
Neg logit contributions | |
orian | -0.652 |
orb | -0.621 |
kson | -0.620 |
rupal | -0.601 |
oulos | -0.599 |
Token | over |
Token ID | 625 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
orian | +0.571 |
orb | +0.544 |
kson | +0.543 |
rupal | +0.526 |
oulos | +0.524 |
Neg logit contributions | |
dump | -0.448 |
Random | -0.446 |
Sham | -0.442 |
nam | -0.437 |
ASA | -0.417 |
Token | 22 |
Token ID | 2534 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
dump | +2.123 |
Sham | +2.115 |
Random | +2.112 |
nam | +2.089 |
ASA | +1.992 |
Neg logit contributions | |
orian | -2.499 |
kson | -2.377 |
orb | -2.356 |
rupal | -2.308 |
arious | -2.292 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
dump | +0.162 |
Random | +0.161 |
Sham | +0.160 |
nam | +0.158 |
ASA | +0.152 |
Neg logit contributions | |
orian | -0.176 |
orb | -0.167 |
kson | -0.167 |
rupal | -0.161 |
oulos | -0.161 |
Token | A |
Token ID | 317 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Sham | +0.758 |
Random | +0.751 |
dump | +0.744 |
nam | +0.736 |
ASA | +0.710 |
Neg logit contributions | |
orian | -0.906 |
orb | -0.866 |
kson | -0.854 |
rupal | -0.832 |
oulos | -0.832 |
Token | pill |
Token ID | 9582 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
dump | +0.653 |
Random | +0.652 |
Sham | +0.650 |
nam | +0.639 |
ASA | +0.611 |
Neg logit contributions | |
orian | -0.844 |
kson | -0.804 |
orb | -0.804 |
oulos | -0.775 |
rupal | -0.775 |
Token | called |
Token ID | 1444 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
dump | +1.216 |
Random | +1.209 |
Sham | +1.195 |
nam | +1.173 |
ASA | +1.124 |
Neg logit contributions | |
orian | -1.652 |
kson | -1.599 |
orb | -1.580 |
oulos | -1.550 |
rupal | -1.537 |
Token | Sugar |
Token ID | 20874 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
Sham | +2.126 |
Random | +2.086 |
dump | +2.083 |
nam | +2.051 |
ASA | +1.983 |
Neg logit contributions | |
orian | -2.928 |
kson | -2.786 |
orb | -2.771 |
arious | -2.695 |
oulos | -2.691 |
Token | Cum |
Token ID | 27843 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
dump | +1.859 |
Random | +1.838 |
Sham | +1.834 |
nam | +1.800 |
ASA | +1.721 |
Neg logit contributions | |
orian | -2.337 |
kson | -2.247 |
orb | -2.210 |
rupal | -2.166 |
oulos | -2.155 |
Token | , |
Token ID | 11 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
dump | +6.905 |
Sham | +6.653 |
Random | +6.600 |
nam | +6.278 |
ASA | +6.118 |
Neg logit contributions | |
orian | -6.910 |
kson | -6.799 |
natureconservancy | -6.616 |
oulos | -6.504 |
agascar | -6.468 |
Token | for |
Token ID | 329 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Sham | +2.466 |
Random | +2.439 |
dump | +2.435 |
nam | +2.401 |
ASA | +2.301 |
Neg logit contributions | |
orian | -2.926 |
kson | -2.779 |
orb | -2.772 |
rupal | -2.709 |
oulos | -2.688 |
Token | instance |
Token ID | 4554 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
orian | +0.206 |
orb | +0.197 |
kson | +0.197 |
rupal | +0.192 |
oulos | +0.191 |
Neg logit contributions | |
dump | -0.130 |
Random | -0.130 |
Sham | -0.128 |
nam | -0.127 |
ASA | -0.120 |
Token | , |
Token ID | 11 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
orian | +1.025 |
orb | +0.978 |
kson | +0.973 |
rupal | +0.944 |
oulos | +0.938 |
Neg logit contributions | |
dump | -0.880 |
Random | -0.878 |
Sham | -0.871 |
nam | -0.858 |
ASA | -0.826 |
Token | allegedly |
Token ID | 7910 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
dump | +0.357 |
Random | +0.356 |
Sham | +0.353 |
nam | +0.349 |
ASA | +0.333 |
Neg logit contributions | |
orian | -0.440 |
orb | -0.419 |
kson | -0.418 |
rupal | -0.405 |
oulos | -0.404 |
Token |
|
Token ID | 198 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
dump | +0.337 |
Random | +0.336 |
Sham | +0.334 |
nam | +0.330 |
ASA | +0.316 |
Neg logit contributions | |
orian | -0.378 |
orb | -0.360 |
kson | -0.358 |
rupal | -0.347 |
oulos | -0.346 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Random | +0.441 |
dump | +0.440 |
Sham | +0.438 |
nam | +0.435 |
ASA | +0.410 |
Neg logit contributions | |
orian | -0.507 |
kson | -0.480 |
orb | -0.480 |
helicop | -0.475 |
oulos | -0.470 |
Token | sudo |
Token ID | 24032 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
dump | +0.659 |
Random | +0.656 |
Sham | +0.643 |
nam | +0.638 |
ASA | +0.594 |
Neg logit contributions | |
orian | -1.223 |
kson | -1.173 |
orb | -1.171 |
oulos | -1.141 |
rupal | -1.140 |
Token | ch |
Token ID | 442 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
dump | +3.256 |
Sham | +3.220 |
Random | +3.201 |
nam | +3.196 |
ASA | +3.039 |
Neg logit contributions | |
orian | -4.013 |
orb | -3.834 |
kson | -3.820 |
oulos | -3.766 |
rupal | -3.711 |
Token | mod |
Token ID | 4666 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
dump | +2.232 |
Random | +2.195 |
nam | +2.184 |
Sham | +2.157 |
ASA | +2.029 |
Neg logit contributions | |
orian | -2.597 |
kson | -2.484 |
orb | -2.443 |
oulos | -2.436 |
rupal | -2.429 |
Token | + |
Token ID | 1343 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
dump | +2.848 |
Random | +2.822 |
Sham | +2.792 |
nam | +2.748 |
ASA | +2.629 |
Neg logit contributions | |
orian | -3.782 |
kson | -3.625 |
orb | -3.596 |
rupal | -3.489 |
arious | -3.480 |
Token | x |
Token ID | 87 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Random | +4.224 |
nam | +4.203 |
dump | +4.175 |
Sham | +4.005 |
ASA | +3.667 |
Neg logit contributions | |
orian | -9.376 |
oulos | -9.262 |
agascar | -9.054 |
kson | -8.953 |
orb | -8.950 |
Token | / |
Token ID | 1220 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
dump | +1.256 |
Random | +1.239 |
Sham | +1.238 |
nam | +1.223 |
ASA | +1.166 |
Neg logit contributions | |
orian | -1.715 |
orb | -1.639 |
kson | -1.634 |
rupal | -1.587 |
oulos | -1.585 |
Token | etc |
Token ID | 14784 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
dump | +1.539 |
Random | +1.531 |
Sham | +1.515 |
nam | +1.504 |
ASA | +1.427 |
Neg logit contributions | |
orian | -1.933 |
kson | -1.840 |
orb | -1.840 |
rupal | -1.786 |
oulos | -1.781 |
Token | / |
Token ID | 14 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
dump | +0.313 |
Random | +0.308 |
Sham | +0.305 |
nam | +0.304 |
ASA | +0.287 |
Neg logit contributions | |
orian | -0.405 |
kson | -0.387 |
orb | -0.386 |
oulos | -0.376 |
arious | -0.375 |
Token | pm |
Token ID | 4426 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
dump | +2.029 |
Random | +1.995 |
nam | +1.984 |
Sham | +1.976 |
ASA | +1.846 |
Neg logit contributions | |
orian | -2.547 |
kson | -2.419 |
orb | -2.414 |
rupal | -2.347 |
oulos | -2.342 |
Token | given |
Token ID | 1813 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
orian | +0.701 |
orb | +0.671 |
kson | +0.670 |
rupal | +0.651 |
oulos | +0.647 |
Neg logit contributions | |
dump | -0.414 |
Random | -0.408 |
Sham | -0.408 |
nam | -0.399 |
ASA | -0.378 |
Token | by |
Token ID | 416 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
dump | +0.576 |
Random | +0.575 |
Sham | +0.572 |
nam | +0.565 |
ASA | +0.538 |
Neg logit contributions | |
orian | -0.665 |
orb | -0.633 |
kson | -0.632 |
rupal | -0.614 |
oulos | -0.609 |
Token | people |
Token ID | 661 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
dump | +0.175 |
Random | +0.175 |
Sham | +0.173 |
nam | +0.171 |
ASA | +0.163 |
Neg logit contributions | |
orian | -0.214 |
orb | -0.203 |
kson | -0.203 |
rupal | -0.197 |
oulos | -0.196 |
Token | like |
Token ID | 588 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
orian | +0.425 |
orb | +0.403 |
kson | +0.403 |
rupal | +0.390 |
oulos | +0.388 |
Neg logit contributions | |
dump | -0.378 |
Random | -0.377 |
Sham | -0.374 |
nam | -0.370 |
ASA | -0.354 |
Token | Bill |
Token ID | 3941 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
orian | +2.029 |
kson | +1.944 |
orb | +1.926 |
rupal | +1.865 |
oulos | +1.860 |
Neg logit contributions | |
dump | -1.699 |
Random | -1.684 |
nam | -1.670 |
Sham | -1.649 |
ASA | -1.583 |
Token | Moy |
Token ID | 28523 |
Feature activation | -9.96e+00 |
Pos logit contributions | |
orian | +4.405 |
kson | +4.278 |
orb | +4.193 |
oulos | +4.060 |
rupal | +4.045 |
Neg logit contributions | |
dump | -3.158 |
Random | -3.145 |
nam | -3.121 |
Sham | -3.033 |
ASA | -2.973 |
Token | ers |
Token ID | 364 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
dump | +4.291 |
nam | +4.239 |
Sham | +4.083 |
Random | +3.977 |
Ut | +3.675 |
Neg logit contributions | |
orian | -9.069 |
kson | -8.897 |
helicop | -8.873 |
agascar | -8.784 |
orb | -8.731 |
Token | , |
Token ID | 11 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
dump | +0.381 |
Random | +0.380 |
Sham | +0.377 |
nam | +0.373 |
ASA | +0.356 |
Neg logit contributions | |
orian | -0.422 |
orb | -0.400 |
kson | -0.400 |
rupal | -0.387 |
oulos | -0.385 |
Token | suggests |
Token ID | 5644 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
orian | +0.288 |
orb | +0.273 |
kson | +0.273 |
rupal | +0.264 |
oulos | +0.263 |
Neg logit contributions | |
dump | -0.259 |
Random | -0.258 |
Sham | -0.255 |
nam | -0.253 |
ASA | -0.242 |
Token | that |
Token ID | 326 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
orian | +0.160 |
kson | +0.153 |
orb | +0.152 |
rupal | +0.147 |
oulos | +0.147 |
Neg logit contributions | |
dump | -0.128 |
Random | -0.127 |
Sham | -0.126 |
nam | -0.125 |
ASA | -0.120 |
Token | the |
Token ID | 262 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
orian | +0.745 |
kson | +0.713 |
orb | +0.710 |
oulos | +0.687 |
rupal | +0.686 |
Neg logit contributions | |
dump | -0.551 |
Random | -0.549 |
Sham | -0.541 |
nam | -0.538 |
ASA | -0.513 |
Token | ways |
Token ID | 2842 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
orian | +2.746 |
kson | +2.611 |
orb | +2.595 |
rupal | +2.520 |
oulos | +2.505 |
Neg logit contributions | |
dump | -2.387 |
Random | -2.373 |
Sham | -2.334 |
nam | -2.314 |
ASA | -2.214 |
Token | that |
Token ID | 326 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Random | +1.257 |
dump | +1.256 |
Sham | +1.255 |
nam | +1.238 |
ASA | +1.174 |
Neg logit contributions | |
orian | -1.696 |
orb | -1.614 |
kson | -1.608 |
oulos | -1.560 |
rupal | -1.560 |
Token | aren |
Token ID | 3588 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
orian | +2.002 |
orb | +1.916 |
kson | +1.906 |
rupal | +1.840 |
oulos | +1.838 |
Neg logit contributions | |
Random | -1.659 |
dump | -1.657 |
Sham | -1.635 |
nam | -1.620 |
ASA | -1.552 |
Token | 't |
Token ID | 470 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
orian | +1.820 |
orb | +1.717 |
kson | +1.714 |
rupal | +1.650 |
oulos | +1.633 |
Neg logit contributions | |
dump | -2.097 |
Random | -2.089 |
Sham | -2.076 |
nam | -2.050 |
ASA | -1.985 |
Token | comm |
Token ID | 725 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
orian | +2.319 |
orb | +2.215 |
kson | +2.202 |
rupal | +2.147 |
oulos | +2.130 |
Neg logit contributions | |
dump | -1.670 |
Random | -1.655 |
Sham | -1.637 |
nam | -1.605 |
ASA | -1.544 |
Token | ens |
Token ID | 641 |
Feature activation | -9.64e+00 |
Pos logit contributions | |
dump | +0.037 |
Random | +0.037 |
Sham | +0.037 |
nam | +0.037 |
ASA | +0.035 |
Neg logit contributions | |
orian | -0.026 |
kson | -0.024 |
orb | -0.024 |
rupal | -0.023 |
oulos | -0.023 |
Token | urate |
Token ID | 15537 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
nam | +7.558 |
Random | +7.534 |
dump | +7.495 |
Sham | +7.494 |
unres | +7.109 |
Neg logit contributions | |
kson | -5.130 |
rupal | -4.944 |
orian | -4.936 |
oulos | -4.902 |
agascar | -4.854 |
Token | with |
Token ID | 351 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
orian | +2.270 |
orb | +2.141 |
kson | +2.097 |
rupal | +2.025 |
tale | +2.002 |
Neg logit contributions | |
dump | -3.190 |
Random | -3.161 |
Sham | -3.119 |
nam | -3.085 |
ASA | -3.014 |
Token | their |
Token ID | 511 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
orian | +1.057 |
orb | +1.008 |
kson | +1.005 |
rupal | +0.975 |
oulos | +0.973 |
Neg logit contributions | |
dump | -0.810 |
Random | -0.806 |
Sham | -0.796 |
nam | -0.786 |
ASA | -0.751 |
Token | past |
Token ID | 1613 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
dump | +0.217 |
Random | +0.216 |
Sham | +0.215 |
nam | +0.212 |
ASA | +0.202 |
Neg logit contributions | |
orian | -0.319 |
orb | -0.304 |
kson | -0.304 |
rupal | -0.296 |
oulos | -0.294 |
Token | performances |
Token ID | 13289 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
orian | +0.486 |
orb | +0.464 |
kson | +0.464 |
rupal | +0.451 |
oulos | +0.449 |
Neg logit contributions | |
dump | -0.315 |
Random | -0.314 |
Sham | -0.311 |
nam | -0.307 |
ASA | -0.291 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
orian | +0.224 |
orb | +0.212 |
kson | +0.212 |
oulos | +0.206 |
rupal | +0.205 |
Neg logit contributions | |
Random | -0.202 |
dump | -0.201 |
Sham | -0.200 |
nam | -0.199 |
ASA | -0.188 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Random | +0.845 |
Sham | +0.842 |
dump | +0.839 |
nam | +0.832 |
ASA | +0.778 |
Neg logit contributions | |
orian | -1.002 |
helicop | -0.954 |
orb | -0.950 |
kson | -0.949 |
oulos | -0.932 |
Token | Show |
Token ID | 15307 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Random | +0.719 |
dump | +0.717 |
Sham | +0.705 |
nam | +0.701 |
ASA | +0.657 |
Neg logit contributions | |
orian | -0.944 |
kson | -0.901 |
orb | -0.896 |
rupal | -0.876 |
oulos | -0.875 |
Token | nested |
Token ID | 28376 |
Feature activation | -6.78e+00 |
Pos logit contributions | |
Random | +0.206 |
dump | +0.205 |
Sham | +0.203 |
nam | +0.200 |
ASA | +0.188 |
Neg logit contributions | |
orian | -0.344 |
kson | -0.329 |
orb | -0.328 |
rupal | -0.319 |
oulos | -0.318 |
Token | quote |
Token ID | 9577 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
nam | +3.198 |
Random | +3.140 |
dump | +3.107 |
Sham | +3.032 |
ASA | +3.008 |
Neg logit contributions | |
orb | -5.954 |
orian | -5.922 |
kson | -5.819 |
ngth | -5.682 |
uitive | -5.646 |
Token | + |
Token ID | 1343 |
Feature activation | -9.62e+00 |
Pos logit contributions | |
Random | +1.900 |
dump | +1.865 |
Sham | +1.789 |
nam | +1.786 |
Dota | +1.673 |
Neg logit contributions | |
orian | -4.679 |
orb | -4.580 |
agascar | -4.527 |
oulos | -4.513 |
kson | -4.480 |
Token |
|
Token ID | 198 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Random | +4.994 |
Sham | +4.909 |
nam | +4.724 |
dump | +4.581 |
Ut | +4.507 |
Neg logit contributions | |
helicop | -8.700 |
orian | -8.169 |
carbohyd | -8.145 |
oulos | -8.002 |
ngth | -7.930 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Random | +1.626 |
Sham | +1.614 |
dump | +1.601 |
nam | +1.594 |
ASA | +1.485 |
Neg logit contributions | |
orian | -2.056 |
helicop | -2.000 |
orb | -1.950 |
kson | -1.943 |
oulos | -1.922 |
Token | On |
Token ID | 2202 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
Random | +1.683 |
dump | +1.664 |
nam | +1.641 |
Sham | +1.638 |
Gh | +1.553 |
Neg logit contributions | |
orian | -1.358 |
kson | -1.285 |
orb | -1.283 |
oulos | -1.248 |
rupal | -1.244 |
Token | September |
Token ID | 2693 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
Sham | +0.270 |
Random | +0.268 |
dump | +0.268 |
nam | +0.264 |
ASA | +0.250 |
Neg logit contributions | |
orian | -0.320 |
orb | -0.305 |
kson | -0.305 |
oulos | -0.296 |
rupal | -0.295 |
Token | 20 |
Token ID | 1160 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
orian | +2.309 |
orb | +2.197 |
kson | +2.161 |
oulos | +2.065 |
tale | +2.059 |
Neg logit contributions | |
dump | -2.985 |
Random | -2.953 |
Sham | -2.902 |
nam | -2.880 |
ASA | -2.816 |
Token | The |
Token ID | 464 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
orian | +0.325 |
orb | +0.310 |
kson | +0.309 |
rupal | +0.301 |
oulos | +0.300 |
Neg logit contributions | |
dump | -0.222 |
Random | -0.220 |
Sham | -0.219 |
nam | -0.216 |
ASA | -0.206 |
Token | Lerner |
Token ID | 49750 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
orian | +0.384 |
kson | +0.364 |
orb | +0.363 |
rupal | +0.350 |
oulos | +0.349 |
Neg logit contributions | |
dump | -0.395 |
Random | -0.394 |
Sham | -0.390 |
nam | -0.387 |
ASA | -0.371 |
Token | emails |
Token ID | 7237 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
orian | +1.957 |
kson | +1.881 |
orb | +1.858 |
rupal | +1.813 |
arious | +1.807 |
Neg logit contributions | |
Random | -1.382 |
dump | -1.371 |
Sham | -1.338 |
nam | -1.338 |
ASA | -1.275 |
Token | have |
Token ID | 423 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
orian | +1.131 |
orb | +1.077 |
kson | +1.072 |
rupal | +1.033 |
oulos | +1.032 |
Neg logit contributions | |
Random | -1.060 |
dump | -1.050 |
Sham | -1.037 |
nam | -1.033 |
ASA | -0.993 |
Token | become |
Token ID | 1716 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
dump | +0.883 |
Random | +0.880 |
Sham | +0.876 |
nam | +0.865 |
ASA | +0.827 |
Neg logit contributions | |
orian | -1.034 |
orb | -0.982 |
kson | -0.980 |
rupal | -0.951 |
oulos | -0.946 |
Token | almost |
Token ID | 2048 |
Feature activation | -9.49e+00 |
Pos logit contributions | |
dump | +2.214 |
Sham | +2.205 |
Random | +2.185 |
nam | +2.173 |
ASA | +2.049 |
Neg logit contributions | |
orian | -3.452 |
kson | -3.321 |
orb | -3.314 |
rupal | -3.243 |
oulos | -3.207 |
Token | as |
Token ID | 355 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
Sham | +5.304 |
nam | +5.283 |
Random | +5.092 |
dump | +5.045 |
unres | +5.033 |
Neg logit contributions | |
orian | -7.460 |
kson | -7.425 |
rupal | -7.262 |
orb | -7.222 |
oulos | -7.129 |
Token | big |
Token ID | 1263 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Random | +1.786 |
dump | +1.783 |
Sham | +1.777 |
nam | +1.747 |
ASA | +1.655 |
Neg logit contributions | |
orian | -2.613 |
kson | -2.490 |
orb | -2.487 |
rupal | -2.435 |
oulos | -2.397 |
Token | a |
Token ID | 257 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
dump | +1.070 |
Random | +1.068 |
Sham | +1.058 |
nam | +1.044 |
ASA | +0.992 |
Neg logit contributions | |
orian | -1.551 |
kson | -1.482 |
orb | -1.481 |
rupal | -1.438 |
oulos | -1.430 |
Token | scandal |
Token ID | 10731 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
dump | +0.098 |
Random | +0.098 |
Sham | +0.096 |
nam | +0.095 |
ASA | +0.091 |
Neg logit contributions | |
orian | -0.134 |
orb | -0.128 |
kson | -0.128 |
rupal | -0.124 |
oulos | -0.124 |
Token | as |
Token ID | 355 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
dump | +0.243 |
Random | +0.243 |
Sham | +0.240 |
nam | +0.237 |
ASA | +0.226 |
Neg logit contributions | |
orian | -0.341 |
orb | -0.325 |
kson | -0.325 |
rupal | -0.315 |
oulos | -0.314 |
Token | Appeals |
Token ID | 20172 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Sham | +0.477 |
Random | +0.474 |
dump | +0.472 |
nam | +0.464 |
ASA | +0.447 |
Neg logit contributions | |
orian | -0.632 |
orb | -0.605 |
kson | -0.598 |
rupal | -0.586 |
oulos | -0.582 |
Token | to |
Token ID | 284 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
orian | +0.902 |
orb | +0.852 |
kson | +0.844 |
rupal | +0.820 |
oulos | +0.815 |
Neg logit contributions | |
dump | -0.943 |
Random | -0.942 |
Sham | -0.931 |
nam | -0.922 |
ASA | -0.889 |
Token | identity |
Token ID | 5369 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
orian | +0.456 |
orb | +0.435 |
kson | +0.434 |
rupal | +0.421 |
oulos | +0.420 |
Neg logit contributions | |
dump | -0.334 |
Random | -0.333 |
Sham | -0.329 |
nam | -0.326 |
ASA | -0.310 |
Token | are |
Token ID | 389 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
orian | +1.276 |
orb | +1.212 |
kson | +1.211 |
rupal | +1.175 |
oulos | +1.168 |
Neg logit contributions | |
dump | -1.043 |
Random | -1.043 |
Sham | -1.028 |
nam | -1.018 |
ASA | -0.976 |
Token | now |
Token ID | 783 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Sham | +0.742 |
dump | +0.740 |
Random | +0.739 |
nam | +0.735 |
ASA | +0.691 |
Neg logit contributions | |
orian | -1.106 |
orb | -1.060 |
kson | -1.058 |
rupal | -1.029 |
oulos | -1.021 |
Token | almost |
Token ID | 2048 |
Feature activation | -9.28e+00 |
Pos logit contributions | |
Sham | +0.878 |
dump | +0.876 |
Random | +0.875 |
nam | +0.869 |
ASA | +0.819 |
Neg logit contributions | |
orian | -1.278 |
orb | -1.227 |
kson | -1.220 |
rupal | -1.189 |
oulos | -1.179 |
Token | exclusively |
Token ID | 11541 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
nam | +5.087 |
Sham | +5.069 |
unres | +5.017 |
Random | +4.880 |
unse | +4.715 |
Neg logit contributions | |
orian | -7.239 |
kson | -7.225 |
orb | -7.056 |
rupal | -7.040 |
ngth | -6.901 |
Token | the |
Token ID | 262 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Sham | +1.177 |
dump | +1.171 |
Random | +1.166 |
nam | +1.163 |
ASA | +1.112 |
Neg logit contributions | |
orian | -1.458 |
orb | -1.400 |
kson | -1.382 |
rupal | -1.350 |
oulos | -1.341 |
Token | preserve |
Token ID | 12201 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
dump | +1.842 |
Sham | +1.838 |
Random | +1.835 |
nam | +1.817 |
ASA | +1.749 |
Neg logit contributions | |
orian | -2.514 |
orb | -2.425 |
kson | -2.406 |
rupal | -2.349 |
oulos | -2.331 |
Token | of |
Token ID | 286 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
dump | +1.783 |
Random | +1.778 |
Sham | +1.763 |
nam | +1.744 |
ASA | +1.671 |
Neg logit contributions | |
orian | -1.967 |
orb | -1.866 |
kson | -1.863 |
rupal | -1.802 |
oulos | -1.794 |
Token | the |
Token ID | 262 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
orian | +0.085 |
orb | +0.081 |
kson | +0.081 |
rupal | +0.078 |
oulos | +0.078 |
Neg logit contributions | |
dump | -0.066 |
Random | -0.065 |
Sham | -0.065 |
nam | -0.064 |
ASA | -0.061 |
Token | or |
Token ID | 393 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
dump | +1.309 |
Random | +1.307 |
Sham | +1.292 |
nam | +1.288 |
ASA | +1.218 |
Neg logit contributions | |
orian | -1.486 |
kson | -1.411 |
orb | -1.401 |
rupal | -1.366 |
oulos | -1.365 |
Token | < |
Token ID | 1279 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
dump | +0.943 |
Random | +0.940 |
Sham | +0.933 |
nam | +0.923 |
ASA | +0.880 |
Neg logit contributions | |
orian | -1.173 |
orb | -1.116 |
kson | -1.115 |
rupal | -1.081 |
oulos | -1.077 |
Token | Tab |
Token ID | 33349 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
Random | +1.560 |
dump | +1.547 |
nam | +1.523 |
Sham | +1.509 |
ASA | +1.402 |
Neg logit contributions | |
orian | -2.374 |
kson | -2.278 |
orb | -2.251 |
oulos | -2.222 |
rupal | -2.217 |
Token | >) |
Token ID | 43734 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
dump | +3.608 |
Random | +3.558 |
nam | +3.519 |
Sham | +3.497 |
ASA | +3.167 |
Neg logit contributions | |
orian | -6.269 |
kson | -6.012 |
oulos | -5.979 |
orb | -5.855 |
rupal | -5.844 |
Token | { |
Token ID | 1391 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Random | +2.097 |
dump | +2.085 |
Sham | +2.061 |
nam | +2.046 |
ASA | +1.963 |
Neg logit contributions | |
orian | -2.570 |
kson | -2.448 |
orb | -2.447 |
oulos | -2.387 |
rupal | -2.376 |
Token | vi |
Token ID | 8903 |
Feature activation | -9.19e+00 |
Pos logit contributions | |
dump | +1.107 |
Random | +1.103 |
Sham | +1.083 |
nam | +1.081 |
ASA | +1.024 |
Neg logit contributions | |
orian | -1.337 |
kson | -1.273 |
orb | -1.268 |
oulos | -1.233 |
rupal | -1.233 |
Token | : |
Token ID | 25 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
dump | +5.615 |
Random | +5.611 |
Sham | +5.552 |
nam | +5.544 |
ASA | +5.151 |
Neg logit contributions | |
orian | -6.711 |
kson | -6.387 |
oulos | -6.330 |
orb | -6.289 |
helicop | -6.222 |
Token | | |
Token ID | 91 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
dump | +1.659 |
Random | +1.650 |
nam | +1.623 |
Sham | +1.622 |
ASA | +1.540 |
Neg logit contributions | |
orian | -1.746 |
kson | -1.660 |
orb | -1.647 |
oulos | -1.608 |
rupal | -1.598 |
Token | vim |
Token ID | 31124 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
dump | +2.790 |
Random | +2.749 |
nam | +2.732 |
Sham | +2.658 |
ASA | +2.514 |
Neg logit contributions | |
orian | -3.638 |
kson | -3.497 |
orb | -3.435 |
oulos | -3.415 |
arious | -3.350 |
Token | : |
Token ID | 25 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
dump | +4.507 |
nam | +4.417 |
Sham | +4.322 |
Random | +4.294 |
ASA | +3.969 |
Neg logit contributions | |
orian | -5.845 |
helicop | -5.837 |
oulos | -5.637 |
kson | -5.631 |
orb | -5.499 |
Token | | |
Token ID | 91 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
dump | +1.718 |
Random | +1.711 |
Sham | +1.690 |
nam | +1.682 |
ASA | +1.605 |
Neg logit contributions | |
orian | -1.759 |
kson | -1.667 |
orb | -1.660 |
oulos | -1.609 |
rupal | -1.606 |
Token | told |
Token ID | 1297 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
dump | +1.721 |
Sham | +1.716 |
Random | +1.711 |
nam | +1.704 |
ASA | +1.631 |
Neg logit contributions | |
orian | -1.295 |
orb | -1.209 |
kson | -1.198 |
rupal | -1.161 |
oulos | -1.155 |
Token | the |
Token ID | 262 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
dump | +1.003 |
Random | +1.002 |
Sham | +0.996 |
nam | +0.980 |
ASA | +0.940 |
Neg logit contributions | |
orian | -1.204 |
orb | -1.145 |
kson | -1.142 |
rupal | -1.108 |
oulos | -1.102 |
Token | Today |
Token ID | 6288 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
orian | +0.279 |
orb | +0.265 |
kson | +0.265 |
oulos | +0.256 |
rupal | +0.255 |
Neg logit contributions | |
dump | -0.223 |
Random | -0.222 |
nam | -0.218 |
Sham | -0.218 |
ASA | -0.206 |
Token | show |
Token ID | 905 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
dump | +0.941 |
Random | +0.938 |
Sham | +0.930 |
nam | +0.914 |
ASA | +0.867 |
Neg logit contributions | |
orian | -1.604 |
orb | -1.539 |
kson | -1.538 |
rupal | -1.496 |
oulos | -1.490 |
Token | 's |
Token ID | 338 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Sham | +2.657 |
dump | +2.643 |
Random | +2.636 |
nam | +2.574 |
ASA | +2.487 |
Neg logit contributions | |
orian | -2.801 |
orb | -2.668 |
kson | -2.652 |
rupal | -2.585 |
arious | -2.566 |
Token | Savannah |
Token ID | 40695 |
Feature activation | -9.16e+00 |
Pos logit contributions | |
dump | +1.392 |
Random | +1.390 |
Sham | +1.384 |
nam | +1.363 |
ASA | +1.310 |
Neg logit contributions | |
orian | -1.441 |
orb | -1.368 |
kson | -1.363 |
rupal | -1.320 |
oulos | -1.313 |
Token | Guth |
Token ID | 44003 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
Sham | +4.574 |
Random | +4.288 |
nam | +4.245 |
dump | +4.097 |
Ut | +3.995 |
Neg logit contributions | |
orian | -8.026 |
kson | -7.783 |
orb | -7.665 |
agascar | -7.660 |
oulos | -7.608 |
Token | rie |
Token ID | 5034 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
dump | +0.411 |
Random | +0.409 |
Sham | +0.406 |
nam | +0.399 |
ASA | +0.387 |
Neg logit contributions | |
orian | -0.386 |
orb | -0.365 |
kson | -0.365 |
rupal | -0.351 |
arious | -0.347 |
Token | who |
Token ID | 508 |
Feature activation | +5.59e-02 |
Pos logit contributions | |
dump | +0.660 |
Random | +0.658 |
Sham | +0.654 |
nam | +0.646 |
ASA | +0.621 |
Neg logit contributions | |
orian | -0.643 |
orb | -0.609 |
kson | -0.607 |
rupal | -0.587 |
oulos | -0.584 |
Token | brought |
Token ID | 3181 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
orian | +0.038 |
orb | +0.036 |
kson | +0.036 |
rupal | +0.034 |
oulos | +0.034 |
Neg logit contributions | |
dump | -0.040 |
Random | -0.040 |
Sham | -0.039 |
nam | -0.039 |
ASA | -0.037 |
Token | up |
Token ID | 510 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
orian | +1.887 |
kson | +1.808 |
orb | +1.800 |
rupal | +1.748 |
oulos | +1.741 |
Neg logit contributions | |
Random | -1.283 |
dump | -1.276 |
nam | -1.240 |
Sham | -1.225 |
ASA | -1.166 |
Token | paragraph |
Token ID | 7322 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
orian | +3.247 |
orb | +3.089 |
kson | +3.067 |
arious | +2.966 |
rupal | +2.952 |
Neg logit contributions | |
Random | -2.618 |
dump | -2.594 |
nam | -2.580 |
Sham | -2.558 |
ASA | -2.403 |
Token | that |
Token ID | 326 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
orian | +0.955 |
kson | +0.905 |
orb | +0.905 |
rupal | +0.875 |
oulos | +0.869 |
Neg logit contributions | |
dump | -0.796 |
Random | -0.795 |
Sham | -0.783 |
nam | -0.778 |
ASA | -0.744 |
Token | said |
Token ID | 531 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
orian | +0.244 |
kson | +0.232 |
orb | +0.232 |
rupal | +0.224 |
oulos | +0.223 |
Neg logit contributions | |
dump | -0.209 |
Random | -0.208 |
Sham | -0.206 |
nam | -0.204 |
ASA | -0.195 |
Token | God |
Token ID | 1793 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
orian | +0.889 |
orb | +0.844 |
kson | +0.842 |
oulos | +0.813 |
rupal | +0.812 |
Neg logit contributions | |
dump | -0.696 |
Random | -0.694 |
Sham | -0.684 |
nam | -0.676 |
ASA | -0.644 |
Token | considers |
Token ID | 14358 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
orian | +1.473 |
orb | +1.395 |
kson | +1.392 |
rupal | +1.348 |
arious | +1.339 |
Neg logit contributions | |
Random | -1.300 |
dump | -1.300 |
Sham | -1.275 |
nam | -1.261 |
ASA | -1.219 |
Token | masturbation |
Token ID | 41054 |
Feature activation | -9.11e+00 |
Pos logit contributions | |
orian | +2.494 |
orb | +2.375 |
kson | +2.372 |
rupal | +2.291 |
oulos | +2.288 |
Neg logit contributions | |
dump | -1.836 |
Random | -1.826 |
Sham | -1.770 |
nam | -1.763 |
ASA | -1.680 |
Token | to |
Token ID | 284 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Sham | +4.847 |
Random | +4.714 |
nam | +4.707 |
unres | +4.651 |
dump | +4.588 |
Neg logit contributions | |
orian | -7.474 |
kson | -7.166 |
orb | -7.056 |
agascar | -6.906 |
rupal | -6.882 |
Token | be |
Token ID | 307 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
dump | +0.996 |
Random | +0.992 |
Sham | +0.979 |
nam | +0.965 |
ASA | +0.922 |
Neg logit contributions | |
orian | -1.403 |
orb | -1.339 |
kson | -1.333 |
rupal | -1.298 |
oulos | -1.293 |
Token | a |
Token ID | 257 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
dump | +0.564 |
Random | +0.562 |
Sham | +0.556 |
nam | +0.549 |
ASA | +0.522 |
Neg logit contributions | |
orian | -0.829 |
orb | -0.792 |
kson | -0.791 |
rupal | -0.768 |
oulos | -0.766 |
Token | " |
Token ID | 366 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
dump | +0.855 |
Random | +0.853 |
Sham | +0.851 |
nam | +0.835 |
ASA | +0.790 |
Neg logit contributions | |
orian | -1.399 |
kson | -1.340 |
orb | -1.340 |
rupal | -1.302 |
oulos | -1.297 |
Token | hom |
Token ID | 26452 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
dump | +1.318 |
Random | +1.312 |
Sham | +1.294 |
nam | +1.291 |
ASA | +1.217 |
Neg logit contributions | |
orian | -1.552 |
kson | -1.485 |
orb | -1.469 |
rupal | -1.429 |
oulos | -1.427 |
Token | ver |
Token ID | 332 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
dump | +1.295 |
Random | +1.290 |
nam | +1.267 |
Sham | +1.266 |
ASA | +1.193 |
Neg logit contributions | |
orian | -1.716 |
kson | -1.642 |
orb | -1.623 |
rupal | -1.595 |
oulos | -1.589 |
Token | tex |
Token ID | 16886 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
dump | +1.181 |
Random | +1.178 |
Sham | +1.169 |
nam | +1.156 |
ASA | +1.110 |
Neg logit contributions | |
orian | -1.192 |
orb | -1.129 |
kson | -1.126 |
rupal | -1.088 |
oulos | -1.082 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
dump | +1.351 |
Random | +1.350 |
Sham | +1.325 |
nam | +1.315 |
ASA | +1.237 |
Neg logit contributions | |
orian | -2.254 |
kson | -2.162 |
orb | -2.156 |
rupal | -2.106 |
oulos | -2.099 |
Token | xy |
Token ID | 5431 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
dump | +1.395 |
Random | +1.380 |
nam | +1.361 |
Sham | +1.351 |
ASA | +1.278 |
Neg logit contributions | |
orian | -1.786 |
kson | -1.715 |
orb | -1.687 |
rupal | -1.664 |
oulos | -1.658 |
Token | z |
Token ID | 89 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
dump | +1.665 |
Random | +1.655 |
nam | +1.619 |
Sham | +1.611 |
ASA | +1.528 |
Neg logit contributions | |
orian | -2.504 |
kson | -2.405 |
orb | -2.376 |
oulos | -2.343 |
rupal | -2.343 |
Token | += |
Token ID | 15853 |
Feature activation | -9.05e+00 |
Pos logit contributions | |
dump | +0.856 |
Random | +0.852 |
Sham | +0.846 |
nam | +0.833 |
ASA | +0.788 |
Neg logit contributions | |
orian | -1.406 |
orb | -1.346 |
kson | -1.341 |
rupal | -1.305 |
oulos | -1.299 |
Token | v |
Token ID | 410 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
Random | +5.155 |
nam | +5.141 |
dump | +5.086 |
Sham | +5.028 |
ASA | +4.887 |
Neg logit contributions | |
orian | -6.874 |
kson | -6.791 |
rupal | -6.587 |
arious | -6.575 |
oulos | -6.515 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Random | +1.891 |
dump | +1.889 |
Sham | +1.865 |
nam | +1.850 |
ASA | +1.769 |
Neg logit contributions | |
orian | -2.063 |
kson | -1.961 |
orb | -1.953 |
rupal | -1.894 |
oulos | -1.891 |
Token | normal |
Token ID | 11265 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
dump | +1.099 |
Random | +1.093 |
Sham | +1.075 |
nam | +1.074 |
ASA | +1.015 |
Neg logit contributions | |
orian | -1.442 |
kson | -1.378 |
orb | -1.368 |
rupal | -1.336 |
oulos | -1.331 |
Token | * |
Token ID | 1635 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
dump | +1.153 |
Random | +1.152 |
Sham | +1.133 |
nam | +1.124 |
ASA | +1.064 |
Neg logit contributions | |
orian | -1.700 |
kson | -1.628 |
orb | -1.619 |
rupal | -1.579 |
oulos | -1.575 |
Token | 1 |
Token ID | 352 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
Random | +2.587 |
dump | +2.568 |
Sham | +2.547 |
nam | +2.546 |
ASA | +2.432 |
Neg logit contributions | |
orian | -3.694 |
kson | -3.606 |
orb | -3.490 |
rupal | -3.479 |
oulos | -3.466 |
Token | map |
Token ID | 8899 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
orian | +1.355 |
orb | +1.220 |
kson | +1.168 |
rupal | +1.129 |
oulos | +1.090 |
Neg logit contributions | |
Sham | -3.717 |
Random | -3.705 |
dump | -3.696 |
nam | -3.655 |
ASA | -3.606 |
Token | $ |
Token ID | 720 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
orian | +0.136 |
orb | +0.130 |
kson | +0.130 |
rupal | +0.125 |
oulos | +0.125 |
Neg logit contributions | |
dump | -0.112 |
Random | -0.112 |
Sham | -0.111 |
nam | -0.110 |
ASA | -0.104 |
Token | b |
Token ID | 65 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
dump | +2.391 |
Random | +2.385 |
nam | +2.316 |
Sham | +2.314 |
ASA | +2.190 |
Neg logit contributions | |
orian | -2.818 |
kson | -2.692 |
orb | -2.626 |
oulos | -2.602 |
rupal | -2.593 |
Token | mp |
Token ID | 3149 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
dump | +1.106 |
Random | +1.095 |
Sham | +1.077 |
nam | +1.076 |
ASA | +1.009 |
Neg logit contributions | |
orian | -1.632 |
kson | -1.561 |
orb | -1.555 |
rupal | -1.513 |
oulos | -1.509 |
Token | = |
Token ID | 796 |
Feature activation | -8.52e+00 |
Pos logit contributions | |
dump | +1.573 |
Random | +1.569 |
Sham | +1.543 |
nam | +1.533 |
ASA | +1.457 |
Neg logit contributions | |
orian | -2.113 |
kson | -2.019 |
orb | -2.010 |
rupal | -1.955 |
oulos | -1.951 |
Token | new |
Token ID | 649 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
dump | +4.160 |
Random | +4.111 |
Sham | +4.032 |
nam | +3.880 |
Ut | +3.699 |
Neg logit contributions | |
orian | -7.511 |
kson | -7.183 |
orb | -7.126 |
oulos | -7.112 |
arious | -7.077 |
Token | - |
Token ID | 12 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
Random | +3.901 |
Sham | +3.825 |
dump | +3.812 |
nam | +3.569 |
Ut | +3.404 |
Neg logit contributions | |
helicop | -8.406 |
orian | -8.214 |
kson | -7.973 |
oulos | -7.970 |
agascar | -7.938 |
Token | object |
Token ID | 15252 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
dump | +1.573 |
Random | +1.566 |
nam | +1.506 |
Sham | +1.462 |
ASA | +1.349 |
Neg logit contributions | |
orian | -2.966 |
kson | -2.877 |
helicop | -2.846 |
agascar | -2.814 |
oulos | -2.803 |
Token | system |
Token ID | 1080 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
dump | +2.220 |
Random | +2.208 |
Sham | +2.196 |
nam | +2.154 |
ASA | +2.052 |
Neg logit contributions | |
orian | -2.683 |
kson | -2.583 |
orb | -2.544 |
oulos | -2.489 |
arious | -2.480 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Random | +1.106 |
dump | +1.095 |
nam | +1.078 |
Sham | +1.077 |
ASA | +1.003 |
Neg logit contributions | |
orian | -1.339 |
helicop | -1.294 |
kson | -1.278 |
orb | -1.273 |
oulos | -1.263 |
Token | draw |
Token ID | 19334 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
dump | +1.279 |
Random | +1.273 |
Sham | +1.251 |
nam | +1.237 |
ASA | +1.157 |
Neg logit contributions | |
orian | -2.476 |
kson | -2.378 |
orb | -2.372 |
rupal | -2.313 |
oulos | -2.308 |
Token | il |
Token ID | 346 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
dump | +0.740 |
Random | +0.734 |
Sham | +0.729 |
nam | +0.725 |
ASA | +0.689 |
Neg logit contributions | |
orian | -0.720 |
kson | -0.680 |
orb | -0.677 |
rupal | -0.657 |
oulos | -0.654 |
Token | ine |
Token ID | 500 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
dump | +1.390 |
Sham | +1.384 |
Random | +1.372 |
nam | +1.372 |
ASA | +1.263 |
Neg logit contributions | |
orian | -2.568 |
kson | -2.502 |
orb | -2.458 |
oulos | -2.415 |
natureconservancy | -2.404 |
Token | $ |
Token ID | 720 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
dump | +0.288 |
Random | +0.287 |
Sham | +0.285 |
nam | +0.281 |
ASA | +0.268 |
Neg logit contributions | |
orian | -0.388 |
orb | -0.370 |
kson | -0.369 |
rupal | -0.359 |
oulos | -0.357 |
Token | art |
Token ID | 433 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
dump | +2.471 |
Random | +2.449 |
nam | +2.395 |
Sham | +2.377 |
ASA | +2.218 |
Neg logit contributions | |
orian | -3.166 |
kson | -3.029 |
orb | -2.967 |
oulos | -2.936 |
rupal | -2.932 |
Token | ext |
Token ID | 2302 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
dump | +1.442 |
Random | +1.429 |
nam | +1.403 |
Sham | +1.402 |
ASA | +1.314 |
Neg logit contributions | |
orian | -2.068 |
kson | -1.991 |
orb | -1.976 |
rupal | -1.927 |
oulos | -1.924 |
Token | = |
Token ID | 796 |
Feature activation | -8.92e+00 |
Pos logit contributions | |
dump | +0.204 |
Sham | +0.204 |
Random | +0.204 |
nam | +0.199 |
ASA | +0.191 |
Neg logit contributions | |
orian | -0.319 |
orb | -0.306 |
kson | -0.303 |
rupal | -0.295 |
oulos | -0.294 |
Token | ($ |
Token ID | 7198 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
dump | +4.641 |
Random | +4.522 |
Sham | +4.522 |
nam | +4.310 |
Ut | +4.196 |
Neg logit contributions | |
orian | -7.529 |
kson | -7.170 |
orb | -7.147 |
arious | -7.086 |
oulos | -7.069 |
Token | text |
Token ID | 5239 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
Random | +2.483 |
dump | +2.456 |
Sham | +2.399 |
nam | +2.390 |
ASA | +2.233 |
Neg logit contributions | |
orian | -3.391 |
kson | -3.254 |
orb | -3.194 |
oulos | -3.166 |
rupal | -3.153 |
Token | - |
Token ID | 532 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
orian | +0.728 |
orb | +0.696 |
kson | +0.688 |
rupal | +0.668 |
arious | +0.663 |
Neg logit contributions | |
Sham | -0.516 |
dump | -0.514 |
Random | -0.513 |
nam | -0.505 |
ASA | -0.487 |
Token | split |
Token ID | 35312 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
dump | +2.215 |
Random | +2.212 |
nam | +2.165 |
Sham | +2.160 |
ASA | +2.017 |
Neg logit contributions | |
orian | -3.152 |
kson | -3.020 |
orb | -2.986 |
rupal | -2.931 |
oulos | -2.922 |
Token | "\ |
Token ID | 37082 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
Random | +2.543 |
dump | +2.539 |
Sham | +2.507 |
nam | +2.487 |
ASA | +2.319 |
Neg logit contributions | |
orian | -3.864 |
kson | -3.692 |
orb | -3.659 |
rupal | -3.602 |
oulos | -3.593 |
Token | text |
Token ID | 5239 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
dump | +3.250 |
Random | +3.226 |
nam | +3.190 |
Sham | +3.106 |
ASA | +2.941 |
Neg logit contributions | |
orian | -3.732 |
kson | -3.592 |
oulos | -3.526 |
orb | -3.517 |
rupal | -3.438 |
Token | ] |
Token ID | 60 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
dump | +1.572 |
Random | +1.557 |
nam | +1.529 |
Sham | +1.529 |
ASA | +1.442 |
Neg logit contributions | |
orian | -2.141 |
kson | -2.057 |
orb | -2.042 |
oulos | -2.002 |
rupal | -1.994 |
Token | { |
Token ID | 90 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
dump | +2.752 |
Random | +2.750 |
nam | +2.685 |
Sham | +2.664 |
ASA | +2.506 |
Neg logit contributions | |
orian | -3.355 |
kson | -3.201 |
orb | -3.199 |
oulos | -3.151 |
arious | -3.081 |
Token | white |
Token ID | 11186 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
dump | +0.943 |
Random | +0.941 |
Sham | +0.924 |
nam | +0.922 |
ASA | +0.873 |
Neg logit contributions | |
orian | -1.130 |
kson | -1.077 |
orb | -1.072 |
oulos | -1.042 |
rupal | -1.041 |
Token | }{ |
Token ID | 18477 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
dump | +2.285 |
Random | +2.284 |
Sham | +2.258 |
nam | +2.247 |
ASA | +2.107 |
Neg logit contributions | |
orian | -2.830 |
kson | -2.733 |
orb | -2.665 |
oulos | -2.652 |
rupal | -2.643 |
Token | vi |
Token ID | 8903 |
Feature activation | -8.91e+00 |
Pos logit contributions | |
dump | +0.889 |
Random | +0.888 |
Sham | +0.874 |
nam | +0.871 |
ASA | +0.827 |
Neg logit contributions | |
orian | -0.962 |
kson | -0.916 |
orb | -0.908 |
rupal | -0.885 |
oulos | -0.884 |
Token | : |
Token ID | 25 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Random | +5.433 |
dump | +5.407 |
nam | +5.320 |
Sham | +5.316 |
ASA | +4.921 |
Neg logit contributions | |
orian | -6.423 |
oulos | -6.167 |
kson | -6.112 |
rupal | -6.060 |
orb | -6.013 |
Token | | |
Token ID | 91 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
dump | +1.618 |
Random | +1.614 |
nam | +1.586 |
Sham | +1.584 |
ASA | +1.503 |
Neg logit contributions | |
orian | -1.757 |
kson | -1.666 |
orb | -1.658 |
oulos | -1.613 |
rupal | -1.609 |
Token | vim |
Token ID | 31124 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
dump | +2.507 |
Random | +2.477 |
nam | +2.443 |
Sham | +2.406 |
ASA | +2.285 |
Neg logit contributions | |
orian | -2.941 |
kson | -2.792 |
orb | -2.771 |
oulos | -2.744 |
rupal | -2.692 |
Token | : |
Token ID | 25 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
dump | +4.720 |
Random | +4.546 |
nam | +4.541 |
Sham | +4.459 |
ASA | +4.205 |
Neg logit contributions | |
orian | -5.140 |
oulos | -4.920 |
kson | -4.898 |
orb | -4.841 |
rupal | -4.749 |
Token | | |
Token ID | 91 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
dump | +1.810 |
Random | +1.798 |
nam | +1.766 |
Sham | +1.758 |
ASA | +1.667 |
Neg logit contributions | |
orian | -2.079 |
kson | -1.975 |
orb | -1.965 |
oulos | -1.926 |
rupal | -1.907 |
Token | of |
Token ID | 286 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Sham | +2.735 |
dump | +2.695 |
Random | +2.688 |
nam | +2.683 |
unres | +2.569 |
Neg logit contributions | |
orian | -3.463 |
kson | -3.341 |
orb | -3.336 |
oulos | -3.222 |
rupal | -3.195 |
Token | Muhammad |
Token ID | 15870 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
dump | +0.759 |
Random | +0.756 |
Sham | +0.746 |
nam | +0.739 |
ASA | +0.703 |
Neg logit contributions | |
orian | -1.074 |
orb | -1.025 |
kson | -1.023 |
rupal | -0.994 |
oulos | -0.990 |
Token | with |
Token ID | 351 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
orian | +2.676 |
orb | +2.527 |
kson | +2.511 |
rupal | +2.438 |
oulos | +2.437 |
Neg logit contributions | |
Random | -2.387 |
dump | -2.379 |
nam | -2.304 |
Sham | -2.303 |
ASA | -2.233 |
Token | his |
Token ID | 465 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Sham | +1.952 |
dump | +1.921 |
Random | +1.915 |
nam | +1.897 |
ASA | +1.803 |
Neg logit contributions | |
orian | -2.845 |
orb | -2.723 |
kson | -2.711 |
rupal | -2.638 |
oulos | -2.631 |
Token | hands |
Token ID | 2832 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
dump | +0.311 |
Random | +0.311 |
Sham | +0.304 |
nam | +0.302 |
ASA | +0.288 |
Neg logit contributions | |
orian | -0.422 |
kson | -0.402 |
orb | -0.402 |
rupal | -0.388 |
oulos | -0.387 |
Token | tied |
Token ID | 8165 |
Feature activation | -8.88e+00 |
Pos logit contributions | |
Sham | +2.549 |
dump | +2.546 |
nam | +2.513 |
Random | +2.488 |
unres | +2.383 |
Neg logit contributions | |
orian | -4.295 |
kson | -4.126 |
orb | -4.069 |
oulos | -4.033 |
rupal | -3.995 |
Token | to |
Token ID | 284 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
Sham | +4.414 |
nam | +4.357 |
Random | +4.242 |
dump | +4.201 |
unres | +4.143 |
Neg logit contributions | |
orian | -7.393 |
kson | -7.235 |
oulos | -7.173 |
rupal | -7.142 |
orb | -7.094 |
Token | his |
Token ID | 465 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Sham | +1.958 |
dump | +1.954 |
Random | +1.934 |
nam | +1.926 |
ASA | +1.816 |
Neg logit contributions | |
orian | -3.116 |
orb | -2.992 |
kson | -2.987 |
oulos | -2.914 |
rupal | -2.911 |
Token | neck |
Token ID | 7393 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
dump | +0.251 |
Random | +0.251 |
Sham | +0.247 |
nam | +0.245 |
ASA | +0.236 |
Neg logit contributions | |
orian | -0.254 |
orb | -0.240 |
kson | -0.240 |
rupal | -0.231 |
oulos | -0.229 |
Token | with |
Token ID | 351 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
dump | +1.218 |
Random | +1.211 |
Sham | +1.209 |
nam | +1.199 |
ASA | +1.138 |
Neg logit contributions | |
orian | -1.455 |
orb | -1.385 |
kson | -1.382 |
rupal | -1.341 |
oulos | -1.339 |
Token | a |
Token ID | 257 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Sham | +3.055 |
nam | +2.971 |
dump | +2.963 |
Random | +2.939 |
ASA | +2.808 |
Neg logit contributions | |
orian | -4.467 |
orb | -4.300 |
kson | -4.281 |
oulos | -4.183 |
rupal | -4.161 |
Token | the |
Token ID | 262 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
dump | +0.114 |
Random | +0.114 |
Sham | +0.113 |
nam | +0.111 |
ASA | +0.106 |
Neg logit contributions | |
orian | -0.152 |
orb | -0.145 |
kson | -0.145 |
rupal | -0.140 |
oulos | -0.140 |
Token | point |
Token ID | 966 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
dump | +1.454 |
Sham | +1.445 |
Random | +1.443 |
nam | +1.419 |
ASA | +1.374 |
Neg logit contributions | |
orian | -1.539 |
orb | -1.459 |
kson | -1.449 |
oulos | -1.414 |
rupal | -1.413 |
Token | where |
Token ID | 810 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
dump | +2.227 |
Random | +2.216 |
Sham | +2.212 |
nam | +2.173 |
ASA | +2.071 |
Neg logit contributions | |
orian | -2.688 |
orb | -2.570 |
kson | -2.560 |
rupal | -2.499 |
oulos | -2.497 |
Token | I |
Token ID | 314 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
dump | +0.042 |
Random | +0.042 |
Sham | +0.041 |
nam | +0.041 |
ASA | +0.039 |
Neg logit contributions | |
orian | -0.057 |
orb | -0.054 |
kson | -0.054 |
rupal | -0.052 |
oulos | -0.052 |
Token | tried |
Token ID | 3088 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
dump | +1.272 |
Sham | +1.250 |
Random | +1.245 |
nam | +1.237 |
ASA | +1.167 |
Neg logit contributions | |
orian | -1.522 |
kson | -1.444 |
orb | -1.434 |
rupal | -1.408 |
arious | -1.398 |
Token | masturb |
Token ID | 22938 |
Feature activation | -8.85e+00 |
Pos logit contributions | |
orian | +0.279 |
orb | +0.265 |
kson | +0.264 |
rupal | +0.255 |
oulos | +0.254 |
Neg logit contributions | |
dump | -0.271 |
Random | -0.271 |
Sham | -0.269 |
nam | -0.266 |
ASA | -0.255 |
Token | ating |
Token ID | 803 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
dump | +3.482 |
nam | +3.439 |
Random | +3.433 |
Sham | +3.311 |
ASA | +2.985 |
Neg logit contributions | |
orian | -8.324 |
kson | -8.214 |
orb | -8.048 |
oulos | -7.931 |
rupal | -7.909 |
Token | as |
Token ID | 355 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
dump | +1.824 |
Random | +1.820 |
Sham | +1.809 |
nam | +1.779 |
unres | +1.693 |
Neg logit contributions | |
orian | -2.103 |
kson | -2.013 |
orb | -1.995 |
oulos | -1.950 |
rupal | -1.945 |
Token | Bruce |
Token ID | 11088 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
dump | +0.767 |
Random | +0.766 |
Sham | +0.760 |
nam | +0.748 |
ASA | +0.712 |
Neg logit contributions | |
orian | -1.059 |
orb | -1.011 |
kson | -1.010 |
rupal | -0.984 |
oulos | -0.978 |
Token | C |
Token ID | 327 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
dump | +0.070 |
Random | +0.070 |
Sham | +0.070 |
nam | +0.069 |
ASA | +0.065 |
Neg logit contributions | |
orian | -0.078 |
orb | -0.075 |
kson | -0.074 |
rupal | -0.072 |
oulos | -0.072 |
Token | odd |
Token ID | 5088 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
dump | +1.524 |
Random | +1.509 |
nam | +1.500 |
Sham | +1.464 |
Jew | +1.349 |
Neg logit contributions | |
orian | -1.968 |
helicop | -1.907 |
orb | -1.884 |
kson | -1.881 |
arious | -1.837 |
Token | the |
Token ID | 262 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
orian | +1.940 |
orb | +1.847 |
kson | +1.845 |
rupal | +1.783 |
oulos | +1.773 |
Neg logit contributions | |
Random | -1.478 |
dump | -1.474 |
Sham | -1.444 |
nam | -1.437 |
ASA | -1.373 |
Token | contact |
Token ID | 2800 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
orian | +0.620 |
orb | +0.589 |
kson | +0.588 |
rupal | +0.569 |
oulos | +0.567 |
Neg logit contributions | |
dump | -0.553 |
Random | -0.552 |
Sham | -0.548 |
nam | -0.542 |
ASA | -0.519 |
Token | of |
Token ID | 286 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
dump | +0.133 |
Random | +0.133 |
Sham | +0.131 |
nam | +0.130 |
ASA | +0.125 |
Neg logit contributions | |
orian | -0.148 |
orb | -0.140 |
kson | -0.140 |
rupal | -0.135 |
oulos | -0.135 |
Token | her |
Token ID | 607 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
orian | +0.961 |
orb | +0.914 |
kson | +0.912 |
rupal | +0.881 |
oulos | +0.880 |
Neg logit contributions | |
dump | -0.705 |
Random | -0.702 |
Sham | -0.685 |
nam | -0.683 |
ASA | -0.648 |
Token | lips |
Token ID | 11914 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
dump | +0.406 |
Random | +0.405 |
Sham | +0.402 |
nam | +0.398 |
ASA | +0.380 |
Neg logit contributions | |
orian | -0.456 |
orb | -0.433 |
kson | -0.433 |
rupal | -0.419 |
oulos | -0.417 |
Token | against |
Token ID | 1028 |
Feature activation | -8.83e+00 |
Pos logit contributions | |
nam | +3.935 |
dump | +3.912 |
Sham | +3.901 |
Random | +3.868 |
unres | +3.714 |
Neg logit contributions | |
orian | -4.348 |
kson | -4.188 |
rupal | -4.087 |
oulos | -4.036 |
orb | -4.035 |
Token | mine |
Token ID | 6164 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
Sham | +5.242 |
Random | +5.104 |
nam | +5.102 |
dump | +5.079 |
ASA | +4.887 |
Neg logit contributions | |
orian | -6.554 |
orb | -6.362 |
kson | -6.355 |
oulos | -6.225 |
agascar | -6.192 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
dump | +3.069 |
Random | +3.042 |
Sham | +3.041 |
nam | +3.027 |
unres | +2.878 |
Neg logit contributions | |
orian | -3.974 |
kson | -3.766 |
orb | -3.754 |
oulos | -3.681 |
rupal | -3.671 |
Token |
|
Token ID | 198 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
Sham | +1.321 |
Random | +1.314 |
dump | +1.309 |
nam | +1.278 |
ASA | +1.231 |
Neg logit contributions | |
orian | -1.829 |
orb | -1.751 |
kson | -1.733 |
rupal | -1.700 |
oulos | -1.688 |
Token |
|
Token ID | 198 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Random | +0.415 |
dump | +0.412 |
Sham | +0.411 |
nam | +0.407 |
ASA | +0.384 |
Neg logit contributions | |
orian | -0.476 |
orb | -0.452 |
kson | -0.451 |
helicop | -0.449 |
oulos | -0.440 |
Token | " |
Token ID | 1 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
dump | +0.220 |
Sham | +0.218 |
Random | +0.217 |
nam | +0.214 |
ASA | +0.205 |
Neg logit contributions | |
orian | -0.375 |
orb | -0.359 |
kson | -0.357 |
rupal | -0.347 |
arious | -0.345 |
Token | T |
Token ID | 309 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
orian | +0.551 |
orb | +0.522 |
kson | +0.522 |
rupal | +0.503 |
oulos | +0.502 |
Neg logit contributions | |
dump | -0.553 |
Random | -0.550 |
Sham | -0.546 |
nam | -0.542 |
ASA | -0.520 |
Token | > |
Token ID | 1875 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
dump | +1.123 |
Random | +1.119 |
Sham | +1.109 |
nam | +1.093 |
ASA | +1.041 |
Neg logit contributions | |
orian | -1.635 |
orb | -1.563 |
kson | -1.561 |
rupal | -1.514 |
oulos | -1.508 |
Token | { |
Token ID | 1391 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
dump | +0.257 |
Random | +0.256 |
Sham | +0.252 |
nam | +0.249 |
ASA | +0.238 |
Neg logit contributions | |
orian | -0.362 |
kson | -0.345 |
orb | -0.345 |
rupal | -0.334 |
oulos | -0.334 |
Token | pub |
Token ID | 2240 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
dump | +0.206 |
Random | +0.205 |
Sham | +0.203 |
nam | +0.201 |
ASA | +0.192 |
Neg logit contributions | |
orian | -0.250 |
orb | -0.237 |
kson | -0.237 |
rupal | -0.230 |
oulos | -0.228 |
Token | fn |
Token ID | 24714 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
dump | +0.921 |
Random | +0.917 |
Sham | +0.905 |
nam | +0.890 |
ASA | +0.831 |
Neg logit contributions | |
orian | -2.063 |
orb | -1.984 |
kson | -1.981 |
rupal | -1.933 |
oulos | -1.927 |
Token | load |
Token ID | 3440 |
Feature activation | -8.83e+00 |
Pos logit contributions | |
dump | +3.010 |
Random | +2.936 |
nam | +2.876 |
Sham | +2.849 |
unres | +2.762 |
Neg logit contributions | |
orian | -4.603 |
kson | -4.428 |
orb | -4.359 |
oulos | -4.333 |
rupal | -4.303 |
Token | < |
Token ID | 1279 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Random | +5.051 |
dump | +4.862 |
nam | +4.716 |
Sham | +4.607 |
ASA | +4.361 |
Neg logit contributions | |
orian | -7.156 |
kson | -6.866 |
orb | -6.780 |
rupal | -6.728 |
oulos | -6.680 |
Token | ' |
Token ID | 705 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Random | +1.444 |
Sham | +1.436 |
dump | +1.436 |
nam | +1.397 |
ASA | +1.342 |
Neg logit contributions | |
orian | -1.936 |
orb | -1.842 |
kson | -1.814 |
rupal | -1.798 |
arious | -1.787 |
Token | a |
Token ID | 64 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
dump | +1.563 |
Random | +1.560 |
Sham | +1.536 |
nam | +1.520 |
ASA | +1.441 |
Neg logit contributions | |
orian | -2.007 |
kson | -1.906 |
orb | -1.903 |
rupal | -1.854 |
oulos | -1.842 |
Token | > |
Token ID | 1875 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
dump | +1.329 |
Random | +1.326 |
Sham | +1.314 |
nam | +1.298 |
ASA | +1.239 |
Neg logit contributions | |
orian | -1.674 |
orb | -1.593 |
kson | -1.591 |
rupal | -1.543 |
oulos | -1.536 |
Token | ( |
Token ID | 357 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
dump | +0.562 |
Random | +0.560 |
Sham | +0.557 |
nam | +0.550 |
ASA | +0.528 |
Neg logit contributions | |
orian | -0.620 |
orb | -0.590 |
kson | -0.588 |
rupal | -0.569 |
oulos | -0.566 |
Token | How |
Token ID | 1374 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
orian | +3.557 |
orb | +3.333 |
kson | +3.319 |
oulos | +3.278 |
tale | +3.193 |
Neg logit contributions | |
dump | -4.050 |
Random | -3.945 |
nam | -3.936 |
Sham | -3.875 |
unres | -3.764 |
Token | St |
Token ID | 1273 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
orian | +2.104 |
orb | +2.025 |
kson | +2.023 |
rupal | +1.974 |
oulos | +1.965 |
Neg logit contributions | |
dump | -0.892 |
Random | -0.885 |
Sham | -0.876 |
nam | -0.860 |
ASA | -0.803 |
Token | uff |
Token ID | 1648 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
orian | +1.922 |
orb | +1.813 |
kson | +1.794 |
rupal | +1.733 |
oulos | +1.704 |
Neg logit contributions | |
dump | -2.397 |
Sham | -2.394 |
Random | -2.387 |
nam | -2.349 |
ASA | -2.319 |
Token | Works |
Token ID | 23044 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Random | +0.605 |
dump | +0.595 |
nam | +0.576 |
Sham | +0.570 |
ASA | +0.520 |
Neg logit contributions | |
orian | -1.263 |
orb | -1.214 |
kson | -1.202 |
helicop | -1.191 |
oulos | -1.186 |
Token | . |
Token ID | 13 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
orian | +1.577 |
orb | +1.495 |
kson | +1.492 |
rupal | +1.441 |
oulos | +1.433 |
Neg logit contributions | |
dump | -1.546 |
Random | -1.540 |
Sham | -1.529 |
nam | -1.512 |
ASA | -1.452 |
Token | com |
Token ID | 785 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
orian | +2.542 |
orb | +2.418 |
kson | +2.409 |
rupal | +2.332 |
oulos | +2.319 |
Neg logit contributions | |
dump | -2.203 |
Random | -2.198 |
Sham | -2.182 |
nam | -2.145 |
ASA | -2.067 |
Token |
|
Token ID | 198 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
orian | +3.826 |
orb | +3.602 |
kson | +3.551 |
oulos | +3.461 |
rupal | +3.413 |
Neg logit contributions | |
dump | -4.264 |
Random | -4.244 |
Sham | -4.227 |
nam | -4.189 |
ASA | -3.994 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
orian | +2.233 |
orb | +2.115 |
kson | +2.108 |
rupal | +2.029 |
tale | +2.006 |
Neg logit contributions | |
dump | -2.400 |
Random | -2.386 |
Sham | -2.367 |
nam | -2.338 |
ASA | -2.268 |
Token | The |
Token ID | 464 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
orian | +1.403 |
orb | +1.350 |
kson | +1.330 |
rupal | +1.290 |
oulos | +1.283 |
Neg logit contributions | |
Sham | -0.910 |
dump | -0.908 |
Random | -0.888 |
nam | -0.882 |
ASA | -0.856 |
Token | next |
Token ID | 1306 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
orian | +0.130 |
orb | +0.124 |
kson | +0.124 |
rupal | +0.120 |
oulos | +0.120 |
Neg logit contributions | |
dump | -0.105 |
Random | -0.105 |
Sham | -0.104 |
nam | -0.102 |
ASA | -0.098 |
Token | breakthrough |
Token ID | 19304 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
dump | +0.472 |
Random | +0.471 |
Sham | +0.469 |
nam | +0.462 |
ASA | +0.446 |
Neg logit contributions | |
orian | -0.537 |
kson | -0.513 |
orb | -0.510 |
rupal | -0.496 |
oulos | -0.494 |
Token | be |
Token ID | 307 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
orian | +1.121 |
orb | +1.071 |
kson | +1.069 |
rupal | +1.037 |
oulos | +1.035 |
Neg logit contributions | |
Random | -0.810 |
dump | -0.809 |
Sham | -0.799 |
nam | -0.788 |
ASA | -0.752 |
Token | locked |
Token ID | 8970 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
orian | +1.050 |
orb | +0.999 |
kson | +0.997 |
rupal | +0.967 |
oulos | +0.963 |
Neg logit contributions | |
dump | -0.861 |
Random | -0.859 |
Sham | -0.852 |
nam | -0.843 |
ASA | -0.804 |
Token | up |
Token ID | 510 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
dump | +0.180 |
Random | +0.179 |
Sham | +0.177 |
nam | +0.174 |
ASA | +0.164 |
Neg logit contributions | |
orian | -0.347 |
orb | -0.333 |
kson | -0.332 |
rupal | -0.324 |
oulos | -0.323 |
Token | ? |
Token ID | 30 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
dump | +1.831 |
Random | +1.826 |
Sham | +1.822 |
nam | +1.807 |
unres | +1.707 |
Neg logit contributions | |
orian | -2.290 |
kson | -2.187 |
orb | -2.185 |
rupal | -2.127 |
arious | -2.111 |
Token | It |
Token ID | 632 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
orian | +0.330 |
orb | +0.315 |
kson | +0.313 |
rupal | +0.304 |
oulos | +0.303 |
Neg logit contributions | |
Random | -0.264 |
dump | -0.264 |
Sham | -0.263 |
nam | -0.258 |
ASA | -0.247 |
Token | depends |
Token ID | 8338 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
dump | +0.535 |
Random | +0.532 |
Sham | +0.531 |
nam | +0.524 |
ASA | +0.496 |
Neg logit contributions | |
orian | -0.673 |
orb | -0.643 |
kson | -0.640 |
rupal | -0.622 |
oulos | -0.620 |
Token | on |
Token ID | 319 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
orian | +3.656 |
kson | +3.419 |
orb | +3.395 |
tale | +3.302 |
oulos | +3.264 |
Neg logit contributions | |
dump | -4.611 |
Random | -4.590 |
Sham | -4.525 |
nam | -4.479 |
ASA | -4.382 |
Token | how |
Token ID | 703 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
orian | +1.832 |
kson | +1.737 |
orb | +1.734 |
oulos | +1.677 |
rupal | +1.674 |
Neg logit contributions | |
dump | -1.532 |
Random | -1.527 |
Sham | -1.500 |
nam | -1.492 |
ASA | -1.424 |
Token | you |
Token ID | 345 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
orian | +0.246 |
orb | +0.234 |
kson | +0.233 |
rupal | +0.227 |
oulos | +0.226 |
Neg logit contributions | |
dump | -0.191 |
Random | -0.191 |
Sham | -0.189 |
nam | -0.186 |
ASA | -0.178 |
Token | define |
Token ID | 8160 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
orian | +0.613 |
orb | +0.583 |
kson | +0.582 |
rupal | +0.564 |
oulos | +0.562 |
Neg logit contributions | |
dump | -0.510 |
Random | -0.507 |
Sham | -0.503 |
nam | -0.498 |
ASA | -0.475 |
Token | a |
Token ID | 257 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Random | +1.357 |
dump | +1.354 |
Sham | +1.353 |
nam | +1.324 |
ASA | +1.254 |
Neg logit contributions | |
orian | -1.983 |
orb | -1.896 |
kson | -1.895 |
rupal | -1.843 |
oulos | -1.833 |
Token | Some |
Token ID | 4366 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
dump | +0.056 |
Random | +0.056 |
Sham | +0.055 |
nam | +0.054 |
ASA | +0.052 |
Neg logit contributions | |
orian | -0.087 |
orb | -0.083 |
kson | -0.083 |
rupal | -0.081 |
oulos | -0.080 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
orian | +1.152 |
orb | +1.092 |
kson | +1.091 |
rupal | +1.057 |
oulos | +1.053 |
Neg logit contributions | |
dump | -0.971 |
Random | -0.967 |
Sham | -0.958 |
nam | -0.949 |
ASA | -0.905 |
Token | of |
Token ID | 286 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
orian | +0.785 |
orb | +0.742 |
kson | +0.739 |
rupal | +0.713 |
arious | +0.709 |
Neg logit contributions | |
dump | -0.755 |
Random | -0.752 |
Sham | -0.746 |
nam | -0.736 |
ASA | -0.707 |
Token | bailout |
Token ID | 29928 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
dump | +0.492 |
Random | +0.490 |
Sham | +0.488 |
nam | +0.482 |
ASA | +0.461 |
Neg logit contributions | |
orian | -0.587 |
orb | -0.559 |
kson | -0.558 |
rupal | -0.540 |
oulos | -0.537 |
Token | , |
Token ID | 11 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
orian | +0.215 |
orb | +0.204 |
kson | +0.204 |
rupal | +0.197 |
oulos | +0.197 |
Neg logit contributions | |
dump | -0.182 |
Random | -0.182 |
Sham | -0.180 |
nam | -0.178 |
ASA | -0.170 |
Token | whether |
Token ID | 1771 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
dump | +0.035 |
Random | +0.035 |
Sham | +0.035 |
nam | +0.034 |
ASA | +0.033 |
Neg logit contributions | |
orian | -0.044 |
orb | -0.042 |
kson | -0.042 |
rupal | -0.041 |
oulos | -0.041 |
Token | granted |
Token ID | 7520 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
orian | +4.092 |
orb | +3.895 |
kson | +3.806 |
arious | +3.724 |
rupal | +3.718 |
Neg logit contributions | |
dump | -3.626 |
Random | -3.574 |
nam | -3.502 |
Sham | -3.483 |
ASA | -3.325 |
Token | with |
Token ID | 351 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
orian | +1.757 |
orb | +1.668 |
kson | +1.654 |
rupal | +1.605 |
oulos | +1.595 |
Neg logit contributions | |
dump | -1.636 |
Random | -1.629 |
Sham | -1.612 |
nam | -1.598 |
ASA | -1.534 |
Token | soft |
Token ID | 2705 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
dump | +0.797 |
Random | +0.793 |
Sham | +0.791 |
nam | +0.778 |
ASA | +0.742 |
Neg logit contributions | |
orian | -1.109 |
orb | -1.060 |
kson | -1.059 |
rupal | -1.027 |
oulos | -1.022 |
Token | or |
Token ID | 393 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
orian | +1.507 |
orb | +1.438 |
kson | +1.424 |
arious | +1.378 |
rupal | +1.377 |
Neg logit contributions | |
dump | -1.199 |
Random | -1.195 |
Sham | -1.182 |
nam | -1.159 |
ASA | -1.115 |
Token | tough |
Token ID | 5802 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
nam | +1.457 |
Random | +1.441 |
dump | +1.440 |
Sham | +1.439 |
ASA | +1.362 |
Neg logit contributions | |
orian | -1.799 |
orb | -1.722 |
kson | -1.718 |
oulos | -1.660 |
rupal | -1.655 |
Token | 's |
Token ID | 338 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
dump | +0.553 |
Random | +0.547 |
Sham | +0.546 |
nam | +0.540 |
ASA | +0.513 |
Neg logit contributions | |
orian | -0.688 |
orb | -0.653 |
kson | -0.652 |
rupal | -0.635 |
oulos | -0.633 |
Token | our |
Token ID | 674 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
orian | +0.111 |
orb | +0.106 |
kson | +0.105 |
rupal | +0.102 |
oulos | +0.102 |
Neg logit contributions | |
dump | -0.080 |
Random | -0.080 |
Sham | -0.079 |
nam | -0.078 |
ASA | -0.074 |
Token | version |
Token ID | 2196 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
dump | +0.248 |
Random | +0.247 |
Sham | +0.245 |
nam | +0.242 |
ASA | +0.230 |
Neg logit contributions | |
orian | -0.352 |
orb | -0.336 |
kson | -0.335 |
rupal | -0.326 |
oulos | -0.325 |
Token | of |
Token ID | 286 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
orian | +0.791 |
orb | +0.749 |
kson | +0.742 |
rupal | +0.714 |
oulos | +0.708 |
Neg logit contributions | |
dump | -0.819 |
Random | -0.815 |
Sham | -0.799 |
nam | -0.798 |
ASA | -0.766 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
orian | +1.461 |
orb | +1.406 |
kson | +1.400 |
rupal | +1.351 |
oulos | +1.344 |
Neg logit contributions | |
dump | -1.110 |
Random | -1.110 |
nam | -1.088 |
Sham | -1.087 |
ASA | -1.025 |
Token | Martian |
Token ID | 32508 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
orian | +1.087 |
orb | +1.040 |
kson | +1.039 |
rupal | +1.003 |
oulos | +0.999 |
Neg logit contributions | |
dump | -0.834 |
Random | -0.832 |
Sham | -0.820 |
nam | -0.815 |
ASA | -0.775 |
Token | car |
Token ID | 1097 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
orian | +4.258 |
orb | +4.095 |
kson | +4.090 |
tale | +3.887 |
rupal | +3.880 |
Neg logit contributions | |
Random | -3.449 |
dump | -3.415 |
nam | -3.398 |
Sham | -3.343 |
ASA | -3.218 |
Token | wash |
Token ID | 34670 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
dump | +0.454 |
Random | +0.450 |
Sham | +0.447 |
nam | +0.443 |
ASA | +0.426 |
Neg logit contributions | |
orian | -0.456 |
kson | -0.434 |
orb | -0.430 |
oulos | -0.419 |
rupal | -0.419 |
Token | ," |
Token ID | 553 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
dump | +1.290 |
Sham | +1.287 |
Random | +1.275 |
nam | +1.252 |
ASA | +1.203 |
Neg logit contributions | |
orian | -1.726 |
orb | -1.632 |
kson | -1.631 |
oulos | -1.601 |
rupal | -1.595 |
Token | said |
Token ID | 531 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
orian | +1.815 |
orb | +1.738 |
kson | +1.732 |
rupal | +1.657 |
oulos | +1.652 |
Neg logit contributions | |
dump | -1.912 |
Random | -1.901 |
nam | -1.863 |
Sham | -1.856 |
ASA | -1.771 |
Token | Chris |
Token ID | 5180 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Sham | +1.504 |
dump | +1.488 |
Random | +1.484 |
nam | +1.459 |
ASA | +1.421 |
Neg logit contributions | |
orian | -1.813 |
orb | -1.710 |
kson | -1.703 |
rupal | -1.671 |
oulos | -1.662 |
Token | which |
Token ID | 543 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
dump | +0.054 |
Random | +0.054 |
Sham | +0.053 |
nam | +0.053 |
ASA | +0.050 |
Neg logit contributions | |
orian | -0.067 |
orb | -0.063 |
kson | -0.063 |
rupal | -0.061 |
oulos | -0.061 |
Token | were |
Token ID | 547 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
dump | +1.188 |
Random | +1.184 |
Sham | +1.179 |
nam | +1.164 |
ASA | +1.117 |
Neg logit contributions | |
orian | -1.367 |
kson | -1.294 |
orb | -1.293 |
rupal | -1.259 |
oulos | -1.251 |
Token | considered |
Token ID | 3177 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
orian | +0.223 |
orb | +0.213 |
kson | +0.213 |
rupal | +0.206 |
oulos | +0.205 |
Neg logit contributions | |
dump | -0.169 |
Random | -0.169 |
Sham | -0.167 |
nam | -0.165 |
ASA | -0.157 |
Token | likely |
Token ID | 1884 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
orian | +0.391 |
orb | +0.374 |
kson | +0.371 |
rupal | +0.359 |
oulos | +0.356 |
Neg logit contributions | |
dump | -0.335 |
Random | -0.335 |
Sham | -0.330 |
nam | -0.326 |
ASA | -0.312 |
Token | Apollo |
Token ID | 17508 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
dump | +0.609 |
Random | +0.607 |
Sham | +0.602 |
nam | +0.596 |
ASA | +0.573 |
Neg logit contributions | |
orian | -0.597 |
orb | -0.565 |
kson | -0.564 |
rupal | -0.545 |
oulos | -0.542 |
Token | landing |
Token ID | 9581 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
orian | +2.664 |
orb | +2.588 |
kson | +2.528 |
oulos | +2.440 |
rupal | +2.434 |
Neg logit contributions | |
Random | -2.383 |
dump | -2.377 |
Sham | -2.349 |
nam | -2.315 |
ASA | -2.237 |
Token | sites |
Token ID | 5043 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
orian | +4.405 |
orb | +4.338 |
kson | +4.297 |
rupal | +4.041 |
arious | +4.021 |
Neg logit contributions | |
Random | -4.455 |
dump | -4.396 |
nam | -4.306 |
Sham | -4.288 |
ASA | -4.106 |
Token | . |
Token ID | 13 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
orian | +2.468 |
orb | +2.366 |
kson | +2.336 |
rupal | +2.240 |
arious | +2.220 |
Neg logit contributions | |
Random | -2.607 |
dump | -2.605 |
Sham | -2.555 |
nam | -2.532 |
ASA | -2.449 |
Token | On |
Token ID | 1550 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
orian | +0.024 |
orb | +0.023 |
kson | +0.023 |
rupal | +0.023 |
oulos | +0.022 |
Neg logit contributions | |
dump | -0.019 |
Random | -0.019 |
Sham | -0.019 |
nam | -0.019 |
ASA | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
orian | +0.697 |
orb | +0.664 |
kson | +0.662 |
rupal | +0.640 |
oulos | +0.637 |
Neg logit contributions | |
dump | -0.610 |
Random | -0.609 |
Sham | -0.603 |
nam | -0.597 |
ASA | -0.571 |
Token | first |
Token ID | 717 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
dump | +0.166 |
Random | +0.165 |
Sham | +0.165 |
nam | +0.162 |
ASA | +0.155 |
Neg logit contributions | |
orian | -0.215 |
kson | -0.204 |
orb | -0.204 |
rupal | -0.198 |
oulos | -0.198 |
Token | . |
Token ID | 13 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
dump | +1.310 |
Random | +1.302 |
Sham | +1.298 |
nam | +1.282 |
ASA | +1.223 |
Neg logit contributions | |
orian | -1.521 |
kson | -1.447 |
orb | -1.443 |
rupal | -1.407 |
oulos | -1.395 |
Token | Exactly |
Token ID | 36819 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
Sham | +0.300 |
Random | +0.296 |
dump | +0.294 |
nam | +0.290 |
ASA | +0.279 |
Neg logit contributions | |
orian | -0.396 |
orb | -0.377 |
kson | -0.374 |
rupal | -0.368 |
oulos | -0.365 |
Token | 50 |
Token ID | 2026 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
orian | +0.642 |
orb | +0.612 |
kson | +0.611 |
rupal | +0.594 |
oulos | +0.591 |
Neg logit contributions | |
dump | -0.496 |
Random | -0.494 |
Sham | -0.490 |
nam | -0.485 |
ASA | -0.462 |
Token | years |
Token ID | 812 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
dump | +0.370 |
Random | +0.369 |
Sham | +0.365 |
nam | +0.361 |
ASA | +0.344 |
Neg logit contributions | |
orian | -0.495 |
orb | -0.472 |
kson | -0.471 |
rupal | -0.457 |
oulos | -0.455 |
Token | later |
Token ID | 1568 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
dump | +0.534 |
Sham | +0.530 |
Random | +0.530 |
nam | +0.521 |
ASA | +0.495 |
Neg logit contributions | |
orian | -0.779 |
kson | -0.746 |
orb | -0.745 |
rupal | -0.727 |
oulos | -0.724 |
Token | — |
Token ID | 960 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
dump | +0.188 |
Random | +0.188 |
Sham | +0.186 |
nam | +0.184 |
ASA | +0.176 |
Neg logit contributions | |
orian | -0.229 |
orb | -0.218 |
kson | -0.218 |
rupal | -0.211 |
oulos | -0.210 |
Token | December |
Token ID | 20588 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
orian | +0.825 |
orb | +0.783 |
kson | +0.780 |
rupal | +0.753 |
oulos | +0.751 |
Neg logit contributions | |
dump | -0.764 |
Random | -0.762 |
Sham | -0.756 |
nam | -0.747 |
ASA | -0.717 |
Token | 17 |
Token ID | 1596 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Sham | +0.342 |
Random | +0.340 |
dump | +0.340 |
nam | +0.335 |
ASA | +0.322 |
Neg logit contributions | |
orian | -0.371 |
orb | -0.352 |
kson | -0.351 |
rupal | -0.344 |
oulos | -0.342 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
dump | +1.273 |
Random | +1.271 |
Sham | +1.261 |
nam | +1.253 |
ASA | +1.187 |
Neg logit contributions | |
orian | -1.722 |
kson | -1.637 |
orb | -1.635 |
rupal | -1.596 |
oulos | -1.583 |
Token | 1995 |
Token ID | 8735 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
orian | +0.629 |
orb | +0.592 |
kson | +0.590 |
rupal | +0.569 |
oulos | +0.564 |
Neg logit contributions | |
dump | -0.792 |
Random | -0.790 |
Sham | -0.785 |
nam | -0.778 |
ASA | -0.750 |
Token | — |
Token ID | 960 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
orian | +0.243 |
orb | +0.231 |
kson | +0.231 |
rupal | +0.223 |
oulos | +0.222 |
Neg logit contributions | |
dump | -0.206 |
Random | -0.205 |
Sham | -0.204 |
nam | -0.201 |
ASA | -0.193 |
Token | dist |
Token ID | 1233 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
dump | +0.496 |
Random | +0.494 |
Sham | +0.489 |
nam | +0.482 |
ASA | +0.457 |
Neg logit contributions | |
orian | -0.823 |
orb | -0.788 |
kson | -0.786 |
rupal | -0.766 |
oulos | -0.763 |
Token | ros |
Token ID | 4951 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
orian | +3.276 |
orb | +3.134 |
kson | +3.055 |
rupal | +3.019 |
arious | +3.005 |
Neg logit contributions | |
dump | -3.080 |
Sham | -3.067 |
Random | -3.058 |
nam | -3.009 |
ASA | -2.932 |
Token | . |
Token ID | 13 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
orian | +1.441 |
orb | +1.362 |
kson | +1.361 |
rupal | +1.314 |
arious | +1.300 |
Neg logit contributions | |
dump | -1.431 |
Random | -1.430 |
Sham | -1.412 |
nam | -1.400 |
ASA | -1.350 |
Token |
|
Token ID | 198 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
orian | +0.443 |
orb | +0.420 |
kson | +0.419 |
rupal | +0.406 |
oulos | +0.405 |
Neg logit contributions | |
dump | -0.412 |
Random | -0.411 |
Sham | -0.408 |
nam | -0.403 |
ASA | -0.387 |
Token |
|
Token ID | 198 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
orian | +0.603 |
orb | +0.571 |
kson | +0.570 |
oulos | +0.551 |
rupal | +0.551 |
Neg logit contributions | |
dump | -0.570 |
Random | -0.569 |
Sham | -0.565 |
nam | -0.560 |
ASA | -0.534 |
Token | In |
Token ID | 818 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
orian | +0.470 |
orb | +0.450 |
kson | +0.447 |
rupal | +0.435 |
oulos | +0.432 |
Neg logit contributions | |
dump | -0.325 |
Sham | -0.323 |
Random | -0.323 |
nam | -0.317 |
ASA | -0.304 |
Token | some |
Token ID | 617 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
orian | +1.548 |
orb | +1.474 |
kson | +1.468 |
rupal | +1.428 |
arious | +1.416 |
Neg logit contributions | |
dump | -1.237 |
Random | -1.233 |
Sham | -1.219 |
nam | -1.198 |
ASA | -1.150 |
Token | ways |
Token ID | 2842 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
Random | +0.868 |
dump | +0.866 |
Sham | +0.859 |
nam | +0.850 |
ASA | +0.814 |
Neg logit contributions | |
orian | -1.003 |
orb | -0.956 |
kson | -0.953 |
rupal | -0.923 |
oulos | -0.923 |
Token | , |
Token ID | 11 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Sham | +2.801 |
dump | +2.800 |
Random | +2.779 |
nam | +2.742 |
ASA | +2.613 |
Neg logit contributions | |
orian | -3.948 |
orb | -3.759 |
kson | -3.747 |
oulos | -3.680 |
natureconservancy | -3.665 |
Token | it |
Token ID | 340 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
orian | +1.028 |
orb | +0.976 |
kson | +0.976 |
rupal | +0.945 |
oulos | +0.939 |
Neg logit contributions | |
dump | -0.845 |
Random | -0.844 |
Sham | -0.832 |
nam | -0.825 |
ASA | -0.787 |
Token | 's |
Token ID | 338 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
orian | +0.891 |
kson | +0.848 |
orb | +0.844 |
rupal | +0.819 |
oulos | +0.812 |
Neg logit contributions | |
Random | -0.733 |
dump | -0.733 |
Sham | -0.721 |
nam | -0.713 |
ASA | -0.687 |
Token | to |
Token ID | 284 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
orian | +0.228 |
kson | +0.216 |
orb | +0.216 |
rupal | +0.209 |
oulos | +0.208 |
Neg logit contributions | |
dump | -0.217 |
Random | -0.216 |
Sham | -0.215 |
nam | -0.213 |
ASA | -0.204 |
Token | prevent |
Token ID | 2948 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
orian | +0.380 |
orb | +0.361 |
kson | +0.360 |
rupal | +0.349 |
oulos | +0.347 |
Neg logit contributions | |
dump | -0.338 |
Random | -0.338 |
Sham | -0.334 |
nam | -0.330 |
ASA | -0.316 |
Token | another |
Token ID | 1194 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
orian | +0.261 |
orb | +0.248 |
kson | +0.248 |
rupal | +0.241 |
oulos | +0.240 |
Neg logit contributions | |
dump | -0.196 |
Random | -0.195 |
Sham | -0.192 |
nam | -0.191 |
ASA | -0.182 |
Token | Portsmouth |
Token ID | 48823 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
dump | +0.191 |
Random | +0.191 |
Sham | +0.190 |
nam | +0.187 |
ASA | +0.179 |
Neg logit contributions | |
orian | -0.220 |
kson | -0.209 |
orb | -0.209 |
rupal | -0.202 |
oulos | -0.201 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
dump | +1.856 |
Sham | +1.851 |
Random | +1.848 |
nam | +1.797 |
ASA | +1.719 |
Neg logit contributions | |
orian | -2.362 |
kson | -2.281 |
orb | -2.248 |
rupal | -2.192 |
oulos | -2.166 |
Token | but |
Token ID | 475 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
Sham | +1.532 |
Random | +1.517 |
dump | +1.501 |
nam | +1.473 |
ASA | +1.415 |
Neg logit contributions | |
orian | -2.250 |
kson | -2.163 |
orb | -2.157 |
rupal | -2.103 |
arious | -2.077 |
Token | not |
Token ID | 407 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
orian | +0.636 |
orb | +0.605 |
kson | +0.604 |
rupal | +0.585 |
oulos | +0.585 |
Neg logit contributions | |
dump | -0.490 |
Random | -0.489 |
Sham | -0.482 |
nam | -0.478 |
ASA | -0.456 |
Token | another |
Token ID | 1194 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
orian | +1.274 |
orb | +1.213 |
kson | +1.208 |
oulos | +1.177 |
rupal | +1.173 |
Neg logit contributions | |
dump | -0.863 |
Random | -0.855 |
nam | -0.835 |
Sham | -0.835 |
ASA | -0.793 |
Token | Manchester |
Token ID | 9502 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
orian | +0.415 |
orb | +0.395 |
kson | +0.395 |
oulos | +0.383 |
rupal | +0.383 |
Neg logit contributions | |
dump | -0.293 |
Random | -0.291 |
nam | -0.285 |
Sham | -0.285 |
ASA | -0.270 |
Token | City |
Token ID | 2254 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
orian | +0.048 |
orb | +0.045 |
kson | +0.045 |
rupal | +0.044 |
oulos | +0.044 |
Neg logit contributions | |
dump | -0.041 |
Random | -0.041 |
Sham | -0.040 |
nam | -0.040 |
ASA | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
dump | +0.589 |
Random | +0.588 |
Sham | +0.584 |
nam | +0.575 |
ASA | +0.550 |
Neg logit contributions | |
orian | -0.683 |
kson | -0.650 |
orb | -0.650 |
rupal | -0.628 |
oulos | -0.624 |
Token | Abstract |
Token ID | 23839 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
orian | +3.280 |
orb | +3.164 |
kson | +3.077 |
tale | +3.024 |
rupal | +3.018 |
Neg logit contributions | |
Sham | -2.147 |
dump | -2.098 |
nam | -2.048 |
Random | -2.035 |
ASA | -2.034 |
Token |
|
Token ID | 198 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
Sham | +1.394 |
Random | +1.394 |
dump | +1.386 |
nam | +1.355 |
ASA | +1.316 |
Neg logit contributions | |
orian | -1.607 |
orb | -1.526 |
kson | -1.520 |
rupal | -1.476 |
oulos | -1.476 |
Token |
|
Token ID | 198 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Random | +1.985 |
Sham | +1.953 |
nam | +1.942 |
dump | +1.937 |
ASA | +1.798 |
Neg logit contributions | |
orian | -2.590 |
helicop | -2.589 |
kson | -2.453 |
agascar | -2.447 |
orb | -2.447 |
Token | Background |
Token ID | 21756 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Random | +1.615 |
dump | +1.586 |
Sham | +1.555 |
nam | +1.543 |
ASA | +1.448 |
Neg logit contributions | |
orian | -2.582 |
kson | -2.470 |
orb | -2.453 |
oulos | -2.414 |
rupal | -2.404 |
Token | Depression |
Token ID | 22483 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
orian | +0.133 |
orb | +0.127 |
kson | +0.127 |
rupal | +0.123 |
oulos | +0.123 |
Neg logit contributions | |
dump | -0.103 |
Random | -0.103 |
Sham | -0.102 |
nam | -0.101 |
ASA | -0.096 |
Token | presents |
Token ID | 10969 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
dump | +0.020 |
Random | +0.020 |
Sham | +0.019 |
nam | +0.019 |
ASA | +0.018 |
Neg logit contributions | |
orian | -0.023 |
orb | -0.022 |
kson | -0.022 |
rupal | -0.021 |
oulos | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
orian | +1.792 |
orb | +1.707 |
kson | +1.696 |
rupal | +1.646 |
oulos | +1.635 |
Neg logit contributions | |
dump | -1.585 |
Random | -1.564 |
Sham | -1.544 |
nam | -1.524 |
ASA | -1.457 |
Token | significant |
Token ID | 2383 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
orian | +1.491 |
orb | +1.422 |
kson | +1.416 |
rupal | +1.374 |
oulos | +1.367 |
Neg logit contributions | |
dump | -1.174 |
Random | -1.164 |
Sham | -1.149 |
nam | -1.136 |
ASA | -1.082 |
Token | burden |
Token ID | 10538 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
dump | +0.339 |
Random | +0.338 |
Sham | +0.336 |
nam | +0.332 |
ASA | +0.319 |
Neg logit contributions | |
orian | -0.372 |
orb | -0.352 |
kson | -0.352 |
rupal | -0.340 |
oulos | -0.339 |
Token | to |
Token ID | 284 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
orian | +1.948 |
orb | +1.826 |
kson | +1.808 |
rupal | +1.747 |
tale | +1.729 |
Neg logit contributions | |
dump | -2.476 |
Random | -2.453 |
Sham | -2.432 |
nam | -2.399 |
ASA | -2.319 |
Token | both |
Token ID | 1111 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
orian | +2.147 |
kson | +2.049 |
orb | +2.033 |
rupal | +1.976 |
oulos | +1.970 |
Neg logit contributions | |
dump | -1.838 |
Random | -1.808 |
Sham | -1.783 |
nam | -1.764 |
ASA | -1.658 |
Token | : |
Token ID | 25 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
Random | +1.487 |
Sham | +1.484 |
dump | +1.474 |
nam | +1.473 |
ASA | +1.375 |
Neg logit contributions | |
orian | -1.739 |
helicop | -1.700 |
kson | -1.648 |
orb | -1.640 |
oulos | -1.620 |
Token | Carly |
Token ID | 35982 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
orian | +0.026 |
orb | +0.024 |
kson | +0.024 |
rupal | +0.023 |
helicop | +0.023 |
Neg logit contributions | |
Sham | -0.038 |
Random | -0.037 |
dump | -0.037 |
nam | -0.037 |
ASA | -0.036 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
Sham | +1.905 |
dump | +1.886 |
Random | +1.875 |
nam | +1.867 |
ASA | +1.804 |
Neg logit contributions | |
orian | -0.920 |
orb | -0.881 |
helicop | -0.863 |
kson | -0.854 |
rupal | -0.840 |
Token | 's |
Token ID | 338 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Sham | +1.666 |
nam | +1.655 |
dump | +1.624 |
Random | +1.613 |
ASA | +1.504 |
Neg logit contributions | |
orian | -3.106 |
helicop | -3.004 |
orb | -2.995 |
kson | -2.931 |
rupal | -2.922 |
Token | political |
Token ID | 1964 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
orian | +0.203 |
orb | +0.194 |
kson | +0.194 |
rupal | +0.189 |
oulos | +0.187 |
Neg logit contributions | |
Random | -0.138 |
dump | -0.138 |
Sham | -0.137 |
nam | -0.135 |
ASA | -0.128 |
Token | career |
Token ID | 3451 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
orian | +0.809 |
orb | +0.770 |
kson | +0.768 |
rupal | +0.748 |
oulos | +0.742 |
Neg logit contributions | |
dump | -0.588 |
Random | -0.586 |
Sham | -0.583 |
nam | -0.575 |
ASA | -0.548 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
orian | +0.162 |
kson | +0.147 |
orb | +0.146 |
rupal | +0.137 |
oulos | +0.137 |
Neg logit contributions | |
dump | -0.401 |
Random | -0.401 |
Sham | -0.397 |
nam | -0.395 |
ASA | -0.384 |
Token | concedes |
Token ID | 49867 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
Sham | +2.234 |
dump | +2.223 |
nam | +2.213 |
Random | +2.205 |
ASA | +2.115 |
Neg logit contributions | |
orian | -1.795 |
orb | -1.695 |
kson | -1.667 |
rupal | -1.636 |
arious | -1.619 |
Token | defeat |
Token ID | 7433 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
dump | +0.052 |
Random | +0.052 |
Sham | +0.051 |
nam | +0.051 |
ASA | +0.048 |
Neg logit contributions | |
orian | -0.076 |
orb | -0.072 |
kson | -0.072 |
rupal | -0.070 |
oulos | -0.070 |
Token | to |
Token ID | 284 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
dump | +0.546 |
Random | +0.544 |
Sham | +0.542 |
nam | +0.534 |
ASA | +0.510 |
Neg logit contributions | |
orian | -0.644 |
orb | -0.612 |
kson | -0.612 |
rupal | -0.592 |
oulos | -0.589 |
Token | her |
Token ID | 607 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
orian | +0.234 |
kson | +0.222 |
orb | +0.222 |
oulos | +0.214 |
rupal | +0.214 |
Neg logit contributions | |
dump | -0.200 |
Random | -0.200 |
Sham | -0.195 |
nam | -0.195 |
ASA | -0.185 |
Token | regulations |
Token ID | 6647 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
orian | +0.393 |
orb | +0.374 |
kson | +0.373 |
rupal | +0.361 |
oulos | +0.359 |
Neg logit contributions | |
dump | -0.347 |
Random | -0.346 |
Sham | -0.343 |
nam | -0.339 |
ASA | -0.325 |
Token | have |
Token ID | 423 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
orian | +0.416 |
orb | +0.396 |
kson | +0.394 |
rupal | +0.382 |
oulos | +0.381 |
Neg logit contributions | |
dump | -0.338 |
Random | -0.338 |
Sham | -0.334 |
nam | -0.330 |
ASA | -0.315 |
Token | been |
Token ID | 587 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
dump | +1.007 |
Random | +1.004 |
Sham | +1.002 |
nam | +0.990 |
ASA | +0.944 |
Neg logit contributions | |
orian | -1.256 |
orb | -1.194 |
kson | -1.190 |
rupal | -1.156 |
oulos | -1.151 |
Token | explored |
Token ID | 18782 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
Sham | +1.112 |
Random | +1.110 |
dump | +1.109 |
nam | +1.105 |
ASA | +1.057 |
Neg logit contributions | |
orian | -1.230 |
kson | -1.173 |
orb | -1.170 |
rupal | -1.130 |
oulos | -1.127 |
Token | at |
Token ID | 379 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
dump | +1.890 |
Sham | +1.876 |
Random | +1.871 |
nam | +1.866 |
unres | +1.758 |
Neg logit contributions | |
orian | -2.413 |
kson | -2.304 |
orb | -2.303 |
rupal | -2.227 |
arious | -2.224 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
dump | +0.645 |
Random | +0.643 |
Sham | +0.638 |
nam | +0.630 |
ASA | +0.602 |
Neg logit contributions | |
orian | -0.837 |
orb | -0.799 |
kson | -0.799 |
rupal | -0.774 |
oulos | -0.772 |
Token | national |
Token ID | 2260 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Random | +0.931 |
dump | +0.928 |
Sham | +0.923 |
nam | +0.915 |
ASA | +0.867 |
Neg logit contributions | |
orian | -1.389 |
kson | -1.339 |
orb | -1.338 |
oulos | -1.298 |
rupal | -1.297 |
Token | level |
Token ID | 1241 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
orian | +0.145 |
kson | +0.137 |
orb | +0.137 |
rupal | +0.133 |
oulos | +0.132 |
Neg logit contributions | |
dump | -0.132 |
Random | -0.132 |
Sham | -0.131 |
nam | -0.130 |
ASA | -0.124 |
Token | ( |
Token ID | 357 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
dump | +0.788 |
Random | +0.782 |
Sham | +0.781 |
nam | +0.772 |
ASA | +0.734 |
Neg logit contributions | |
orian | -0.989 |
orb | -0.942 |
kson | -0.941 |
rupal | -0.911 |
oulos | -0.908 |
Token | e |
Token ID | 68 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
orian | +0.977 |
orb | +0.926 |
kson | +0.920 |
rupal | +0.889 |
oulos | +0.884 |
Neg logit contributions | |
dump | -0.988 |
Random | -0.984 |
Sham | -0.981 |
nam | -0.968 |
ASA | -0.933 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Random | +0.281 |
dump | +0.278 |
Sham | +0.277 |
nam | +0.275 |
ASA | +0.259 |
Neg logit contributions | |
orian | -0.332 |
orb | -0.315 |
kson | -0.313 |
helicop | -0.310 |
oulos | -0.308 |
Token | for |
Token ID | 329 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Sham | +1.863 |
dump | +1.844 |
Random | +1.835 |
nam | +1.816 |
ASA | +1.711 |
Neg logit contributions | |
orian | -2.686 |
kson | -2.543 |
orb | -2.541 |
rupal | -2.484 |
oulos | -2.474 |
Token | Star |
Token ID | 2907 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
Random | +1.054 |
Sham | +1.054 |
dump | +1.052 |
nam | +1.035 |
ASA | +0.983 |
Neg logit contributions | |
orian | -1.401 |
orb | -1.336 |
kson | -1.334 |
rupal | -1.299 |
oulos | -1.291 |
Token | Wars |
Token ID | 6176 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
orian | +3.683 |
orb | +3.545 |
kson | +3.539 |
rupal | +3.449 |
oulos | +3.439 |
Neg logit contributions | |
dump | -1.471 |
Random | -1.464 |
Sham | -1.433 |
nam | -1.411 |
ASA | -1.319 |
Token | ? |
Token ID | 30 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
orian | +3.690 |
orb | +3.519 |
kson | +3.491 |
oulos | +3.397 |
tale | +3.396 |
Neg logit contributions | |
dump | -3.303 |
Random | -3.273 |
nam | -3.195 |
Sham | -3.167 |
ASA | -3.082 |
Token |
|
Token ID | 198 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
Sham | +1.187 |
Random | +1.176 |
dump | +1.164 |
nam | +1.150 |
ASA | +1.108 |
Neg logit contributions | |
orian | -1.425 |
orb | -1.353 |
kson | -1.341 |
rupal | -1.323 |
oulos | -1.313 |
Token |
|
Token ID | 198 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
Sham | +1.683 |
Random | +1.675 |
dump | +1.661 |
nam | +1.650 |
ASA | +1.524 |
Neg logit contributions | |
orian | -2.225 |
helicop | -2.214 |
agascar | -2.109 |
orb | -2.107 |
kson | -2.093 |
Token | No |
Token ID | 2949 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
Random | +1.268 |
dump | +1.248 |
Sham | +1.232 |
nam | +1.220 |
ASA | +1.137 |
Neg logit contributions | |
orian | -1.887 |
kson | -1.802 |
orb | -1.796 |
oulos | -1.762 |
rupal | -1.761 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
orian | +3.204 |
orb | +3.072 |
kson | +3.032 |
oulos | +2.906 |
rupal | +2.875 |
Neg logit contributions | |
dump | -3.430 |
Random | -3.410 |
nam | -3.304 |
Sham | -3.288 |
ASA | -3.184 |
Token | My |
Token ID | 2011 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
orian | +0.797 |
kson | +0.758 |
orb | +0.758 |
rupal | +0.733 |
oulos | +0.730 |
Neg logit contributions | |
dump | -0.635 |
Random | -0.632 |
Sham | -0.625 |
nam | -0.619 |
ASA | -0.591 |
Token | parents |
Token ID | 3397 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
dump | +0.381 |
Random | +0.380 |
Sham | +0.377 |
nam | +0.372 |
ASA | +0.355 |
Neg logit contributions | |
orian | -0.509 |
orb | -0.485 |
kson | -0.484 |
rupal | -0.470 |
oulos | -0.468 |
Token | are |
Token ID | 389 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
dump | +0.825 |
Sham | +0.821 |
Random | +0.819 |
nam | +0.811 |
ASA | +0.771 |
Neg logit contributions | |
orian | -0.994 |
orb | -0.943 |
kson | -0.942 |
rupal | -0.923 |
oulos | -0.917 |
Token |
|
Token ID | 198 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Random | +0.214 |
dump | +0.213 |
Sham | +0.212 |
nam | +0.209 |
ASA | +0.200 |
Neg logit contributions | |
orian | -0.259 |
orb | -0.246 |
kson | -0.245 |
rupal | -0.238 |
oulos | -0.238 |
Token |
|
Token ID | 198 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Random | +0.118 |
dump | +0.118 |
Sham | +0.117 |
nam | +0.116 |
ASA | +0.110 |
Neg logit contributions | |
orian | -0.133 |
orb | -0.126 |
kson | -0.126 |
helicop | -0.123 |
oulos | -0.122 |
Token | Over |
Token ID | 5886 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
dump | +0.258 |
Random | +0.256 |
Sham | +0.255 |
nam | +0.251 |
ASA | +0.239 |
Neg logit contributions | |
orian | -0.428 |
orb | -0.410 |
kson | -0.409 |
rupal | -0.398 |
oulos | -0.395 |
Token | drive |
Token ID | 19472 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
dump | +2.242 |
Random | +2.220 |
Sham | +2.213 |
nam | +2.170 |
ASA | +2.043 |
Neg logit contributions | |
orian | -2.955 |
kson | -2.838 |
orb | -2.800 |
rupal | -2.750 |
oulos | -2.717 |
Token | is |
Token ID | 318 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Sham | +1.542 |
Random | +1.541 |
dump | +1.536 |
nam | +1.497 |
ASA | +1.431 |
Neg logit contributions | |
orian | -1.861 |
orb | -1.756 |
kson | -1.755 |
rupal | -1.715 |
oulos | -1.700 |
Token | a |
Token ID | 257 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
dump | +0.638 |
Random | +0.637 |
Sham | +0.633 |
nam | +0.623 |
ASA | +0.592 |
Neg logit contributions | |
orian | -0.916 |
orb | -0.873 |
kson | -0.872 |
rupal | -0.848 |
oulos | -0.844 |
Token | piece |
Token ID | 3704 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
dump | +0.291 |
Random | +0.291 |
Sham | +0.289 |
nam | +0.284 |
ASA | +0.270 |
Neg logit contributions | |
orian | -0.404 |
orb | -0.385 |
kson | -0.385 |
rupal | -0.374 |
oulos | -0.374 |
Token | I |
Token ID | 314 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
dump | +0.330 |
Random | +0.329 |
Sham | +0.325 |
nam | +0.322 |
ASA | +0.309 |
Neg logit contributions | |
orian | -0.383 |
orb | -0.364 |
kson | -0.364 |
rupal | -0.352 |
oulos | -0.350 |
Token | � |
Token ID | 447 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
orian | +1.114 |
orb | +1.060 |
kson | +1.058 |
rupal | +1.024 |
oulos | +1.020 |
Neg logit contributions | |
dump | -0.897 |
Random | -0.895 |
Sham | -0.888 |
nam | -0.875 |
ASA | -0.840 |
Token | � |
Token ID | 247 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
orian | +0.610 |
kson | +0.574 |
orb | +0.573 |
rupal | +0.555 |
oulos | +0.552 |
Neg logit contributions | |
Random | -0.804 |
dump | -0.804 |
Sham | -0.796 |
nam | -0.794 |
ASA | -0.759 |
Token | ve |
Token ID | 303 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
orian | +0.033 |
kson | +0.031 |
orb | +0.031 |
rupal | +0.030 |
oulos | +0.030 |
Neg logit contributions | |
dump | -0.024 |
Random | -0.024 |
Sham | -0.023 |
nam | -0.023 |
ASA | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
dump | +0.763 |
Random | +0.762 |
Sham | +0.758 |
nam | +0.748 |
ASA | +0.716 |
Neg logit contributions | |
orian | -0.839 |
orb | -0.796 |
kson | -0.795 |
rupal | -0.770 |
oulos | -0.765 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Random | +0.814 |
Sham | +0.809 |
dump | +0.809 |
nam | +0.801 |
ASA | +0.754 |
Neg logit contributions | |
orian | -0.961 |
helicop | -0.917 |
orb | -0.911 |
kson | -0.910 |
oulos | -0.892 |
Token | The |
Token ID | 464 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Random | +0.716 |
dump | +0.715 |
Sham | +0.705 |
nam | +0.698 |
ASA | +0.661 |
Neg logit contributions | |
orian | -0.985 |
kson | -0.940 |
orb | -0.939 |
rupal | -0.913 |
oulos | -0.910 |
Token | young |
Token ID | 1862 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
dump | +0.084 |
Random | +0.083 |
Sham | +0.083 |
nam | +0.081 |
ASA | +0.077 |
Neg logit contributions | |
orian | -0.125 |
orb | -0.119 |
kson | -0.119 |
rupal | -0.116 |
oulos | -0.115 |
Token | man |
Token ID | 582 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Sham | +1.672 |
dump | +1.662 |
Random | +1.651 |
nam | +1.628 |
ASA | +1.524 |
Neg logit contributions | |
orian | -3.561 |
orb | -3.428 |
kson | -3.415 |
oulos | -3.357 |
rupal | -3.355 |
Token | was |
Token ID | 373 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
Sham | +1.126 |
dump | +1.125 |
Random | +1.114 |
nam | +1.108 |
ASA | +1.056 |
Neg logit contributions | |
orian | -1.209 |
orb | -1.148 |
kson | -1.139 |
rupal | -1.116 |
arious | -1.107 |
Token | a |
Token ID | 257 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
dump | +0.012 |
Random | +0.012 |
Sham | +0.012 |
nam | +0.012 |
ASA | +0.011 |
Neg logit contributions | |
orian | -0.018 |
orb | -0.017 |
kson | -0.017 |
rupal | -0.017 |
oulos | -0.017 |
Token | junior |
Token ID | 13430 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
orian | +0.297 |
orb | +0.282 |
kson | +0.282 |
rupal | +0.273 |
oulos | +0.272 |
Neg logit contributions | |
dump | -0.219 |
Random | -0.219 |
Sham | -0.215 |
nam | -0.213 |
ASA | -0.203 |
Token | clerk |
Token ID | 21120 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Sham | +1.082 |
Random | +1.079 |
dump | +1.077 |
nam | +1.059 |
ASA | +1.016 |
Neg logit contributions | |
orian | -1.393 |
kson | -1.331 |
orb | -1.327 |
rupal | -1.295 |
oulos | -1.289 |
Token | in |
Token ID | 287 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
orian | +0.734 |
orb | +0.695 |
kson | +0.694 |
rupal | +0.671 |
oulos | +0.668 |
Neg logit contributions | |
dump | -0.670 |
Random | -0.668 |
Sham | -0.660 |
nam | -0.654 |
ASA | -0.627 |
Token | the |
Token ID | 262 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
orian | +0.417 |
orb | +0.396 |
kson | +0.396 |
rupal | +0.383 |
oulos | +0.381 |
Neg logit contributions | |
dump | -0.325 |
Random | -0.323 |
nam | -0.316 |
Sham | -0.315 |
ASA | -0.300 |
Token | to |
Token ID | 284 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
orian | +0.817 |
orb | +0.772 |
kson | +0.771 |
rupal | +0.743 |
oulos | +0.739 |
Neg logit contributions | |
dump | -0.869 |
Random | -0.867 |
Sham | -0.859 |
nam | -0.851 |
ASA | -0.818 |
Token | voters |
Token ID | 4446 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
dump | +0.370 |
Random | +0.369 |
Sham | +0.366 |
nam | +0.361 |
ASA | +0.344 |
Neg logit contributions | |
orian | -0.484 |
orb | -0.461 |
kson | -0.460 |
rupal | -0.446 |
oulos | -0.445 |
Token | , |
Token ID | 11 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
dump | +0.130 |
Random | +0.130 |
Sham | +0.129 |
nam | +0.127 |
ASA | +0.122 |
Neg logit contributions | |
orian | -0.146 |
orb | -0.139 |
kson | -0.139 |
rupal | -0.134 |
oulos | -0.134 |
Token | than |
Token ID | 621 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
dump | +0.519 |
Random | +0.517 |
Sham | +0.517 |
nam | +0.507 |
ASA | +0.487 |
Neg logit contributions | |
orian | -0.633 |
orb | -0.604 |
kson | -0.603 |
rupal | -0.585 |
oulos | -0.581 |
Token | the |
Token ID | 262 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
dump | +0.704 |
Random | +0.701 |
Sham | +0.699 |
nam | +0.690 |
ASA | +0.664 |
Neg logit contributions | |
orian | -0.717 |
orb | -0.679 |
kson | -0.678 |
rupal | -0.655 |
oulos | -0.652 |
Token | bully |
Token ID | 27410 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
dump | +0.199 |
Random | +0.198 |
Sham | +0.195 |
nam | +0.194 |
ASA | +0.184 |
Neg logit contributions | |
orian | -0.248 |
kson | -0.236 |
orb | -0.235 |
rupal | -0.228 |
oulos | -0.228 |
Token | pul |
Token ID | 17472 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
dump | +0.296 |
Random | +0.295 |
Sham | +0.291 |
nam | +0.287 |
ASA | +0.272 |
Neg logit contributions | |
orian | -0.512 |
orb | -0.490 |
kson | -0.490 |
rupal | -0.477 |
oulos | -0.475 |
Token | pit |
Token ID | 15544 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
dump | +0.006 |
Random | +0.006 |
Sham | +0.006 |
nam | +0.006 |
ASA | +0.006 |
Neg logit contributions | |
orian | -0.006 |
orb | -0.006 |
kson | -0.006 |
rupal | -0.006 |
oulos | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
dump | +0.785 |
Random | +0.782 |
Sham | +0.779 |
nam | +0.769 |
ASA | +0.736 |
Neg logit contributions | |
orian | -0.879 |
orb | -0.836 |
kson | -0.833 |
rupal | -0.807 |
oulos | -0.803 |
Token | PK |
Token ID | 29673 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
Random | +0.351 |
dump | +0.350 |
Sham | +0.349 |
nam | +0.342 |
ASA | +0.328 |
Neg logit contributions | |
orian | -0.451 |
orb | -0.430 |
kson | -0.427 |
rupal | -0.416 |
oulos | -0.414 |
Token | claims |
Token ID | 3667 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Sham | +1.866 |
dump | +1.864 |
Random | +1.860 |
nam | +1.828 |
ASA | +1.752 |
Neg logit contributions | |
orian | -1.879 |
orb | -1.790 |
kson | -1.774 |
rupal | -1.714 |
oulos | -1.711 |
Token | was |
Token ID | 373 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
orian | +0.188 |
orb | +0.179 |
kson | +0.179 |
rupal | +0.173 |
oulos | +0.172 |
Neg logit contributions | |
dump | -0.149 |
Random | -0.148 |
Sham | -0.147 |
nam | -0.145 |
ASA | -0.139 |
Token | valued |
Token ID | 17560 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
orian | +0.331 |
orb | +0.316 |
kson | +0.315 |
rupal | +0.306 |
oulos | +0.304 |
Neg logit contributions | |
dump | -0.260 |
Random | -0.259 |
Sham | -0.257 |
nam | -0.254 |
ASA | -0.242 |
Token | as |
Token ID | 355 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
dump | +0.371 |
Random | +0.371 |
Sham | +0.369 |
nam | +0.366 |
ASA | +0.347 |
Neg logit contributions | |
orian | -0.446 |
orb | -0.424 |
kson | -0.424 |
rupal | -0.411 |
oulos | -0.409 |
Token | � |
Token ID | 564 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
orian | +0.055 |
orb | +0.052 |
kson | +0.052 |
rupal | +0.051 |
oulos | +0.051 |
Neg logit contributions | |
dump | -0.038 |
Random | -0.038 |
Sham | -0.037 |
nam | -0.037 |
ASA | -0.035 |
Token | � |
Token ID | 246 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
dump | +0.167 |
Random | +0.167 |
Sham | +0.165 |
nam | +0.163 |
ASA | +0.156 |
Neg logit contributions | |
orian | -0.189 |
orb | -0.180 |
kson | -0.179 |
rupal | -0.174 |
oulos | -0.173 |
Token | good |
Token ID | 11274 |
Feature activation | -5.94e+00 |
Pos logit contributions | |
dump | +0.822 |
Random | +0.820 |
Sham | +0.809 |
nam | +0.808 |
ASA | +0.762 |
Neg logit contributions | |
orian | -0.935 |
kson | -0.890 |
orb | -0.884 |
rupal | -0.860 |
oulos | -0.856 |
Token | � |
Token ID | 447 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
nam | +4.147 |
dump | +4.124 |
Random | +4.111 |
Sham | +4.109 |
unres | +3.927 |
Neg logit contributions | |
orian | -3.945 |
kson | -3.748 |
orb | -3.719 |
rupal | -3.598 |
oulos | -3.567 |
Token | � |
Token ID | 247 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
dump | +1.073 |
Random | +1.072 |
Sham | +1.065 |
nam | +1.057 |
ASA | +1.011 |
Neg logit contributions | |
orian | -0.930 |
orb | -0.876 |
kson | -0.873 |
rupal | -0.847 |
oulos | -0.842 |
Token | became |
Token ID | 2627 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
dump | +0.208 |
Random | +0.207 |
Sham | +0.206 |
nam | +0.204 |
ASA | +0.194 |
Neg logit contributions | |
orian | -0.239 |
orb | -0.227 |
kson | -0.227 |
rupal | -0.220 |
oulos | -0.219 |
Token | � |
Token ID | 564 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
dump | +1.312 |
Random | +1.309 |
Sham | +1.307 |
nam | +1.298 |
ASA | +1.230 |
Neg logit contributions | |
orian | -1.504 |
orb | -1.431 |
kson | -1.428 |
rupal | -1.381 |
oulos | -1.377 |
Token | � |
Token ID | 246 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
dump | +0.148 |
Random | +0.147 |
Sham | +0.146 |
nam | +0.145 |
ASA | +0.138 |
Neg logit contributions | |
orian | -0.166 |
orb | -0.157 |
kson | -0.157 |
rupal | -0.152 |
oulos | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
orian | +0.443 |
orb | +0.422 |
kson | +0.421 |
rupal | +0.408 |
oulos | +0.406 |
Neg logit contributions | |
dump | -0.363 |
Random | -0.362 |
Sham | -0.358 |
nam | -0.354 |
ASA | -0.339 |
Token |
|
Token ID | 198 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Sham | +1.517 |
Random | +1.516 |
dump | +1.504 |
nam | +1.481 |
ASA | +1.422 |
Neg logit contributions | |
orian | -1.915 |
orb | -1.832 |
kson | -1.810 |
rupal | -1.771 |
oulos | -1.765 |
Token |
|
Token ID | 198 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
Random | +0.285 |
dump | +0.284 |
Sham | +0.282 |
nam | +0.279 |
ASA | +0.267 |
Neg logit contributions | |
orian | -0.298 |
orb | -0.283 |
kson | -0.282 |
rupal | -0.273 |
oulos | -0.272 |
Token | H |
Token ID | 39 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
dump | +0.330 |
Random | +0.327 |
Sham | +0.326 |
nam | +0.321 |
ASA | +0.306 |
Neg logit contributions | |
orian | -0.510 |
orb | -0.488 |
kson | -0.486 |
rupal | -0.473 |
oulos | -0.470 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
dump | +0.218 |
Random | +0.218 |
Sham | +0.216 |
nam | +0.214 |
ASA | +0.204 |
Neg logit contributions | |
orian | -0.236 |
kson | -0.224 |
orb | -0.223 |
rupal | -0.216 |
oulos | -0.215 |
Token | ime |
Token ID | 524 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
dump | +1.299 |
Random | +1.291 |
Sham | +1.284 |
nam | +1.272 |
ASA | +1.203 |
Neg logit contributions | |
orian | -1.643 |
kson | -1.566 |
orb | -1.564 |
rupal | -1.517 |
oulos | -1.516 |
Token | Tab |
Token ID | 16904 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
Sham | +3.498 |
dump | +3.432 |
nam | +3.395 |
Random | +3.383 |
ASA | +3.269 |
Neg logit contributions | |
orian | -4.242 |
orb | -4.037 |
kson | -3.939 |
rupal | -3.900 |
arious | -3.880 |
Token | ata |
Token ID | 1045 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
dump | +3.398 |
nam | +3.376 |
Sham | +3.296 |
Random | +3.268 |
ASA | +2.991 |
Neg logit contributions | |
orian | -5.045 |
kson | -4.878 |
orb | -4.847 |
natureconservancy | -4.793 |
agascar | -4.745 |
Token | : |
Token ID | 25 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Sham | +3.212 |
Random | +3.178 |
dump | +3.161 |
nam | +3.158 |
ASA | +2.993 |
Neg logit contributions | |
orian | -3.834 |
orb | -3.634 |
kson | -3.617 |
agascar | -3.535 |
rupal | -3.534 |
Token | There |
Token ID | 1318 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
dump | +0.731 |
Random | +0.731 |
Sham | +0.727 |
nam | +0.716 |
ASA | +0.684 |
Neg logit contributions | |
orian | -0.952 |
orb | -0.909 |
kson | -0.905 |
rupal | -0.879 |
oulos | -0.875 |
Token | were |
Token ID | 547 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
dump | +0.195 |
Random | +0.194 |
Sham | +0.192 |
nam | +0.190 |
ASA | +0.182 |
Neg logit contributions | |
orian | -0.228 |
orb | -0.216 |
kson | -0.216 |
rupal | -0.209 |
oulos | -0.208 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Random | +1.057 |
dump | +1.057 |
Sham | +1.054 |
nam | +1.037 |
ASA | +0.995 |
Neg logit contributions | |
orian | -1.326 |
orb | -1.262 |
kson | -1.259 |
rupal | -1.223 |
oulos | -1.215 |
Token | University |
Token ID | 2059 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
dump | +0.081 |
Random | +0.080 |
Sham | +0.079 |
nam | +0.079 |
ASA | +0.075 |
Neg logit contributions | |
orian | -0.111 |
orb | -0.106 |
kson | -0.106 |
rupal | -0.103 |
oulos | -0.102 |
Token | of |
Token ID | 286 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
Sham | +0.997 |
Random | +0.977 |
nam | +0.975 |
dump | +0.974 |
ASA | +0.921 |
Neg logit contributions | |
orian | -1.278 |
orb | -1.231 |
kson | -1.221 |
helicop | -1.197 |
arious | -1.193 |
Token | California |
Token ID | 3442 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
Sham | +2.203 |
Random | +2.154 |
dump | +2.141 |
nam | +2.110 |
ASA | +2.058 |
Neg logit contributions | |
orian | -2.903 |
orb | -2.746 |
kson | -2.740 |
rupal | -2.686 |
oulos | -2.669 |
Token | , |
Token ID | 11 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
Sham | +3.662 |
Random | +3.590 |
nam | +3.555 |
dump | +3.552 |
ASA | +3.381 |
Neg logit contributions | |
orian | -5.159 |
orb | -4.872 |
kson | -4.867 |
rupal | -4.785 |
natureconservancy | -4.779 |
Token | Santa |
Token ID | 8909 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
Sham | +3.027 |
Random | +3.002 |
dump | +2.973 |
nam | +2.935 |
ASA | +2.826 |
Neg logit contributions | |
orian | -3.603 |
orb | -3.433 |
kson | -3.405 |
rupal | -3.322 |
oulos | -3.318 |
Token | Barbara |
Token ID | 16685 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
Sham | +3.862 |
Random | +3.668 |
nam | +3.642 |
dump | +3.607 |
ASA | +3.583 |
Neg logit contributions | |
orian | -4.201 |
orb | -4.044 |
oulos | -3.958 |
rupal | -3.896 |
kson | -3.894 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Random | +2.469 |
Sham | +2.469 |
dump | +2.462 |
nam | +2.430 |
ASA | +2.325 |
Neg logit contributions | |
orian | -2.952 |
orb | -2.814 |
kson | -2.809 |
rupal | -2.735 |
arious | -2.709 |
Token | and |
Token ID | 290 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
dump | +0.706 |
Random | +0.705 |
Sham | +0.699 |
nam | +0.691 |
ASA | +0.662 |
Neg logit contributions | |
orian | -0.794 |
orb | -0.754 |
kson | -0.753 |
rupal | -0.729 |
oulos | -0.725 |
Token | an |
Token ID | 281 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
orian | +0.286 |
orb | +0.272 |
kson | +0.272 |
rupal | +0.264 |
oulos | +0.263 |
Neg logit contributions | |
dump | -0.191 |
Random | -0.190 |
Sham | -0.186 |
nam | -0.184 |
ASA | -0.174 |
Token | organizer |
Token ID | 26311 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
Random | +0.665 |
Sham | +0.663 |
dump | +0.662 |
nam | +0.655 |
ASA | +0.630 |
Neg logit contributions | |
orian | -0.877 |
kson | -0.838 |
orb | -0.836 |
rupal | -0.815 |
oulos | -0.807 |
Token | the |
Token ID | 262 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
dump | +0.074 |
Random | +0.074 |
Sham | +0.074 |
nam | +0.073 |
ASA | +0.069 |
Neg logit contributions | |
orian | -0.098 |
orb | -0.094 |
kson | -0.094 |
rupal | -0.091 |
oulos | -0.091 |
Token | European |
Token ID | 3427 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
orian | +2.229 |
kson | +2.109 |
orb | +2.096 |
oulos | +2.017 |
rupal | +2.016 |
Neg logit contributions | |
dump | -1.894 |
Random | -1.893 |
Sham | -1.854 |
nam | -1.846 |
ASA | -1.747 |
Token | rule |
Token ID | 3896 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
orian | +0.999 |
orb | +0.952 |
kson | +0.947 |
rupal | +0.920 |
oulos | +0.917 |
Neg logit contributions | |
dump | -0.706 |
Random | -0.703 |
Sham | -0.694 |
nam | -0.687 |
ASA | -0.652 |
Token | book |
Token ID | 1492 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
dump | +0.508 |
Random | +0.504 |
Sham | +0.503 |
nam | +0.496 |
ASA | +0.474 |
Neg logit contributions | |
orian | -0.592 |
kson | -0.565 |
orb | -0.564 |
rupal | -0.547 |
oulos | -0.543 |
Token | in |
Token ID | 287 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
orian | +1.168 |
orb | +1.104 |
kson | +1.104 |
rupal | +1.065 |
oulos | +1.062 |
Neg logit contributions | |
dump | -1.082 |
Random | -1.082 |
Sham | -1.072 |
nam | -1.060 |
ASA | -1.018 |
Token | terms |
Token ID | 2846 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
dump | +0.142 |
Random | +0.142 |
Sham | +0.141 |
nam | +0.139 |
ASA | +0.133 |
Neg logit contributions | |
orian | -0.179 |
orb | -0.171 |
kson | -0.170 |
rupal | -0.165 |
oulos | -0.164 |
Token | of |
Token ID | 286 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Sham | +3.500 |
dump | +3.497 |
Random | +3.485 |
nam | +3.457 |
ASA | +3.282 |
Neg logit contributions | |
orian | -4.376 |
orb | -4.218 |
kson | -4.192 |
oulos | -4.060 |
arious | -4.058 |
Token | its |
Token ID | 663 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
dump | +1.031 |
Random | +1.027 |
Sham | +1.027 |
nam | +1.012 |
ASA | +0.966 |
Neg logit contributions | |
orian | -1.406 |
orb | -1.350 |
kson | -1.346 |
rupal | -1.309 |
oulos | -1.299 |
Token | sensible |
Token ID | 20586 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
dump | +1.279 |
Random | +1.276 |
Sham | +1.274 |
nam | +1.255 |
ASA | +1.201 |
Neg logit contributions | |
orian | -1.597 |
orb | -1.534 |
kson | -1.527 |
rupal | -1.486 |
oulos | -1.478 |
Token | application |
Token ID | 3586 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
dump | +0.473 |
Random | +0.471 |
Sham | +0.467 |
nam | +0.462 |
ASA | +0.442 |
Neg logit contributions | |
orian | -0.542 |
orb | -0.515 |
kson | -0.514 |
rupal | -0.498 |
oulos | -0.496 |
Token | to |
Token ID | 284 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
orian | +0.991 |
orb | +0.937 |
kson | +0.933 |
rupal | +0.904 |
oulos | +0.900 |
Neg logit contributions | |
dump | -0.913 |
Random | -0.909 |
Sham | -0.900 |
nam | -0.890 |
ASA | -0.855 |
Token | first |
Token ID | 717 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
orian | +1.254 |
orb | +1.197 |
kson | +1.195 |
rupal | +1.161 |
oulos | +1.156 |
Neg logit contributions | |
dump | -0.881 |
Random | -0.879 |
Sham | -0.870 |
nam | -0.859 |
ASA | -0.818 |
Token | Ghostbusters |
Token ID | 50037 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
orian | +2.225 |
orb | +2.154 |
kson | +2.067 |
tale | +2.027 |
arious | +2.019 |
Neg logit contributions | |
dump | -2.430 |
Random | -2.415 |
Sham | -2.410 |
nam | -2.379 |
ASA | -2.328 |
Token | , |
Token ID | 11 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
orian | +4.260 |
orb | +4.108 |
kson | +4.034 |
tale | +3.909 |
rupal | +3.882 |
Neg logit contributions | |
dump | -4.117 |
Random | -4.065 |
Sham | -4.018 |
nam | -3.984 |
ASA | -3.876 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
orian | +0.791 |
kson | +0.753 |
orb | +0.753 |
rupal | +0.730 |
oulos | +0.729 |
Neg logit contributions | |
dump | -0.571 |
Random | -0.571 |
Sham | -0.568 |
nam | -0.560 |
ASA | -0.530 |
Token | ne |
Token ID | 710 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
orian | +0.818 |
orb | +0.783 |
kson | +0.773 |
oulos | +0.752 |
arious | +0.750 |
Neg logit contributions | |
dump | -0.646 |
Random | -0.646 |
Sham | -0.636 |
nam | -0.631 |
ASA | -0.608 |
Token | igh |
Token ID | 394 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
orian | +0.936 |
orb | +0.880 |
kson | +0.878 |
rupal | +0.841 |
oulos | +0.838 |
Neg logit contributions | |
Random | -1.156 |
dump | -1.155 |
Sham | -1.145 |
nam | -1.135 |
ASA | -1.094 |
Token | bor |
Token ID | 2865 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
Sham | +3.232 |
dump | +3.229 |
nam | +3.223 |
Random | +3.191 |
ASA | +2.892 |
Neg logit contributions | |
orian | -5.457 |
kson | -5.160 |
oulos | -5.135 |
rupal | -5.109 |
orb | -5.056 |
Token | hood |
Token ID | 2894 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
orian | +0.314 |
orb | +0.300 |
kson | +0.300 |
rupal | +0.291 |
oulos | +0.290 |
Neg logit contributions | |
dump | -0.215 |
Random | -0.215 |
Sham | -0.212 |
nam | -0.210 |
ASA | -0.200 |
Token | in |
Token ID | 287 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
orian | +1.198 |
orb | +1.158 |
kson | +1.121 |
tale | +1.100 |
arious | +1.093 |
Neg logit contributions | |
Random | -1.090 |
dump | -1.080 |
Sham | -1.055 |
nam | -1.045 |
unres | -1.023 |
Token | New |
Token ID | 968 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
orian | +1.060 |
orb | +1.020 |
kson | +1.005 |
oulos | +0.973 |
rupal | +0.973 |
Neg logit contributions | |
dump | -0.824 |
Random | -0.815 |
Sham | -0.806 |
nam | -0.794 |
ASA | -0.771 |
Token | York |
Token ID | 1971 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
Random | +0.151 |
Sham | +0.150 |
dump | +0.150 |
nam | +0.149 |
ASA | +0.138 |
Neg logit contributions | |
orian | -0.235 |
orb | -0.225 |
kson | -0.222 |
helicop | -0.220 |
rupal | -0.220 |