Token | - |
Token ID | 12 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
avage | +2.615 |
leck | +2.243 |
ghai | +2.159 |
Gat | +2.108 |
anski | +2.098 |
Neg logit contributions | |
Nept | -2.404 |
Reef | -2.264 |
oranges | -2.222 |
Ib | -2.185 |
Mercury | -2.139 |
Token | Ret |
Token ID | 9781 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Nept | +4.480 |
Reef | +4.318 |
Ib | +4.166 |
Mercury | +4.062 |
oranges | +4.019 |
Neg logit contributions | |
avage | -5.218 |
leck | -4.603 |
ghai | -4.528 |
anski | -4.297 |
Gat | -4.216 |
Token | arded |
Token ID | 10676 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
avage | +2.167 |
leck | +1.878 |
ghai | +1.811 |
anski | +1.763 |
Gat | +1.756 |
Neg logit contributions | |
Nept | -1.755 |
Reef | -1.657 |
oranges | -1.621 |
Ib | -1.599 |
Mercury | -1.554 |
Token | Cook |
Token ID | 8261 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
Nept | +0.788 |
Reef | +0.747 |
Ib | +0.720 |
oranges | +0.714 |
Mercury | +0.698 |
Neg logit contributions | |
avage | -0.978 |
leck | -0.855 |
ghai | -0.829 |
anski | -0.802 |
Gat | -0.791 |
Token | 200 |
Token ID | 939 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
avage | +1.337 |
leck | +1.167 |
ghai | +1.127 |
anski | +1.096 |
Gat | +1.092 |
Neg logit contributions | |
Nept | -1.042 |
Reef | -0.985 |
oranges | -0.954 |
Ib | -0.949 |
Mercury | -0.919 |
Token | 80 |
Token ID | 1795 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Nept | +4.262 |
Reef | +4.092 |
Ib | +3.932 |
Norn | +3.863 |
Mercury | +3.844 |
Neg logit contributions | |
avage | -4.254 |
leck | -3.794 |
ghai | -3.626 |
anski | -3.512 |
Gat | -3.400 |
Token | 202 |
Token ID | 19004 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
Nept | +12.732 |
Reef | +12.213 |
Ib | +11.645 |
201 | +11.490 |
2022 | +11.270 |
Neg logit contributions | |
avage | -22.394 |
ghai | -21.134 |
leck | -19.828 |
etheless | -19.234 |
anski | -19.101 |
Token | O |
Token ID | 440 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Nept | +3.366 |
Reef | +3.183 |
Ib | +3.109 |
Mercury | +2.734 |
Ox | +2.664 |
Neg logit contributions | |
avage | -12.707 |
leck | -11.789 |
ghai | -11.431 |
etheless | -11.414 |
anski | -11.112 |
Token | & |
Token ID | 5 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
Nept | +2.967 |
Reef | +2.872 |
Ib | +2.779 |
oranges | +2.718 |
Mercury | +2.705 |
Neg logit contributions | |
avage | -3.206 |
leck | -2.772 |
ghai | -2.676 |
anski | -2.602 |
Gat | -2.557 |
Token | A |
Token ID | 32 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
avage | +0.298 |
leck | +0.262 |
ghai | +0.254 |
Gat | +0.249 |
anski | +0.249 |
Neg logit contributions | |
Nept | -0.184 |
Reef | -0.172 |
oranges | -0.167 |
Ib | -0.164 |
Mercury | -0.159 |
Token | - |
Token ID | 12 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
avage | +2.010 |
leck | +1.709 |
ghai | +1.640 |
Gat | +1.632 |
anski | +1.596 |
Neg logit contributions | |
Nept | -1.922 |
oranges | -1.805 |
Reef | -1.804 |
Ib | -1.745 |
adul | -1.723 |
Token | , |
Token ID | 11 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Nept | +7.140 |
Reef | +6.654 |
Ib | +6.580 |
oranges | +6.444 |
adul | +6.310 |
Neg logit contributions | |
avage | -10.271 |
ghai | -8.967 |
leck | -8.833 |
GBT | -8.621 |
anski | -8.477 |
Token | but |
Token ID | 475 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
Nept | +5.690 |
Reef | +5.355 |
Ib | +5.317 |
adul | +5.167 |
oranges | +5.129 |
Neg logit contributions | |
avage | -8.907 |
leck | -7.712 |
ghai | -7.687 |
GBT | -7.305 |
anski | -7.292 |
Token | he |
Token ID | 339 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
Nept | +6.670 |
Ib | +6.320 |
Reef | +6.309 |
oranges | +6.111 |
adul | +5.929 |
Neg logit contributions | |
avage | -9.883 |
leck | -8.555 |
ghai | -8.469 |
GBT | -8.081 |
anski | -8.004 |
Token | p |
Token ID | 279 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
Nept | +7.221 |
Ib | +6.782 |
Reef | +6.684 |
oranges | +6.628 |
adul | +6.583 |
Neg logit contributions | |
avage | -11.752 |
leck | -10.323 |
ghai | -10.113 |
GBT | -9.936 |
anski | -9.730 |
Token | ales |
Token ID | 2040 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Nept | +8.398 |
Ib | +8.147 |
oranges | +7.924 |
Reef | +7.793 |
adul | +7.757 |
Neg logit contributions | |
avage | -9.431 |
leck | -8.597 |
ghai | -8.480 |
Gat | -7.916 |
GBT | -7.908 |
Token | in |
Token ID | 287 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Nept | +9.149 |
Ib | +8.804 |
oranges | +8.683 |
Reef | +8.539 |
Mercury | +8.160 |
Neg logit contributions | |
avage | -15.720 |
leck | -14.483 |
sth | -13.682 |
ghai | -13.663 |
anski | -13.519 |
Token | com |
Token ID | 401 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
Nept | +13.669 |
Ib | +13.338 |
Reef | +13.232 |
oranges | +13.061 |
adul | +13.043 |
Neg logit contributions | |
avage | -19.741 |
ghai | -18.084 |
leck | -17.199 |
anski | -16.740 |
GBT | -16.377 |
Token | |
Token ID | 3907 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Nept | +3.202 |
Reef | +2.637 |
Ib | +2.578 |
oranges | +2.347 |
adul | +2.305 |
Neg logit contributions | |
avage | -13.218 |
leck | -12.052 |
ghai | -11.968 |
GBT | -11.948 |
Discover | -11.457 |
Token | par |
Token ID | 1845 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Nept | +1.396 |
Reef | +1.317 |
oranges | +1.287 |
Ib | +1.283 |
Mercury | +1.250 |
Neg logit contributions | |
avage | -1.624 |
leck | -1.414 |
ghai | -1.369 |
Gat | -1.324 |
anski | -1.315 |
Token | |
Token ID | 3907 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
Nept | +2.278 |
Reef | +2.052 |
Ib | +1.975 |
oranges | +1.932 |
adul | +1.860 |
Neg logit contributions | |
avage | -7.409 |
leck | -6.751 |
ghai | -6.671 |
GBT | -6.528 |
anski | -6.509 |
Token | is |
Token ID | 271 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Nept | +0.948 |
Reef | +0.895 |
oranges | +0.873 |
Ib | +0.871 |
adul | +0.839 |
Neg logit contributions | |
avage | -1.287 |
leck | -1.132 |
ghai | -1.097 |
Gat | -1.065 |
anski | -1.062 |
Token | other |
Token ID | 584 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
Nept | +6.348 |
Reef | +6.093 |
oranges | +5.883 |
Ib | +5.881 |
Mercury | +5.880 |
Neg logit contributions | |
avage | -10.023 |
leck | -9.058 |
ghai | -8.821 |
anski | -8.579 |
Interstitial | -8.191 |
Token | C |
Token ID | 327 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
Nept | +4.455 |
Reef | +4.219 |
oranges | +4.074 |
Ib | +3.988 |
Mercury | +3.941 |
Neg logit contributions | |
avage | -6.799 |
leck | -6.062 |
ghai | -5.945 |
anski | -5.732 |
Gat | -5.529 |
Token | BA |
Token ID | 4339 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Reef | +6.494 |
Nept | +6.351 |
Ib | +6.306 |
oranges | +5.966 |
adul | +5.815 |
Neg logit contributions | |
avage | -13.180 |
leck | -11.568 |
ghai | -11.480 |
etheless | -11.469 |
anski | -11.290 |
Token | contexts |
Token ID | 26307 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Nept | +4.234 |
Reef | +4.014 |
oranges | +3.910 |
Ib | +3.856 |
Mercury | +3.762 |
Neg logit contributions | |
avage | -5.209 |
leck | -4.527 |
ghai | -4.430 |
anski | -4.265 |
Gat | -4.126 |
Token | . |
Token ID | 13 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
avage | +2.853 |
leck | +2.454 |
ghai | +2.364 |
anski | +2.295 |
Gat | +2.291 |
Neg logit contributions | |
Nept | -2.602 |
Reef | -2.472 |
oranges | -2.396 |
Ib | -2.382 |
Mercury | -2.314 |
Token | Industrial |
Token ID | 19034 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Nept | +3.655 |
Reef | +3.488 |
Ib | +3.376 |
Mercury | +3.306 |
oranges | +3.207 |
Neg logit contributions | |
avage | -5.020 |
leck | -4.511 |
ghai | -4.355 |
anski | -4.248 |
sth | -4.059 |
Token | due |
Token ID | 2233 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Nept | +10.852 |
Reef | +10.832 |
Ib | +10.735 |
Mercury | +10.282 |
oranges | +10.170 |
Neg logit contributions | |
avage | -21.305 |
leck | -19.808 |
ghai | -19.305 |
anski | -18.716 |
Interstitial | -18.380 |
Token | process |
Token ID | 1429 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
avage | +1.681 |
leck | +1.437 |
ghai | +1.373 |
Gat | +1.346 |
anski | +1.317 |
Neg logit contributions | |
Nept | -1.844 |
Reef | -1.751 |
oranges | -1.708 |
Ib | -1.692 |
Norn | -1.651 |
Token | is |
Token ID | 318 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Nept | +2.082 |
Reef | +1.988 |
oranges | +1.913 |
Ib | +1.902 |
Mercury | +1.859 |
Neg logit contributions | |
avage | -2.834 |
leck | -2.483 |
ghai | -2.410 |
anski | -2.344 |
Gat | -2.293 |
Token | that |
Token ID | 326 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Nept | +2.698 |
Reef | +2.569 |
oranges | +2.488 |
Ib | +2.470 |
Mercury | +2.421 |
Neg logit contributions | |
avage | -3.881 |
leck | -3.415 |
ghai | -3.332 |
anski | -3.241 |
Gat | -3.135 |
Token | bare |
Token ID | 6247 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Nept | +2.064 |
Reef | +1.966 |
oranges | +1.904 |
Ib | +1.902 |
Mercury | +1.861 |
Neg logit contributions | |
avage | -2.562 |
leck | -2.213 |
ghai | -2.169 |
anski | -2.102 |
Gat | -2.045 |
Token | 2001 |
Token ID | 5878 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Nept | +8.256 |
Reef | +7.816 |
Ib | +7.593 |
oranges | +7.539 |
Mercury | +7.441 |
Neg logit contributions | |
avage | -13.368 |
leck | -12.044 |
ghai | -11.824 |
anski | -11.249 |
GBT | -11.211 |
Token | Eric |
Token ID | 7651 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
avage | +2.410 |
leck | +2.128 |
ghai | +2.047 |
Gat | +2.013 |
anski | +2.002 |
Neg logit contributions | |
Nept | -1.647 |
Reef | -1.541 |
oranges | -1.507 |
Ib | -1.479 |
adul | -1.433 |
Token | McCorm |
Token ID | 42037 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
avage | +0.626 |
leck | +0.500 |
ghai | +0.470 |
Gat | +0.461 |
anski | +0.454 |
Neg logit contributions | |
Nept | -1.070 |
Reef | -1.030 |
oranges | -1.019 |
Ib | -1.003 |
adul | -0.986 |
Token | ack |
Token ID | 441 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
avage | +5.101 |
leck | +3.479 |
anski | +3.372 |
ghai | +2.793 |
sth | +2.665 |
Neg logit contributions | |
Nept | -14.557 |
Reef | -13.733 |
oranges | -13.580 |
Skydragon | -13.572 |
thous | -13.434 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
avage | +0.320 |
leck | +0.275 |
ghai | +0.265 |
Gat | +0.258 |
anski | +0.258 |
Neg logit contributions | |
Nept | -0.289 |
Reef | -0.273 |
oranges | -0.267 |
Ib | -0.264 |
Mercury | -0.256 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Nept | +0.202 |
Reef | +0.191 |
oranges | +0.186 |
Ib | +0.184 |
Mercury | +0.179 |
Neg logit contributions | |
avage | -0.225 |
leck | -0.194 |
ghai | -0.187 |
Gat | -0.181 |
anski | -0.181 |
Token | 2001 |
Token ID | 14585 |
Feature activation | +9.49e-03 |
Pos logit contributions | |
Nept | +8.200 |
Truth | +8.018 |
Reef | +7.496 |
Mercury | +7.147 |
oranges | +7.105 |
Neg logit contributions | |
avage | -24.572 |
etheless | -23.534 |
ghai | -22.917 |
leck | -22.379 |
Gat | -21.460 |
Token | Kel |
Token ID | 15150 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Nept | +0.094 |
Reef | +0.089 |
Ib | +0.085 |
oranges | +0.085 |
Mercury | +0.082 |
Neg logit contributions | |
avage | -0.136 |
leck | -0.119 |
ghai | -0.116 |
anski | -0.112 |
Gat | -0.111 |
Token | sey |
Token ID | 4397 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
avage | +3.005 |
leck | +2.634 |
ghai | +2.523 |
anski | +2.474 |
Gat | +2.426 |
Neg logit contributions | |
Nept | -2.724 |
Reef | -2.526 |
oranges | -2.512 |
Ib | -2.463 |
adul | -2.390 |
Token | Gram |
Token ID | 20159 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
avage | +1.031 |
leck | +0.894 |
ghai | +0.862 |
Gat | +0.844 |
anski | +0.838 |
Neg logit contributions | |
Nept | -0.932 |
Reef | -0.882 |
oranges | -0.871 |
Ib | -0.852 |
adul | -0.834 |
Token | mer |
Token ID | 647 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
avage | +3.685 |
leck | +3.079 |
ghai | +2.844 |
anski | +2.772 |
Gat | +2.741 |
Neg logit contributions | |
Nept | -5.695 |
Reef | -5.384 |
oranges | -5.337 |
Ib | -5.275 |
adul | -5.144 |
Token | 93 |
Token ID | 6052 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Nept | +6.898 |
Reef | +6.596 |
Ib | +6.480 |
oranges | +6.261 |
Mercury | +6.248 |
Neg logit contributions | |
avage | -8.220 |
leck | -7.318 |
ghai | -7.171 |
anski | -6.866 |
etheless | -6.661 |
Token | | |
Token ID | 930 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
Nept | +2.825 |
Reef | +2.653 |
Ib | +2.562 |
oranges | +2.462 |
Mercury | +2.434 |
Neg logit contributions | |
avage | -7.072 |
leck | -6.465 |
ghai | -6.278 |
anski | -6.208 |
etheless | -6.058 |
Token | | |
Token ID | 930 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Nept | +4.727 |
Reef | +4.388 |
oranges | +4.344 |
Ib | +4.327 |
Mercury | +4.084 |
Neg logit contributions | |
avage | -9.945 |
leck | -9.032 |
anski | -8.722 |
ghai | -8.646 |
Gat | -8.324 |
Token | org |
Token ID | 8745 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Nept | +2.964 |
oranges | +2.709 |
Reef | +2.677 |
Ib | +2.661 |
Mercury | +2.514 |
Neg logit contributions | |
avage | -6.894 |
leck | -6.184 |
ghai | -5.991 |
anski | -5.967 |
sth | -5.759 |
Token | . |
Token ID | 764 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Nept | +3.973 |
Reef | +3.782 |
Ib | +3.712 |
oranges | +3.657 |
Mercury | +3.643 |
Neg logit contributions | |
avage | -3.900 |
leck | -3.366 |
ghai | -3.228 |
anski | -3.119 |
Gat | -3.050 |
Token | cl |
Token ID | 537 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Nept | +4.459 |
oranges | +4.230 |
Ib | +4.165 |
Reef | +4.139 |
Mercury | +4.035 |
Neg logit contributions | |
avage | -6.180 |
leck | -5.303 |
anski | -5.140 |
ghai | -5.094 |
GBT | -4.935 |
Token | ojure |
Token ID | 32511 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
jah | +9.064 |
Nept | +9.000 |
Ib | +8.889 |
oranges | +8.681 |
ojure | +8.590 |
Neg logit contributions | |
avage | -21.680 |
etheless | -20.922 |
Interstitial | -20.795 |
GBT | -20.487 |
Gat | -20.373 |
Token | / |
Token ID | 1220 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
Nept | +1.400 |
Reef | +1.319 |
Ib | +1.274 |
oranges | +1.265 |
Mercury | +1.242 |
Neg logit contributions | |
avage | -1.966 |
leck | -1.736 |
ghai | -1.667 |
anski | -1.628 |
Gat | -1.600 |
Token | cl |
Token ID | 537 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Nept | +0.500 |
Reef | +0.473 |
oranges | +0.465 |
Ib | +0.462 |
Mercury | +0.448 |
Neg logit contributions | |
avage | -0.569 |
leck | -0.491 |
ghai | -0.469 |
anski | -0.464 |
Gat | -0.455 |
Token | ojure |
Token ID | 32511 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
Nept | +7.986 |
jah | +7.916 |
Ib | +7.875 |
oranges | +7.548 |
Mercury | +7.420 |
Neg logit contributions | |
avage | -21.061 |
Interstitial | -20.011 |
etheless | -19.977 |
GBT | -19.697 |
Gat | -19.583 |
Token | | |
Token ID | 930 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Nept | +3.210 |
Reef | +2.917 |
Ib | +2.884 |
oranges | +2.821 |
Mercury | +2.730 |
Neg logit contributions | |
avage | -8.747 |
leck | -7.966 |
ghai | -7.709 |
anski | -7.641 |
Gat | -7.446 |
Token | 251 |
Token ID | 28072 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Nept | +7.032 |
Reef | +6.702 |
Ib | +6.566 |
oranges | +6.506 |
Mercury | +6.366 |
Neg logit contributions | |
avage | -9.019 |
leck | -8.083 |
ghai | -7.888 |
anski | -7.537 |
Gat | -7.417 |
Token | | |
Token ID | 930 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
Nept | +2.929 |
Reef | +2.694 |
Ib | +2.644 |
oranges | +2.597 |
Mercury | +2.438 |
Neg logit contributions | |
avage | -8.137 |
leck | -7.430 |
ghai | -7.193 |
anski | -7.102 |
Gat | -6.951 |
Token | | |
Token ID | 930 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
Nept | +4.710 |
Reef | +4.317 |
Ib | +4.276 |
oranges | +4.225 |
Mercury | +3.992 |
Neg logit contributions | |
avage | -10.845 |
leck | -9.909 |
anski | -9.555 |
ghai | -9.505 |
Gat | -9.142 |
Token | org |
Token ID | 8745 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Nept | +3.685 |
oranges | +3.392 |
Ib | +3.323 |
Reef | +3.292 |
sax | +3.140 |
Neg logit contributions | |
avage | -8.588 |
leck | -7.689 |
ghai | -7.454 |
anski | -7.450 |
sth | -7.163 |
Token | . |
Token ID | 764 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Nept | +4.817 |
Reef | +4.569 |
Ib | +4.505 |
Mercury | +4.424 |
oranges | +4.416 |
Neg logit contributions | |
avage | -4.958 |
leck | -4.307 |
ghai | -4.120 |
anski | -3.988 |
etheless | -3.912 |
Token | cl |
Token ID | 537 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Nept | +4.149 |
oranges | +3.969 |
Ib | +3.867 |
Reef | +3.832 |
sax | +3.759 |
Neg logit contributions | |
avage | -5.680 |
leck | -4.871 |
anski | -4.742 |
ghai | -4.659 |
Gat | -4.546 |
Token | ojure |
Token ID | 32511 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
jah | +9.340 |
Nept | +9.248 |
Ib | +9.225 |
oranges | +9.052 |
ojure | +8.799 |
Neg logit contributions | |
avage | -21.283 |
Interstitial | -20.500 |
etheless | -20.442 |
GBT | -20.139 |
Gat | -19.990 |
Token | / |
Token ID | 1220 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Nept | +2.948 |
Reef | +2.746 |
Ib | +2.690 |
oranges | +2.681 |
Mercury | +2.607 |
Neg logit contributions | |
avage | -4.441 |
leck | -3.964 |
ghai | -3.782 |
anski | -3.725 |
Gat | -3.652 |
Token | cl |
Token ID | 537 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Nept | +2.096 |
Reef | +1.971 |
oranges | +1.961 |
Ib | +1.941 |
Mercury | +1.879 |
Neg logit contributions | |
avage | -2.517 |
leck | -2.183 |
anski | -2.079 |
ghai | -2.079 |
Gat | -2.021 |
Token | ojure |
Token ID | 32511 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Nept | +7.943 |
Ib | +7.883 |
jah | +7.861 |
oranges | +7.640 |
Mercury | +7.395 |
Neg logit contributions | |
avage | -20.800 |
Interstitial | -19.812 |
etheless | -19.618 |
GBT | -19.484 |
Gat | -19.352 |
Token | | |
Token ID | 930 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Nept | +3.854 |
Ib | +3.506 |
Reef | +3.495 |
oranges | +3.430 |
Mercury | +3.316 |
Neg logit contributions | |
avage | -9.991 |
leck | -9.096 |
ghai | -8.799 |
anski | -8.710 |
Gat | -8.503 |
Token | |
Token ID | 3907 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Nept | +3.202 |
Reef | +2.637 |
Ib | +2.578 |
oranges | +2.347 |
adul | +2.305 |
Neg logit contributions | |
avage | -13.218 |
leck | -12.052 |
ghai | -11.968 |
GBT | -11.948 |
Discover | -11.457 |
Token | par |
Token ID | 1845 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Nept | +1.396 |
Reef | +1.317 |
oranges | +1.287 |
Ib | +1.283 |
Mercury | +1.250 |
Neg logit contributions | |
avage | -1.624 |
leck | -1.414 |
ghai | -1.369 |
Gat | -1.324 |
anski | -1.315 |
Token | |
Token ID | 3907 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
Nept | +2.278 |
Reef | +2.052 |
Ib | +1.975 |
oranges | +1.932 |
adul | +1.860 |
Neg logit contributions | |
avage | -7.409 |
leck | -6.751 |
ghai | -6.671 |
GBT | -6.528 |
anski | -6.509 |
Token | is |
Token ID | 271 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Nept | +0.948 |
Reef | +0.895 |
oranges | +0.873 |
Ib | +0.871 |
adul | +0.839 |
Neg logit contributions | |
avage | -1.287 |
leck | -1.132 |
ghai | -1.097 |
Gat | -1.065 |
anski | -1.062 |
Token | |
Token ID | 3907 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Nept | +6.193 |
Reef | +5.596 |
oranges | +5.312 |
Ib | +5.229 |
adul | +4.803 |
Neg logit contributions | |
avage | -16.390 |
leck | -14.916 |
ghai | -14.715 |
GBT | -14.689 |
anski | -14.241 |
Token | on |
Token ID | 261 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
avage | +1.828 |
leck | +1.594 |
ghai | +1.539 |
anski | +1.500 |
Gat | +1.494 |
Neg logit contributions | |
Nept | -1.408 |
Reef | -1.330 |
oranges | -1.285 |
Ib | -1.278 |
Mercury | -1.238 |
Token | to |
Token ID | 284 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
Nept | +14.485 |
Ib | +13.654 |
Reef | +13.484 |
oranges | +13.274 |
adul | +13.019 |
Neg logit contributions | |
avage | -17.969 |
ghai | -15.540 |
GBT | -15.514 |
veyard | -15.077 |
anski | -14.929 |
Token | this |
Token ID | 428 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
Nept | +6.478 |
Reef | +6.236 |
Ib | +6.078 |
oranges | +5.958 |
adul | +5.840 |
Neg logit contributions | |
avage | -9.536 |
ghai | -8.317 |
leck | -8.244 |
anski | -7.774 |
sth | -7.666 |
Token | pres |
Token ID | 906 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
Nept | +5.256 |
Reef | +4.901 |
Ib | +4.831 |
adul | +4.738 |
oranges | +4.712 |
Neg logit contributions | |
avage | -7.400 |
leck | -6.478 |
ghai | -6.380 |
anski | -6.040 |
GBT | -5.948 |
Token | |
Token ID | 3907 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Nept | +2.968 |
Reef | +2.588 |
Ib | +2.550 |
oranges | +2.359 |
Mercury | +2.313 |
Neg logit contributions | |
avage | -9.279 |
ghai | -8.309 |
leck | -8.279 |
anski | -8.087 |
GBT | -8.046 |
Token | id |
Token ID | 312 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
avage | +2.317 |
leck | +2.000 |
ghai | +1.921 |
anski | +1.865 |
Gat | +1.858 |
Neg logit contributions | |
Nept | -2.073 |
Reef | -1.965 |
oranges | -1.900 |
Ib | -1.887 |
Mercury | -1.837 |
Token | Kel |
Token ID | 15150 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Nept | +0.094 |
Reef | +0.089 |
Ib | +0.085 |
oranges | +0.085 |
Mercury | +0.082 |
Neg logit contributions | |
avage | -0.136 |
leck | -0.119 |
ghai | -0.116 |
anski | -0.112 |
Gat | -0.111 |
Token | sey |
Token ID | 4397 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
avage | +3.005 |
leck | +2.634 |
ghai | +2.523 |
anski | +2.474 |
Gat | +2.426 |
Neg logit contributions | |
Nept | -2.724 |
Reef | -2.526 |
oranges | -2.512 |
Ib | -2.463 |
adul | -2.390 |
Token | Gram |
Token ID | 20159 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
avage | +1.031 |
leck | +0.894 |
ghai | +0.862 |
Gat | +0.844 |
anski | +0.838 |
Neg logit contributions | |
Nept | -0.932 |
Reef | -0.882 |
oranges | -0.871 |
Ib | -0.852 |
adul | -0.834 |
Token | mer |
Token ID | 647 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
avage | +3.685 |
leck | +3.079 |
ghai | +2.844 |
anski | +2.772 |
Gat | +2.741 |
Neg logit contributions | |
Nept | -5.695 |
Reef | -5.384 |
oranges | -5.337 |
Ib | -5.275 |
adul | -5.144 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Nept | +4.195 |
Reef | +4.083 |
Ib | +3.913 |
Mercury | +3.816 |
oranges | +3.777 |
Neg logit contributions | |
avage | -5.955 |
leck | -5.293 |
ghai | -5.142 |
anski | -4.971 |
etheless | -4.869 |
Token |
|
Token ID | 198 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Nept | +1.390 |
Reef | +1.325 |
Ib | +1.278 |
oranges | +1.272 |
Mercury | +1.242 |
Neg logit contributions | |
avage | -1.677 |
leck | -1.464 |
ghai | -1.409 |
anski | -1.371 |
Gat | -1.354 |
Token | 2001 |
Token ID | 14585 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Nept | +7.421 |
Truth | +7.237 |
Reef | +7.199 |
Ib | +6.863 |
Mercury | +6.704 |
Neg logit contributions | |
avage | -24.947 |
etheless | -24.119 |
ghai | -23.002 |
leck | -22.589 |
anski | -21.885 |
Token | John |
Token ID | 1757 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Nept | +1.459 |
Reef | +1.383 |
Ib | +1.322 |
oranges | +1.296 |
Mercury | +1.281 |
Neg logit contributions | |
avage | -2.365 |
leck | -2.077 |
ghai | -2.041 |
anski | -1.970 |
GBT | -1.942 |
Token | Lith |
Token ID | 19730 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
avage | +3.904 |
leck | +3.399 |
Gat | +3.237 |
ghai | +3.220 |
anski | +3.146 |
Neg logit contributions | |
Nept | -3.991 |
oranges | -3.855 |
Reef | -3.837 |
adul | -3.664 |
Ib | -3.661 |
Token | gow |
Token ID | 21175 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
avage | +2.842 |
leck | +2.166 |
ghai | +1.892 |
anski | +1.771 |
Gat | +1.697 |
Neg logit contributions | |
Nept | -8.393 |
Reef | -7.940 |
oranges | -7.876 |
Ib | -7.788 |
Norn | -7.729 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e-03 |
Pos logit contributions | |
Nept | +5.277 |
Reef | +5.144 |
Ib | +4.964 |
Mercury | +4.837 |
oranges | +4.725 |
Neg logit contributions | |
avage | -7.927 |
leck | -7.033 |
ghai | -6.915 |
anski | -6.644 |
etheless | -6.641 |
Token | than |
Token ID | 621 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
avage | +2.658 |
leck | +2.191 |
ghai | +2.133 |
anski | +2.042 |
Gat | +2.040 |
Neg logit contributions | |
Nept | -3.489 |
Reef | -3.325 |
oranges | -3.254 |
Ib | -3.208 |
adul | -3.142 |
Token | having |
Token ID | 1719 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
avage | +1.481 |
leck | +1.234 |
ghai | +1.178 |
Gat | +1.134 |
anski | +1.120 |
Neg logit contributions | |
Nept | -1.971 |
Reef | -1.876 |
oranges | -1.835 |
Ib | -1.817 |
Norn | -1.776 |
Token | the |
Token ID | 262 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Nept | +2.318 |
Reef | +2.214 |
Ib | +2.126 |
oranges | +2.073 |
Mercury | +2.065 |
Neg logit contributions | |
avage | -3.536 |
leck | -3.134 |
ghai | -3.029 |
anski | -2.950 |
Gat | -2.877 |
Token | sign |
Token ID | 1051 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Nept | +1.611 |
Reef | +1.536 |
oranges | +1.468 |
Ib | +1.458 |
Mercury | +1.420 |
Neg logit contributions | |
avage | -2.473 |
leck | -2.186 |
ghai | -2.112 |
anski | -2.061 |
Gat | -2.025 |
Token | of |
Token ID | 286 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
Nept | +4.800 |
Reef | +4.770 |
Ib | +4.515 |
Mercury | +4.391 |
adul | +4.188 |
Neg logit contributions | |
avage | -8.714 |
leck | -8.023 |
etheless | -7.711 |
anski | -7.506 |
ghai | -7.436 |
Token | a |
Token ID | 257 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Nept | +4.757 |
Reef | +4.555 |
Ib | +4.455 |
Mercury | +4.336 |
oranges | +4.244 |
Neg logit contributions | |
avage | -7.935 |
leck | -7.165 |
ghai | -6.849 |
etheless | -6.794 |
anski | -6.792 |
Token | good |
Token ID | 922 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
Mercury | +3.835 |
oranges | +3.676 |
adul | +3.634 |
Reef | +3.546 |
Nept | +3.543 |
Neg logit contributions | |
avage | -28.144 |
etheless | -28.110 |
anski | -26.936 |
Interstitial | -26.458 |
leck | -26.279 |
Token | aligned |
Token ID | 19874 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
Nept | +4.139 |
Ib | +3.817 |
Reef | +3.812 |
oranges | +3.778 |
Mercury | +3.647 |
Neg logit contributions | |
avage | -8.216 |
leck | -7.227 |
ghai | -7.107 |
anski | -7.000 |
sth | -6.934 |
Token | god |
Token ID | 5770 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Nept | +5.743 |
Reef | +5.081 |
Mercury | +5.069 |
Ib | +5.063 |
adul | +4.960 |
Neg logit contributions | |
avage | -10.198 |
leck | -9.393 |
etheless | -9.004 |
ghai | -8.864 |
Interstitial | -8.858 |
Token | , |
Token ID | 11 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
Nept | +1.183 |
Reef | +1.126 |
Ib | +1.086 |
oranges | +1.076 |
Mercury | +1.056 |
Neg logit contributions | |
avage | -1.487 |
leck | -1.303 |
ghai | -1.251 |
anski | -1.223 |
Gat | -1.201 |
Token | it |
Token ID | 340 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
avage | +0.682 |
leck | +0.595 |
ghai | +0.577 |
Gat | +0.564 |
anski | +0.561 |
Neg logit contributions | |
Nept | -0.503 |
Reef | -0.473 |
oranges | -0.459 |
Ib | -0.453 |
Mercury | -0.439 |
Token | | |
Token ID | 930 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
Nept | +5.024 |
Reef | +4.601 |
Ib | +4.481 |
oranges | +4.472 |
Mercury | +4.272 |
Neg logit contributions | |
avage | -10.174 |
leck | -9.044 |
anski | -8.839 |
ghai | -8.753 |
Gat | -8.372 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Nept | +5.695 |
oranges | +5.241 |
Ib | +5.240 |
Reef | +5.147 |
Mercury | +4.969 |
Neg logit contributions | |
avage | -10.237 |
leck | -9.069 |
ghai | -8.814 |
anski | -8.777 |
GBT | -8.348 |
Token | | |
Token ID | 930 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Nept | +6.727 |
oranges | +6.318 |
Ib | +6.196 |
Reef | +6.106 |
Mercury | +5.929 |
Neg logit contributions | |
avage | -15.563 |
leck | -14.276 |
ghai | -13.607 |
anski | -13.459 |
Gat | -13.318 |
Token | org |
Token ID | 8745 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
Nept | +2.854 |
oranges | +2.606 |
Ib | +2.581 |
Reef | +2.577 |
Mercury | +2.442 |
Neg logit contributions | |
avage | -6.243 |
leck | -5.552 |
ghai | -5.401 |
anski | -5.363 |
Gat | -5.182 |
Token | . |
Token ID | 764 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
Nept | +3.648 |
Reef | +3.474 |
Ib | +3.414 |
oranges | +3.366 |
Mercury | +3.336 |
Neg logit contributions | |
avage | -3.499 |
leck | -3.007 |
ghai | -2.880 |
anski | -2.790 |
Gat | -2.736 |
Token | cl |
Token ID | 537 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Nept | +4.460 |
oranges | +4.266 |
Ib | +4.188 |
Reef | +4.108 |
Mercury | +4.041 |
Neg logit contributions | |
avage | -6.368 |
leck | -5.450 |
anski | -5.311 |
ghai | -5.256 |
GBT | -5.111 |
Token | ojure |
Token ID | 32511 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
jah | +8.787 |
Nept | +8.647 |
Ib | +8.621 |
oranges | +8.292 |
ojure | +8.063 |
Neg logit contributions | |
avage | -21.467 |
etheless | -20.758 |
Interstitial | -20.609 |
GBT | -20.335 |
Gat | -20.208 |
Token | / |
Token ID | 1220 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
Nept | +1.646 |
Reef | +1.554 |
Ib | +1.499 |
oranges | +1.483 |
Mercury | +1.461 |
Neg logit contributions | |
avage | -2.331 |
leck | -2.060 |
ghai | -1.979 |
anski | -1.934 |
Gat | -1.902 |
Token | cl |
Token ID | 537 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Nept | +0.591 |
Reef | +0.560 |
oranges | +0.548 |
Ib | +0.545 |
Mercury | +0.529 |
Neg logit contributions | |
avage | -0.650 |
leck | -0.559 |
ghai | -0.537 |
anski | -0.526 |
Gat | -0.519 |
Token | oj |
Token ID | 13210 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
Nept | +7.696 |
jah | +7.690 |
Ib | +7.590 |
oranges | +7.229 |
Mercury | +7.019 |
Neg logit contributions | |
avage | -21.339 |
Interstitial | -20.402 |
etheless | -20.362 |
GBT | -20.117 |
Gat | -19.917 |
Token | ures |
Token ID | 942 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
avage | +0.925 |
leck | +0.798 |
ghai | +0.768 |
anski | +0.746 |
Gat | +0.743 |
Neg logit contributions | |
Nept | -0.841 |
Reef | -0.798 |
oranges | -0.776 |
Ib | -0.772 |
Mercury | -0.750 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Nept | +13.462 |
Ib | +13.218 |
adul | +12.884 |
sax | +12.816 |
Reef | +12.659 |
Neg logit contributions | |
avage | -16.425 |
ghai | -14.750 |
leck | -14.456 |
anski | -14.005 |
veyard | -13.864 |
Token | non |
Token ID | 1729 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
Nept | +11.178 |
Ib | +10.603 |
adul | +10.314 |
Reef | +10.135 |
sax | +9.988 |
Neg logit contributions | |
avage | -14.693 |
leck | -12.814 |
ghai | -12.660 |
anski | -12.092 |
GBT | -11.942 |
Token | - |
Token ID | 12 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
Nept | +6.929 |
Ib | +6.482 |
Reef | +6.404 |
sax | +6.335 |
adul | +6.334 |
Neg logit contributions | |
avage | -11.644 |
ghai | -10.406 |
leck | -10.142 |
anski | -9.920 |
GBT | -9.832 |
Token | prime |
Token ID | 35505 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
Nept | +9.446 |
Ib | +9.045 |
Reef | +8.889 |
adul | +8.679 |
sax | +8.593 |
Neg logit contributions | |
avage | -11.180 |
ghai | -9.980 |
leck | -9.685 |
Gat | -9.312 |
anski | -9.271 |
Token | - |
Token ID | 12 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
Nept | +8.344 |
Reef | +7.879 |
Ib | +7.805 |
sax | +7.550 |
adul | +7.444 |
Neg logit contributions | |
avage | -13.472 |
ghai | -11.898 |
leck | -11.700 |
anski | -11.336 |
veyard | -11.002 |
Token | time |
Token ID | 2435 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Nept | +6.593 |
Reef | +6.141 |
Ib | +5.989 |
adul | +5.848 |
oranges | +5.805 |
Neg logit contributions | |
avage | -11.063 |
ghai | -9.684 |
Gat | -9.624 |
leck | -9.622 |
anski | -9.373 |
Token | video |
Token ID | 2008 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Nept | +14.181 |
Ib | +13.693 |
sax | +13.575 |
Reef | +13.506 |
adul | +13.408 |
Neg logit contributions | |
avage | -18.342 |
ghai | -16.470 |
anski | -15.593 |
veyard | -15.552 |
leck | -15.532 |
Token | mes |
Token ID | 18842 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
Nept | +12.235 |
Ib | +11.624 |
Reef | +11.321 |
adul | +11.234 |
sax | +11.082 |
Neg logit contributions | |
avage | -17.197 |
ghai | -15.446 |
leck | -15.078 |
veyard | -14.899 |
anski | -14.809 |
Token | |
Token ID | 3907 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Nept | +2.697 |
Reef | +2.247 |
Ib | +2.221 |
oranges | +2.175 |
Mercury | +2.076 |
Neg logit contributions | |
avage | -10.036 |
leck | -9.309 |
ghai | -9.054 |
anski | -8.895 |
GBT | -8.814 |
Token | s |
Token ID | 82 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
avage | +3.806 |
leck | +3.327 |
ghai | +3.187 |
anski | +3.146 |
Gat | +3.123 |
Neg logit contributions | |
Nept | -2.794 |
Reef | -2.642 |
Ib | -2.530 |
oranges | -2.522 |
Mercury | -2.447 |
Token | age |
Token ID | 496 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
avage | +1.261 |
leck | +1.100 |
ghai | +1.062 |
anski | +1.033 |
Gat | +1.030 |
Neg logit contributions | |
Nept | -0.991 |
Reef | -0.936 |
oranges | -0.907 |
Ib | -0.902 |
Mercury | -0.874 |
Token |
|
Token ID | 198 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
avage | +2.480 |
leck | +2.067 |
ghai | +2.005 |
Gat | +2.003 |
sth | +1.938 |
Neg logit contributions | |
Nept | -2.630 |
oranges | -2.476 |
Reef | -2.458 |
Ib | -2.377 |
adul | -2.344 |
Token | 1998 |
Token ID | 21113 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Reef | +5.448 |
Nept | +5.295 |
Mercury | +4.752 |
Ib | +4.711 |
jah | +4.597 |
Neg logit contributions | |
avage | -14.725 |
leck | -13.256 |
ghai | -13.057 |
etheless | -12.903 |
anski | -12.773 |
Token | Garry |
Token ID | 45354 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
Nept | +3.440 |
Reef | +3.316 |
Ib | +3.227 |
Mercury | +3.185 |
oranges | +3.176 |
Neg logit contributions | |
avage | -2.203 |
leck | -1.768 |
ghai | -1.714 |
anski | -1.631 |
sth | -1.553 |
Token | Sh |
Token ID | 911 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
avage | +5.589 |
Gat | +4.716 |
Discover | +4.471 |
sth | +4.404 |
ghai | +4.364 |
Neg logit contributions | |
oranges | -10.361 |
Nept | -10.176 |
thous | -9.785 |
adul | -9.722 |
sax | -9.720 |
Token | and |
Token ID | 392 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
avage | +6.944 |
leck | +5.612 |
anski | +5.319 |
ghai | +5.292 |
sth | +5.166 |
Neg logit contributions | |
Nept | -11.278 |
oranges | -10.744 |
Reef | -10.564 |
thous | -10.548 |
Skydragon | -10.543 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
avage | +3.250 |
leck | +2.536 |
ghai | +2.234 |
anski | +2.070 |
sth | +1.912 |
Neg logit contributions | |
Nept | -9.561 |
oranges | -9.094 |
Reef | -9.059 |
Ib | -8.938 |
sax | -8.779 |
Token | 1999 |
Token ID | 7358 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Nept | +11.465 |
Reef | +11.285 |
Ib | +10.825 |
Mercury | +10.799 |
oranges | +10.658 |
Neg logit contributions | |
avage | -20.230 |
leck | -18.847 |
ghai | -18.101 |
anski | -17.562 |
GBT | -17.243 |
Token | John |
Token ID | 1757 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
avage | +2.321 |
leck | +2.034 |
ghai | +1.948 |
Gat | +1.918 |
anski | +1.900 |
Neg logit contributions | |
Nept | -1.844 |
Reef | -1.736 |
oranges | -1.702 |
Ib | -1.673 |
adul | -1.625 |
Token | Lith |
Token ID | 19730 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
avage | +1.529 |
leck | +1.318 |
ghai | +1.261 |
Gat | +1.240 |
anski | +1.226 |
Neg logit contributions | |
Nept | -1.490 |
Reef | -1.420 |
oranges | -1.402 |
Ib | -1.366 |
adul | -1.340 |
Token | gow |
Token ID | 21175 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
avage | +2.646 |
leck | +2.013 |
ghai | +1.737 |
anski | +1.640 |
Gat | +1.599 |
Neg logit contributions | |
Nept | -7.759 |
Reef | -7.349 |
oranges | -7.296 |
Ib | -7.200 |
Norn | -7.138 |
Token |
|
Token ID | 198 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
avage | +2.205 |
leck | +1.860 |
ghai | +1.784 |
Gat | +1.774 |
anski | +1.744 |
Neg logit contributions | |
Nept | -2.204 |
Reef | -2.066 |
oranges | -2.053 |
Ib | -1.999 |
adul | -1.960 |
Token | With |
Token ID | 2080 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
avage | +1.552 |
leck | +1.345 |
ghai | +1.298 |
anski | +1.262 |
Gat | +1.261 |
Neg logit contributions | |
Nept | -1.307 |
Reef | -1.235 |
oranges | -1.203 |
Ib | -1.192 |
Mercury | -1.158 |
Token | Dr |
Token ID | 1583 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Nept | +1.522 |
Reef | +1.443 |
Ib | +1.392 |
oranges | +1.371 |
Mercury | +1.344 |
Neg logit contributions | |
avage | -2.029 |
leck | -1.780 |
ghai | -1.736 |
anski | -1.672 |
Gat | -1.640 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Nept | +4.344 |
Reef | +4.170 |
Ib | +4.058 |
oranges | +3.942 |
Mercury | +3.905 |
Neg logit contributions | |
avage | -5.586 |
leck | -4.853 |
ghai | -4.720 |
anski | -4.500 |
GBT | -4.484 |
Token | Steve |
Token ID | 6542 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Nept | +2.481 |
Reef | +2.333 |
Ib | +2.245 |
oranges | +2.189 |
Mercury | +2.187 |
Neg logit contributions | |
avage | -3.679 |
leck | -3.245 |
ghai | -3.180 |
anski | -3.064 |
GBT | -3.015 |
Token | 200 |
Token ID | 939 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
avage | +4.156 |
leck | +3.627 |
Gat | +3.458 |
ghai | +3.455 |
anski | +3.401 |
Neg logit contributions | |
Nept | -3.173 |
Reef | -2.975 |
oranges | -2.963 |
Ib | -2.862 |
adul | -2.829 |
Token | 80 |
Token ID | 1795 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Nept | +2.499 |
Reef | +2.396 |
Ib | +2.327 |
oranges | +2.316 |
Mercury | +2.270 |
Neg logit contributions | |
avage | -2.246 |
leck | -1.964 |
ghai | -1.870 |
anski | -1.805 |
Gat | -1.766 |
Token | 204 |
Token ID | 18638 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
Reef | +7.687 |
Nept | +6.873 |
Mercury | +6.221 |
201 | +5.951 |
Ib | +5.867 |
Neg logit contributions | |
avage | -23.215 |
ghai | -22.014 |
leck | -21.805 |
anski | -20.843 |
ivas | -20.707 |
Token | O |
Token ID | 440 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Nept | +3.112 |
Reef | +2.913 |
Ib | +2.837 |
Mercury | +2.557 |
Ox | +2.414 |
Neg logit contributions | |
avage | -10.772 |
leck | -9.930 |
ghai | -9.668 |
etheless | -9.538 |
anski | -9.404 |
Token | & |
Token ID | 5 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
Nept | +2.379 |
Reef | +2.294 |
Ib | +2.221 |
oranges | +2.186 |
Mercury | +2.161 |
Neg logit contributions | |
avage | -2.479 |
leck | -2.138 |
ghai | -2.060 |
anski | -2.000 |
Gat | -1.969 |
Token | A |
Token ID | 32 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
Nept | +0.093 |
Reef | +0.087 |
oranges | +0.084 |
Ib | +0.083 |
Mercury | +0.080 |
Neg logit contributions | |
avage | -0.155 |
leck | -0.137 |
ghai | -0.133 |
anski | -0.129 |
Gat | -0.129 |
Token | - |
Token ID | 12 |
Feature activation | +9.50e-04 |
Pos logit contributions | |
avage | +1.143 |
leck | +0.979 |
ghai | +0.941 |
Gat | +0.927 |
anski | +0.916 |
Neg logit contributions | |
Nept | -1.049 |
Reef | -0.987 |
oranges | -0.977 |
Ib | -0.954 |
adul | -0.935 |
Token | Sven |
Token ID | 44611 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
Nept | +4.493 |
Reef | +4.238 |
Ib | +4.199 |
oranges | +4.024 |
Mercury | +3.997 |
Neg logit contributions | |
avage | -5.363 |
leck | -4.615 |
ghai | -4.448 |
anski | -4.307 |
Gat | -4.233 |
Token | s |
Token ID | 82 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
avage | +0.191 |
leck | +0.164 |
ghai | +0.158 |
Gat | +0.153 |
anski | +0.153 |
Neg logit contributions | |
Nept | -0.170 |
Reef | -0.162 |
oranges | -0.157 |
Ib | -0.157 |
Mercury | -0.152 |
Token | ka |
Token ID | 4914 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Nept | +0.288 |
Reef | +0.275 |
Ib | +0.269 |
oranges | +0.268 |
Mercury | +0.261 |
Neg logit contributions | |
avage | -0.246 |
leck | -0.210 |
ghai | -0.200 |
Gat | -0.192 |
anski | -0.191 |
Token | Te |
Token ID | 1665 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
Nept | +2.683 |
Reef | +2.523 |
Ib | +2.489 |
oranges | +2.424 |
Mercury | +2.384 |
Neg logit contributions | |
avage | -3.482 |
leck | -3.018 |
ghai | -2.920 |
anski | -2.816 |
GBT | -2.767 |
Token | ater |
Token ID | 729 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
avage | +0.856 |
leck | +0.738 |
ghai | +0.710 |
anski | +0.689 |
Gat | +0.686 |
Neg logit contributions | |
Nept | -0.783 |
Reef | -0.743 |
oranges | -0.721 |
Ib | -0.720 |
Mercury | -0.698 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Nept | +1.028 |
Reef | +0.969 |
Ib | +0.941 |
oranges | +0.935 |
Mercury | +0.911 |
Neg logit contributions | |
avage | -1.215 |
leck | -1.054 |
ghai | -1.013 |
Gat | -0.984 |
anski | -0.979 |
Token | 26 |
Token ID | 2075 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Nept | +10.132 |
Reef | +10.129 |
Mercury | +9.812 |
Ib | +9.573 |
Norn | +9.413 |
Neg logit contributions | |
avage | -19.298 |
ghai | -17.573 |
leck | -17.456 |
anski | -17.167 |
Gat | -16.528 |
Token | ] |
Token ID | 60 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Nept | +3.744 |
Reef | +3.493 |
Ib | +3.459 |
oranges | +3.339 |
Mercury | +3.305 |
Neg logit contributions | |
avage | -6.625 |
leck | -5.958 |
ghai | -5.757 |
anski | -5.597 |
Gat | -5.521 |
Token |
|
Token ID | 198 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
Nept | +4.434 |
Reef | +4.156 |
Ib | +4.049 |
Mercury | +3.984 |
Norn | +3.891 |
Neg logit contributions | |
avage | -6.388 |
leck | -5.648 |
ghai | -5.513 |
anski | -5.270 |
sth | -5.189 |
Token |
|
Token ID | 198 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
Nept | +0.837 |
Reef | +0.796 |
Ib | +0.768 |
oranges | +0.767 |
Mercury | +0.746 |
Neg logit contributions | |
avage | -0.990 |
leck | -0.861 |
ghai | -0.830 |
anski | -0.806 |
Gat | -0.799 |
Token | In |
Token ID | 818 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
Nept | +0.414 |
Reef | +0.391 |
Ib | +0.379 |
oranges | +0.377 |
Mercury | +0.368 |
Neg logit contributions | |
avage | -0.522 |
leck | -0.455 |
ghai | -0.441 |
anski | -0.426 |
Gat | -0.426 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
avage | +4.729 |
leck | +4.028 |
ghai | +3.871 |
Gat | +3.815 |
anski | +3.725 |
Neg logit contributions | |
Nept | -4.532 |
Reef | -4.267 |
oranges | -4.180 |
Ib | -4.107 |
adul | -4.035 |
Token | 98 |
Token ID | 4089 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Nept | +4.329 |
Reef | +4.216 |
Ib | +3.885 |
Mercury | +3.832 |
Norn | +3.823 |
Neg logit contributions | |
avage | -10.044 |
leck | -9.187 |
ghai | -9.085 |
anski | -8.823 |
Gat | -8.633 |
Token | ] |
Token ID | 60 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Nept | +3.509 |
Reef | +3.295 |
Ib | +3.221 |
oranges | +3.122 |
Mercury | +3.077 |
Neg logit contributions | |
avage | -6.244 |
leck | -5.574 |
ghai | -5.454 |
anski | -5.279 |
sth | -5.200 |
Token | Sporting |
Token ID | 31790 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
avage | +2.273 |
leck | +1.969 |
ghai | +1.893 |
Gat | +1.863 |
anski | +1.846 |
Neg logit contributions | |
Nept | -1.871 |
Reef | -1.763 |
oranges | -1.723 |
Ib | -1.697 |
adul | -1.653 |
Token | News |
Token ID | 3000 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
Nept | +1.923 |
Reef | +1.852 |
Ib | +1.815 |
oranges | +1.782 |
Mercury | +1.775 |
Neg logit contributions | |
avage | -2.005 |
leck | -1.747 |
ghai | -1.671 |
anski | -1.628 |
Gat | -1.590 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
avage | +2.875 |
leck | +2.465 |
ghai | +2.380 |
Gat | +2.314 |
anski | +2.301 |
Neg logit contributions | |
Nept | -2.570 |
Reef | -2.429 |
oranges | -2.366 |
Ib | -2.343 |
adul | -2.279 |
Token | 99 |
Token ID | 2079 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Nept | +8.989 |
Norn | +8.629 |
Reef | +8.308 |
Mercury | +8.034 |
299 | +7.983 |
Neg logit contributions | |
avage | -20.526 |
ghai | -19.795 |
anski | -19.630 |
leck | -19.559 |
Gat | -17.948 |
Token | ] |
Token ID | 60 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Nept | +1.912 |
Reef | +1.800 |
Ib | +1.742 |
oranges | +1.719 |
Mercury | +1.671 |
Neg logit contributions | |
avage | -3.114 |
leck | -2.762 |
ghai | -2.677 |
anski | -2.606 |
Gat | -2.576 |
Token | SB |
Token ID | 18056 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
avage | +1.575 |
leck | +1.366 |
ghai | +1.316 |
Gat | +1.284 |
anski | +1.280 |
Neg logit contributions | |
Nept | -1.310 |
Reef | -1.238 |
oranges | -1.205 |
Ib | -1.192 |
adul | -1.157 |
Token | Nation |
Token ID | 8741 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
avage | +2.040 |
leck | +1.785 |
ghai | +1.733 |
anski | +1.687 |
Gat | +1.682 |
Neg logit contributions | |
Nept | -1.415 |
Reef | -1.328 |
oranges | -1.287 |
Ib | -1.276 |
adul | -1.236 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
avage | +3.951 |
leck | +3.366 |
ghai | +3.234 |
Gat | +3.164 |
anski | +3.124 |
Neg logit contributions | |
Nept | -3.708 |
Reef | -3.495 |
oranges | -3.421 |
Ib | -3.363 |
adul | -3.300 |
Token | org |
Token ID | 8745 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Nept | +2.964 |
oranges | +2.709 |
Reef | +2.677 |
Ib | +2.661 |
Mercury | +2.514 |
Neg logit contributions | |
avage | -6.894 |
leck | -6.184 |
ghai | -5.991 |
anski | -5.967 |
sth | -5.759 |
Token | . |
Token ID | 764 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Nept | +3.973 |
Reef | +3.782 |
Ib | +3.712 |
oranges | +3.657 |
Mercury | +3.643 |
Neg logit contributions | |
avage | -3.900 |
leck | -3.366 |
ghai | -3.228 |
anski | -3.119 |
Gat | -3.050 |
Token | cl |
Token ID | 537 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Nept | +4.459 |
oranges | +4.230 |
Ib | +4.165 |
Reef | +4.139 |
Mercury | +4.035 |
Neg logit contributions | |
avage | -6.180 |
leck | -5.303 |
anski | -5.140 |
ghai | -5.094 |
GBT | -4.935 |
Token | ojure |
Token ID | 32511 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
jah | +9.064 |
Nept | +9.000 |
Ib | +8.889 |
oranges | +8.681 |
ojure | +8.590 |
Neg logit contributions | |
avage | -21.680 |
etheless | -20.922 |
Interstitial | -20.795 |
GBT | -20.487 |
Gat | -20.373 |
Token | / |
Token ID | 1220 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
Nept | +1.400 |
Reef | +1.319 |
Ib | +1.274 |
oranges | +1.265 |
Mercury | +1.242 |
Neg logit contributions | |
avage | -1.966 |
leck | -1.736 |
ghai | -1.667 |
anski | -1.628 |
Gat | -1.600 |
Token | cl |
Token ID | 537 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Nept | +0.500 |
Reef | +0.473 |
oranges | +0.465 |
Ib | +0.462 |
Mercury | +0.448 |
Neg logit contributions | |
avage | -0.569 |
leck | -0.491 |
ghai | -0.469 |
anski | -0.464 |
Gat | -0.455 |
Token | ojure |
Token ID | 32511 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
Nept | +7.986 |
jah | +7.916 |
Ib | +7.875 |
oranges | +7.548 |
Mercury | +7.420 |
Neg logit contributions | |
avage | -21.061 |
Interstitial | -20.011 |
etheless | -19.977 |
GBT | -19.697 |
Gat | -19.583 |
Token | | |
Token ID | 930 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Nept | +3.210 |
Reef | +2.917 |
Ib | +2.884 |
oranges | +2.821 |
Mercury | +2.730 |
Neg logit contributions | |
avage | -8.747 |
leck | -7.966 |
ghai | -7.709 |
anski | -7.641 |
Gat | -7.446 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
Nept | +1.835 |
Reef | +1.701 |
oranges | +1.666 |
Ib | +1.659 |
Mercury | +1.610 |
Neg logit contributions | |
avage | -2.646 |
leck | -2.346 |
ghai | -2.252 |
anski | -2.213 |
Gat | -2.169 |
Token | . |
Token ID | 764 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Nept | +0.420 |
Reef | +0.402 |
oranges | +0.391 |
Ib | +0.390 |
Mercury | +0.381 |
Neg logit contributions | |
avage | -0.352 |
leck | -0.297 |
ghai | -0.283 |
anski | -0.274 |
Gat | -0.272 |
Token | 8 |
Token ID | 807 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
avage | +2.379 |
leck | +2.082 |
ghai | +2.018 |
Gat | +1.981 |
anski | +1.970 |
Neg logit contributions | |
Nept | -1.676 |
Reef | -1.577 |
oranges | -1.534 |
Ib | -1.508 |
adul | -1.465 |
Token | org |
Token ID | 8745 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
Nept | +2.854 |
oranges | +2.606 |
Ib | +2.581 |
Reef | +2.577 |
Mercury | +2.442 |
Neg logit contributions | |
avage | -6.243 |
leck | -5.552 |
ghai | -5.401 |
anski | -5.363 |
Gat | -5.182 |
Token | . |
Token ID | 764 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
Nept | +3.648 |
Reef | +3.474 |
Ib | +3.414 |
oranges | +3.366 |
Mercury | +3.336 |
Neg logit contributions | |
avage | -3.499 |
leck | -3.007 |
ghai | -2.880 |
anski | -2.790 |
Gat | -2.736 |
Token | cl |
Token ID | 537 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Nept | +4.460 |
oranges | +4.266 |
Ib | +4.188 |
Reef | +4.108 |
Mercury | +4.041 |
Neg logit contributions | |
avage | -6.368 |
leck | -5.450 |
anski | -5.311 |
ghai | -5.256 |
GBT | -5.111 |
Token | ojure |
Token ID | 32511 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
jah | +8.787 |
Nept | +8.647 |
Ib | +8.621 |
oranges | +8.292 |
ojure | +8.063 |
Neg logit contributions | |
avage | -21.467 |
etheless | -20.758 |
Interstitial | -20.609 |
GBT | -20.335 |
Gat | -20.208 |
Token | / |
Token ID | 1220 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
Nept | +1.646 |
Reef | +1.554 |
Ib | +1.499 |
oranges | +1.483 |
Mercury | +1.461 |
Neg logit contributions | |
avage | -2.331 |
leck | -2.060 |
ghai | -1.979 |
anski | -1.934 |
Gat | -1.902 |
Token | cl |
Token ID | 537 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Nept | +0.591 |
Reef | +0.560 |
oranges | +0.548 |
Ib | +0.545 |
Mercury | +0.529 |
Neg logit contributions | |
avage | -0.650 |
leck | -0.559 |
ghai | -0.537 |
anski | -0.526 |
Gat | -0.519 |
Token | oj |
Token ID | 13210 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
Nept | +7.696 |
jah | +7.690 |
Ib | +7.590 |
oranges | +7.229 |
Mercury | +7.019 |
Neg logit contributions | |
avage | -21.339 |
Interstitial | -20.402 |
etheless | -20.362 |
GBT | -20.117 |
Gat | -19.917 |
Token | ures |
Token ID | 942 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
avage | +0.925 |
leck | +0.798 |
ghai | +0.768 |
anski | +0.746 |
Gat | +0.743 |
Neg logit contributions | |
Nept | -0.841 |
Reef | -0.798 |
oranges | -0.776 |
Ib | -0.772 |
Mercury | -0.750 |
Token | cript |
Token ID | 6519 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
avage | +2.857 |
leck | +2.435 |
ghai | +2.340 |
Gat | +2.265 |
anski | +2.258 |
Neg logit contributions | |
Nept | -2.787 |
Reef | -2.652 |
oranges | -2.568 |
Ib | -2.539 |
adul | -2.496 |
Token | | |
Token ID | 930 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Nept | +3.823 |
oranges | +3.541 |
Reef | +3.499 |
Ib | +3.476 |
Mercury | +3.278 |
Neg logit contributions | |
avage | -7.764 |
leck | -7.010 |
ghai | -6.691 |
anski | -6.609 |
Gat | -6.575 |
Token | 30 |
Token ID | 1542 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
Nept | +3.450 |
Reef | +3.255 |
Ib | +3.131 |
oranges | +2.989 |
Mercury | +2.980 |
Neg logit contributions | |
avage | -6.511 |
leck | -5.879 |
ghai | -5.740 |
anski | -5.572 |
sth | -5.391 |
Token | org |
Token ID | 8745 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Nept | +3.685 |
oranges | +3.392 |
Ib | +3.323 |
Reef | +3.292 |
sax | +3.140 |
Neg logit contributions | |
avage | -8.588 |
leck | -7.689 |
ghai | -7.454 |
anski | -7.450 |
sth | -7.163 |
Token | . |
Token ID | 764 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Nept | +4.817 |
Reef | +4.569 |
Ib | +4.505 |
Mercury | +4.424 |
oranges | +4.416 |
Neg logit contributions | |
avage | -4.958 |
leck | -4.307 |
ghai | -4.120 |
anski | -3.988 |
etheless | -3.912 |
Token | cl |
Token ID | 537 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Nept | +4.149 |
oranges | +3.969 |
Ib | +3.867 |
Reef | +3.832 |
sax | +3.759 |
Neg logit contributions | |
avage | -5.680 |
leck | -4.871 |
anski | -4.742 |
ghai | -4.659 |
Gat | -4.546 |
Token | ojure |
Token ID | 32511 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
jah | +9.340 |
Nept | +9.248 |
Ib | +9.225 |
oranges | +9.052 |
ojure | +8.799 |
Neg logit contributions | |
avage | -21.283 |
Interstitial | -20.500 |
etheless | -20.442 |
GBT | -20.139 |
Gat | -19.990 |
Token | / |
Token ID | 1220 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Nept | +2.948 |
Reef | +2.746 |
Ib | +2.690 |
oranges | +2.681 |
Mercury | +2.607 |
Neg logit contributions | |
avage | -4.441 |
leck | -3.964 |
ghai | -3.782 |
anski | -3.725 |
Gat | -3.652 |
Token | cl |
Token ID | 537 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Nept | +2.096 |
Reef | +1.971 |
oranges | +1.961 |
Ib | +1.941 |
Mercury | +1.879 |
Neg logit contributions | |
avage | -2.517 |
leck | -2.183 |
anski | -2.079 |
ghai | -2.079 |
Gat | -2.021 |
Token | ojure |
Token ID | 32511 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Nept | +7.943 |
Ib | +7.883 |
jah | +7.861 |
oranges | +7.640 |
Mercury | +7.395 |
Neg logit contributions | |
avage | -20.800 |
Interstitial | -19.812 |
etheless | -19.618 |
GBT | -19.484 |
Gat | -19.352 |
Token | | |
Token ID | 930 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Nept | +3.854 |
Ib | +3.506 |
Reef | +3.495 |
oranges | +3.430 |
Mercury | +3.316 |
Neg logit contributions | |
avage | -9.991 |
leck | -9.096 |
ghai | -8.799 |
anski | -8.710 |
Gat | -8.503 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
Nept | +2.053 |
Reef | +1.900 |
oranges | +1.864 |
Ib | +1.858 |
Mercury | +1.804 |
Neg logit contributions | |
avage | -2.993 |
leck | -2.656 |
ghai | -2.551 |
anski | -2.507 |
Gat | -2.454 |
Token | . |
Token ID | 764 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Nept | +0.243 |
Reef | +0.232 |
oranges | +0.226 |
Ib | +0.226 |
Mercury | +0.220 |
Neg logit contributions | |
avage | -0.203 |
leck | -0.171 |
ghai | -0.163 |
anski | -0.157 |
Gat | -0.156 |
Token | 7 |
Token ID | 767 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
avage | +5.892 |
leck | +5.135 |
Gat | +4.990 |
ghai | +4.964 |
anski | +4.869 |
Neg logit contributions | |
Nept | -4.510 |
Reef | -4.252 |
oranges | -4.168 |
Ib | -4.026 |
adul | -3.986 |
Token | not |
Token ID | 407 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Nept | +2.637 |
Reef | +2.521 |
oranges | +2.467 |
Ib | +2.439 |
adul | +2.384 |
Neg logit contributions | |
avage | -3.321 |
leck | -2.876 |
ghai | -2.752 |
anski | -2.681 |
sth | -2.616 |
Token | an |
Token ID | 281 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
Nept | +1.183 |
Reef | +1.121 |
oranges | +1.094 |
Ib | +1.085 |
Mercury | +1.051 |
Neg logit contributions | |
avage | -1.559 |
leck | -1.354 |
ghai | -1.310 |
anski | -1.281 |
sth | -1.253 |
Token | apples |
Token ID | 22514 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
Nept | +0.821 |
Reef | +0.777 |
oranges | +0.759 |
Ib | +0.753 |
adul | +0.728 |
Neg logit contributions | |
avage | -1.187 |
leck | -1.044 |
ghai | -1.000 |
anski | -0.982 |
Gat | -0.965 |
Token | - |
Token ID | 12 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
oranges | +6.406 |
Nept | +6.387 |
Reef | +6.193 |
Ib | +5.993 |
adul | +5.764 |
Neg logit contributions | |
avage | -10.850 |
leck | -9.812 |
ghai | -9.711 |
Interstitial | -9.331 |
anski | -9.253 |
Token | to |
Token ID | 1462 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
oranges | +6.624 |
Nept | +5.717 |
Ib | +5.574 |
Mercury | +5.491 |
Reef | +5.432 |
Neg logit contributions | |
avage | -13.022 |
ghai | -11.799 |
GBT | -11.590 |
Gat | -11.583 |
leck | -11.491 |
Token | - |
Token ID | 12 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Nept | +3.850 |
Reef | +3.673 |
oranges | +3.663 |
Ib | +3.538 |
Mercury | +3.445 |
Neg logit contributions | |
avage | -5.437 |
leck | -4.782 |
ghai | -4.699 |
anski | -4.484 |
Gat | -4.472 |
Token | app |
Token ID | 1324 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
oranges | +10.233 |
apples | +8.321 |
needed | +6.829 |
jah | +6.441 |
truth | +6.414 |
Neg logit contributions | |
avage | -21.168 |
Achievements | -20.360 |
ghai | -20.235 |
Gat | -20.156 |
veyard | -20.002 |
Token | les |
Token ID | 829 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
oranges | +5.297 |
Nept | +5.266 |
Reef | +5.179 |
Ib | +5.012 |
adul | +4.890 |
Neg logit contributions | |
avage | -2.586 |
ghai | -1.946 |
leck | -1.890 |
Gat | -1.843 |
sth | -1.746 |
Token | comparison |
Token ID | 7208 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
oranges | +7.274 |
Reef | +6.797 |
Ib | +6.693 |
Nept | +6.645 |
adul | +6.555 |
Neg logit contributions | |
avage | -16.802 |
leck | -15.418 |
ghai | -15.011 |
anski | -14.800 |
Interstitial | -14.695 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Nept | +4.903 |
Reef | +4.616 |
oranges | +4.489 |
Ib | +4.466 |
adul | +4.357 |
Neg logit contributions | |
avage | -7.494 |
leck | -6.770 |
ghai | -6.504 |
Interstitial | -6.330 |
GBT | -6.313 |
Token |
|
Token ID | 198 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
avage | +1.437 |
leck | +1.246 |
ghai | +1.202 |
anski | +1.168 |
Gat | +1.168 |
Neg logit contributions | |
Nept | -1.218 |
Reef | -1.152 |
oranges | -1.121 |
Ib | -1.111 |
Mercury | -1.079 |
Token | 2001 |
Token ID | 14585 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Nept | +7.421 |
Truth | +7.237 |
Reef | +7.199 |
Ib | +6.863 |
Mercury | +6.704 |
Neg logit contributions | |
avage | -24.947 |
etheless | -24.119 |
ghai | -23.002 |
leck | -22.589 |
anski | -21.885 |
Token | John |
Token ID | 1757 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Nept | +1.459 |
Reef | +1.383 |
Ib | +1.322 |
oranges | +1.296 |
Mercury | +1.281 |
Neg logit contributions | |
avage | -2.365 |
leck | -2.077 |
ghai | -2.041 |
anski | -1.970 |
GBT | -1.942 |
Token | Lith |
Token ID | 19730 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
avage | +3.904 |
leck | +3.399 |
Gat | +3.237 |
ghai | +3.220 |
anski | +3.146 |
Neg logit contributions | |
Nept | -3.991 |
oranges | -3.855 |
Reef | -3.837 |
adul | -3.664 |
Ib | -3.661 |
Token | gow |
Token ID | 21175 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
avage | +2.842 |
leck | +2.166 |
ghai | +1.892 |
anski | +1.771 |
Gat | +1.697 |
Neg logit contributions | |
Nept | -8.393 |
Reef | -7.940 |
oranges | -7.876 |
Ib | -7.788 |
Norn | -7.729 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e-03 |
Pos logit contributions | |
Nept | +5.277 |
Reef | +5.144 |
Ib | +4.964 |
Mercury | +4.837 |
oranges | +4.725 |
Neg logit contributions | |
avage | -7.927 |
leck | -7.033 |
ghai | -6.915 |
anski | -6.644 |
etheless | -6.641 |
Token |
|
Token ID | 198 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
avage | +0.030 |
leck | +0.026 |
ghai | +0.025 |
Gat | +0.024 |
anski | +0.024 |
Neg logit contributions | |
Nept | -0.028 |
Reef | -0.026 |
oranges | -0.025 |
Ib | -0.025 |
adul | -0.024 |
Token | 2001 |
Token ID | 14585 |
Feature activation | +9.98e-02 |
Pos logit contributions | |
Nept | +7.220 |
Truth | +6.870 |
Reef | +6.867 |
Ib | +6.691 |
Mercury | +6.404 |
Neg logit contributions | |
avage | -23.149 |
etheless | -21.726 |
ghai | -21.168 |
leck | -20.606 |
anski | -20.029 |
Token | Frankie |
Token ID | 48535 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Nept | +0.972 |
Reef | +0.920 |
Ib | +0.882 |
oranges | +0.868 |
Mercury | +0.855 |
Neg logit contributions | |
avage | -1.448 |
leck | -1.264 |
ghai | -1.239 |
anski | -1.197 |
Gat | -1.177 |
Token | Mun |
Token ID | 12107 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
avage | +3.602 |
leck | +3.139 |
Gat | +2.979 |
ghai | +2.957 |
anski | +2.956 |
Neg logit contributions | |
Nept | -2.905 |
Reef | -2.724 |
oranges | -2.691 |
Ib | -2.620 |
adul | -2.560 |
Token | iz |
Token ID | 528 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
avage | +3.185 |
leck | +2.597 |
ghai | +2.378 |
anski | +2.340 |
Gat | +2.276 |
Neg logit contributions | |
Nept | -5.428 |
Reef | -5.207 |
oranges | -5.104 |
Ib | -5.099 |
Norn | -5.046 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Nept | +5.319 |
Reef | +4.983 |
Ib | +4.925 |
oranges | +4.875 |
Mercury | +4.691 |
Neg logit contributions | |
avage | -8.773 |
ghai | -7.718 |
leck | -7.630 |
sth | -7.348 |
GBT | -7.327 |
Token | NS |
Token ID | 8035 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
avage | +6.045 |
leck | +4.485 |
sth | +4.236 |
ghai | +4.177 |
anski | +4.030 |
Neg logit contributions | |
Nept | -13.072 |
oranges | -12.606 |
Reef | -12.579 |
Ib | -12.538 |
adul | -12.456 |
Token | following |
Token ID | 1708 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
avage | +8.228 |
leck | +6.729 |
ghai | +6.575 |
Gat | +6.509 |
anski | +6.328 |
Neg logit contributions | |
Nept | -8.033 |
Reef | -7.649 |
oranges | -7.317 |
Ib | -7.159 |
Mercury | -7.087 |
Token | 4 |
Token ID | 604 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
avage | +15.484 |
Gat | +13.034 |
ghai | +12.524 |
leck | +12.398 |
Discover | +12.313 |
Neg logit contributions | |
Nept | -11.318 |
Reef | -10.701 |
oranges | -9.841 |
Norn | -9.696 |
Mercury | -9.445 |
Token | weeks |
Token ID | 2745 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
avage | +0.357 |
leck | +0.313 |
ghai | +0.302 |
anski | +0.294 |
Gat | +0.292 |
Neg logit contributions | |
Nept | -0.275 |
Reef | -0.259 |
oranges | -0.253 |
Ib | -0.251 |
Mercury | -0.242 |
Token | of |
Token ID | 286 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
avage | +8.197 |
ghai | +6.634 |
leck | +6.553 |
Gat | +6.544 |
sth | +6.309 |
Neg logit contributions | |
Nept | -7.767 |
Reef | -7.418 |
oranges | -7.106 |
Ib | -6.906 |
Mercury | -6.865 |
Token | sham |
Token ID | 23565 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
avage | +16.787 |
Gat | +14.087 |
ghai | +13.672 |
Discover | +13.405 |
sth | +13.222 |
Neg logit contributions | |
Nept | -13.881 |
Reef | -13.060 |
oranges | -11.787 |
Norn | -11.651 |
Mercury | -11.521 |
Token | ); |
Token ID | 1776 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
avage | +21.755 |
ghai | +17.949 |
Gat | +17.854 |
leck | +17.410 |
sth | +17.115 |
Neg logit contributions | |
Nept | -15.378 |
Reef | -14.511 |
oranges | -13.009 |
Mercury | -12.817 |
adul | -12.732 |
Token | and |
Token ID | 290 |
Feature activation | -5.83e-03 |
Pos logit contributions | |
Nept | +1.365 |
Reef | +1.297 |
oranges | +1.264 |
Ib | +1.259 |
Mercury | +1.212 |
Neg logit contributions | |
avage | -1.903 |
leck | -1.690 |
ghai | -1.623 |
anski | -1.577 |
Gat | -1.568 |
Token | ( |
Token ID | 357 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
avage | +0.082 |
leck | +0.072 |
ghai | +0.070 |
anski | +0.068 |
Gat | +0.068 |
Neg logit contributions | |
Nept | -0.058 |
Reef | -0.055 |
oranges | -0.053 |
Ib | -0.053 |
Mercury | -0.051 |
Token | 3 |
Token ID | 18 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Nept | +3.405 |
Reef | +3.284 |
Ib | +3.116 |
Mercury | +3.073 |
oranges | +2.942 |
Neg logit contributions | |
avage | -7.678 |
leck | -7.035 |
ghai | -6.760 |
anski | -6.597 |
Gat | -6.566 |
Token | ) |
Token ID | 8 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Nept | +3.302 |
Reef | +3.158 |
Ib | +3.045 |
oranges | +2.971 |
Mercury | +2.968 |
Neg logit contributions | |
avage | -4.698 |
leck | -4.179 |
ghai | -4.041 |
anski | -3.932 |
Gat | -3.858 |
Token | 8 |
Token ID | 23 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
avage | +6.487 |
leck | +5.564 |
ghai | +5.394 |
anski | +5.263 |
sth | +5.164 |
Neg logit contributions | |
Nept | -6.110 |
Reef | -5.711 |
oranges | -5.594 |
Mercury | -5.406 |
Ib | -5.394 |
Token | { |
Token ID | 1391 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
avage | +8.193 |
leck | +6.558 |
Gat | +6.472 |
ghai | +6.420 |
Discover | +6.166 |
Neg logit contributions | |
Nept | -12.586 |
Reef | -12.070 |
oranges | -11.941 |
adul | -11.610 |
Mercury | -11.484 |
Token | ( |
Token ID | 7 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Nept | +0.595 |
Reef | +0.567 |
Ib | +0.548 |
oranges | +0.548 |
Mercury | +0.533 |
Neg logit contributions | |
avage | -0.650 |
leck | -0.561 |
ghai | -0.540 |
anski | -0.524 |
Gat | -0.521 |
Token | 113 |
Token ID | 16616 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
Nept | +1.447 |
Reef | +1.373 |
Ib | +1.330 |
oranges | +1.310 |
Mercury | +1.288 |
Neg logit contributions | |
avage | -1.979 |
leck | -1.736 |
ghai | -1.689 |
anski | -1.637 |
Gat | -1.623 |
Token | s |
Token ID | 82 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
avage | +1.409 |
leck | +1.236 |
ghai | +1.202 |
anski | +1.173 |
Gat | +1.169 |
Neg logit contributions | |
Nept | -0.960 |
Reef | -0.900 |
oranges | -0.866 |
Ib | -0.862 |
adul | -0.834 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Nept | +0.547 |
Reef | +0.519 |
oranges | +0.503 |
Ib | +0.501 |
Mercury | +0.487 |
Neg logit contributions | |
avage | -0.628 |
leck | -0.543 |
ghai | -0.524 |
anski | -0.509 |
Gat | -0.507 |
Token | 56 |
Token ID | 7265 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
avage | +18.125 |
Gat | +16.788 |
ghai | +15.503 |
Discover | +15.416 |
leck | +15.022 |
Neg logit contributions | |
oranges | -15.784 |
Nept | -15.619 |
jah | -14.926 |
Reef | -14.650 |
thous | -14.452 |
Token | . |
Token ID | 13 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
avage | +4.877 |
leck | +4.041 |
Gat | +4.034 |
ghai | +3.983 |
Discover | +3.816 |
Neg logit contributions | |
Nept | -5.623 |
oranges | -5.346 |
Reef | -5.310 |
sax | -5.079 |
Ib | -5.065 |
Token | f |
Token ID | 277 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
avage | +3.602 |
leck | +3.149 |
ghai | +3.034 |
Gat | +2.995 |
anski | +2.956 |
Neg logit contributions | |
Nept | -2.824 |
Reef | -2.669 |
oranges | -2.617 |
Ib | -2.548 |
Mercury | -2.509 |
Token | 5 |
Token ID | 20 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
avage | +4.796 |
leck | +4.196 |
ghai | +3.991 |
anski | +3.908 |
Gat | +3.871 |
Neg logit contributions | |
Nept | -4.076 |
Reef | -3.845 |
oranges | -3.760 |
Ib | -3.668 |
Mercury | -3.604 |
Token | { |
Token ID | 1391 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
avage | +5.674 |
leck | +4.754 |
ghai | +4.555 |
Gat | +4.505 |
anski | +4.427 |
Neg logit contributions | |
Nept | -7.059 |
Reef | -6.757 |
oranges | -6.682 |
Ib | -6.436 |
adul | -6.428 |
Token | start |
Token ID | 923 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
avage | +3.865 |
leck | +3.393 |
ghai | +3.291 |
Gat | +3.244 |
anski | +3.210 |
Neg logit contributions | |
Nept | -2.739 |
Reef | -2.577 |
oranges | -2.514 |
Ib | -2.464 |
Norn | -2.419 |
Token | . |
Token ID | 13 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
avage | +5.370 |
leck | +4.625 |
ghai | +4.471 |
Gat | +4.389 |
anski | +4.301 |
Neg logit contributions | |
Nept | -4.919 |
Reef | -4.663 |
oranges | -4.563 |
Ib | -4.456 |
adul | -4.371 |
Token | When |
Token ID | 1649 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
avage | +5.104 |
leck | +4.378 |
Gat | +4.229 |
ghai | +4.187 |
Discover | +4.083 |
Neg logit contributions | |
Nept | -4.747 |
oranges | -4.478 |
Reef | -4.474 |
adul | -4.287 |
sax | -4.266 |
Token | we |
Token ID | 356 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
avage | +7.069 |
leck | +6.188 |
Gat | +5.916 |
ghai | +5.869 |
anski | +5.676 |
Neg logit contributions | |
Nept | -6.533 |
Reef | -6.221 |
oranges | -5.985 |
Norn | -5.859 |
adul | -5.847 |
Token | lost |
Token ID | 2626 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
avage | +6.568 |
leck | +5.673 |
ghai | +5.472 |
Gat | +5.396 |
anski | +5.362 |
Neg logit contributions | |
Nept | -5.797 |
Reef | -5.502 |
oranges | -5.327 |
Ib | -5.245 |
Norn | -5.176 |
Token | at |
Token ID | 379 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
avage | +6.483 |
leck | +5.708 |
Gat | +5.494 |
ghai | +5.386 |
anski | +5.288 |
Neg logit contributions | |
Nept | -5.563 |
Reef | -5.213 |
oranges | -5.098 |
Ib | -4.947 |
Norn | -4.943 |
Token | Crystal |
Token ID | 12969 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
avage | +19.956 |
Gat | +18.802 |
Discover | +17.315 |
leck | +16.602 |
Shank | +16.599 |
Neg logit contributions | |
Nept | -13.192 |
oranges | -12.629 |
Skydragon | -12.540 |
sax | -12.494 |
Reef | -12.404 |
Token | Palace |
Token ID | 15301 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
avage | +2.556 |
leck | +2.261 |
ghai | +2.181 |
Gat | +2.141 |
anski | +2.126 |
Neg logit contributions | |
Nept | -1.727 |
Reef | -1.581 |
oranges | -1.562 |
Ib | -1.513 |
adul | -1.506 |
Token | , |
Token ID | 11 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
avage | +6.370 |
leck | +5.543 |
ghai | +5.301 |
Gat | +5.255 |
anski | +5.169 |
Neg logit contributions | |
Nept | -5.977 |
Reef | -5.657 |
oranges | -5.534 |
Ib | -5.398 |
Norn | -5.321 |
Token | for |
Token ID | 329 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
avage | +8.090 |
leck | +7.066 |
Gat | +6.738 |
ghai | +6.627 |
anski | +6.501 |
Neg logit contributions | |
Nept | -7.269 |
Reef | -6.888 |
oranges | -6.633 |
Norn | -6.475 |
sax | -6.459 |
Token | example |
Token ID | 1672 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
avage | +9.554 |
leck | +8.514 |
Gat | +7.975 |
ghai | +7.468 |
anski | +7.396 |
Neg logit contributions | |
Nept | -11.823 |
Reef | -10.990 |
oranges | -10.806 |
Norn | -10.770 |
Skydragon | -10.732 |
Token | ALL |
Token ID | 11096 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
avage | +7.037 |
leck | +5.669 |
Gat | +5.468 |
Discover | +5.396 |
GBT | +5.220 |
Neg logit contributions | |
Nept | -9.750 |
oranges | -9.311 |
Reef | -9.275 |
adul | -8.892 |
Ib | -8.725 |
Token | PERSON |
Token ID | 46740 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
avage | +6.549 |
leck | +5.287 |
Gat | +4.986 |
Discover | +4.941 |
TE | +4.868 |
Neg logit contributions | |
Nept | -10.644 |
oranges | -10.479 |
Reef | -10.025 |
adul | -9.838 |
sax | -9.747 |
Token | EL |
Token ID | 3698 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
avage | +8.062 |
leck | +6.191 |
Gat | +6.134 |
sth | +6.077 |
TE | +6.043 |
Neg logit contributions | |
oranges | -13.804 |
Nept | -13.693 |
sax | -12.721 |
thous | -12.685 |
Ib | -12.659 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
avage | +3.339 |
leck | +2.610 |
ghai | +2.442 |
Gat | +2.408 |
anski | +2.328 |
Neg logit contributions | |
Nept | -5.964 |
Reef | -5.671 |
oranges | -5.647 |
Ib | -5.528 |
adul | -5.475 |
Token | : |
Token ID | 25 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
Nept | +1.866 |
Reef | +1.760 |
Ib | +1.700 |
oranges | +1.667 |
Mercury | +1.649 |
Neg logit contributions | |
avage | -2.586 |
leck | -2.281 |
ghai | -2.207 |
anski | -2.149 |
Gat | -2.094 |
Token | 0 |
Token ID | 657 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
avage | +6.315 |
leck | +5.306 |
Gat | +5.180 |
ghai | +5.060 |
Discover | +5.042 |
Neg logit contributions | |
Nept | -6.379 |
oranges | -6.091 |
Reef | -6.076 |
Ib | -5.849 |
sax | -5.833 |
Token | 605 |
Token ID | 32417 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
avage | +13.523 |
Gat | +11.077 |
ghai | +10.457 |
sth | +10.416 |
GBT | +10.225 |
Neg logit contributions | |
Nept | -20.652 |
Reef | -19.644 |
oranges | -19.442 |
adul | -19.260 |
sax | -19.083 |
Token | z |
Token ID | 89 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Nept | +5.225 |
Reef | +4.950 |
oranges | +4.859 |
Ib | +4.825 |
Mercury | +4.717 |
Neg logit contributions | |
avage | -5.388 |
leck | -4.594 |
ghai | -4.451 |
GBT | -4.259 |
anski | -4.229 |
Token | BLACK |
Token ID | 31963 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
avage | +2.565 |
leck | +2.218 |
ghai | +2.131 |
Gat | +2.100 |
anski | +2.080 |
Neg logit contributions | |
Nept | -2.147 |
Reef | -2.030 |
oranges | -1.985 |
Ib | -1.949 |
adul | -1.901 |
Token | FO |
Token ID | 6080 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
Nept | +0.908 |
Reef | +0.864 |
Ib | +0.822 |
oranges | +0.814 |
Mercury | +0.792 |
Neg logit contributions | |
avage | -1.801 |
leck | -1.617 |
ghai | -1.583 |
anski | -1.536 |
Gat | -1.521 |
Token | OT |
Token ID | 2394 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
avage | +2.916 |
Gat | +1.667 |
leck | +1.611 |
GBT | +1.596 |
OTS | +1.520 |
Neg logit contributions | |
Nept | -12.373 |
oranges | -11.916 |
Reef | -11.746 |
adul | -11.583 |
sax | -11.536 |
Token | improvement |
Token ID | 9025 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
avage | +2.443 |
leck | +2.119 |
ghai | +2.055 |
Gat | +2.007 |
anski | +1.997 |
Neg logit contributions | |
Nept | -1.965 |
Reef | -1.859 |
oranges | -1.796 |
Ib | -1.778 |
Mercury | -1.727 |
Token | than |
Token ID | 621 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
avage | +4.005 |
leck | +3.426 |
ghai | +3.353 |
Gat | +3.239 |
anski | +3.217 |
Neg logit contributions | |
Nept | -3.482 |
Reef | -3.310 |
oranges | -3.226 |
Ib | -3.167 |
Mercury | -3.086 |
Token | patients |
Token ID | 3871 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
avage | +10.335 |
Gat | +8.642 |
ghai | +8.555 |
leck | +8.538 |
anski | +8.055 |
Neg logit contributions | |
Nept | -9.965 |
Reef | -9.416 |
oranges | -9.126 |
Norn | -8.990 |
Ib | -8.965 |
Token | in |
Token ID | 287 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
avage | +8.403 |
ghai | +7.040 |
leck | +6.877 |
Gat | +6.829 |
sth | +6.472 |
Neg logit contributions | |
Nept | -8.642 |
Reef | -8.280 |
oranges | -7.905 |
Norn | -7.787 |
Ib | -7.727 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
avage | +9.819 |
leck | +7.935 |
Gat | +7.885 |
ghai | +7.784 |
anski | +7.604 |
Neg logit contributions | |
Nept | -10.171 |
Reef | -9.746 |
Norn | -9.093 |
oranges | -9.074 |
Ib | -9.033 |
Token | sham |
Token ID | 23565 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
avage | +9.861 |
Gat | +7.946 |
ghai | +7.823 |
leck | +7.705 |
anski | +7.560 |
Neg logit contributions | |
Nept | -12.148 |
Reef | -11.527 |
Mercury | -10.813 |
oranges | -10.779 |
Norn | -10.743 |
Token | ta |
Token ID | 20486 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
avage | +19.224 |
ghai | +16.368 |
Gat | +15.970 |
leck | +15.749 |
sth | +15.387 |
Neg logit contributions | |
Nept | -15.062 |
Reef | -14.393 |
oranges | -13.070 |
Norn | -13.059 |
adul | -12.950 |
Token | V |
Token ID | 53 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
avage | +7.054 |
sth | +4.935 |
leck | +4.736 |
ghai | +4.657 |
Gat | +4.617 |
Neg logit contributions | |
Nept | -15.630 |
oranges | -15.414 |
thous | -14.987 |
Reef | -14.890 |
sax | -14.668 |
Token | NS |
Token ID | 8035 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
avage | +4.373 |
leck | +3.384 |
ghai | +3.212 |
sth | +3.108 |
anski | +3.091 |
Neg logit contributions | |
Nept | -8.353 |
Reef | -8.016 |
Ib | -7.976 |
oranges | -7.957 |
adul | -7.842 |
Token | group |
Token ID | 1448 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
avage | +9.889 |
Gat | +7.547 |
leck | +7.518 |
ghai | +7.465 |
anski | +7.012 |
Neg logit contributions | |
Nept | -14.405 |
Reef | -13.888 |
Norn | -13.264 |
oranges | -13.019 |
Ib | -12.899 |
Token | as |
Token ID | 355 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
avage | +9.802 |
leck | +8.083 |
ghai | +7.966 |
Gat | +7.853 |
anski | +7.469 |
Neg logit contributions | |
Nept | -9.391 |
Reef | -8.845 |
oranges | -8.571 |
Ib | -8.380 |
Norn | -8.349 |
Token | a |
Token ID | 257 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
avage | +5.081 |
leck | +4.427 |
ghai | +4.240 |
Gat | +4.232 |
anski | +4.107 |
Neg logit contributions | |
Nept | -4.360 |
Reef | -4.084 |
oranges | -3.964 |
Ib | -3.879 |
Norn | -3.844 |
Token | Capital |
Token ID | 9747 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
avage | +5.347 |
leck | +4.687 |
ghai | +4.543 |
Gat | +4.491 |
anski | +4.425 |
Neg logit contributions | |
Nept | -3.601 |
Reef | -3.377 |
oranges | -3.292 |
Ib | -3.205 |
Norn | -3.153 |
Token | One |
Token ID | 1881 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
Reef | +4.186 |
Nept | +4.160 |
Ib | +3.984 |
Mercury | +3.802 |
Norn | +3.647 |
Neg logit contributions | |
avage | -9.709 |
leck | -8.735 |
anski | -8.389 |
ghai | -8.356 |
GBT | -8.244 |
Token | Cup |
Token ID | 5454 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
Nept | +0.165 |
Reef | +0.156 |
Ib | +0.151 |
oranges | +0.150 |
Mercury | +0.145 |
Neg logit contributions | |
avage | -0.242 |
leck | -0.213 |
ghai | -0.206 |
anski | -0.202 |
Gat | -0.197 |
Token | tie |
Token ID | 9839 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
avage | +5.589 |
leck | +4.800 |
ghai | +4.688 |
Gat | +4.563 |
anski | +4.452 |
Neg logit contributions | |
Nept | -5.310 |
Reef | -4.999 |
oranges | -4.871 |
Ib | -4.736 |
Norn | -4.708 |
Token | at |
Token ID | 379 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Nept | +1.507 |
Reef | +1.411 |
Ib | +1.385 |
oranges | +1.371 |
Mercury | +1.327 |
Neg logit contributions | |
avage | -2.243 |
leck | -1.970 |
ghai | -1.908 |
anski | -1.896 |
Gat | -1.834 |
Token | B |
Token ID | 347 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
avage | +18.448 |
Gat | +17.526 |
Discover | +16.022 |
leck | +15.178 |
Shank | +15.060 |
Neg logit contributions | |
Nept | -13.840 |
Reef | -12.903 |
oranges | -12.899 |
sax | -12.574 |
adul | -12.537 |
Token | ourn |
Token ID | 1798 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
avage | +5.346 |
leck | +4.651 |
ghai | +4.451 |
anski | +4.399 |
sth | +4.303 |
Neg logit contributions | |
Nept | -4.203 |
Reef | -3.876 |
oranges | -3.789 |
Ib | -3.690 |
Norn | -3.657 |
Token | emouth |
Token ID | 46880 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
avage | +4.196 |
leck | +3.397 |
ghai | +3.254 |
Gat | +3.235 |
anski | +3.201 |
Neg logit contributions | |
Nept | -6.048 |
Reef | -5.690 |
oranges | -5.583 |
Ib | -5.576 |
Norn | -5.511 |
Token | . |
Token ID | 13 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
avage | +0.525 |
leck | +0.456 |
ghai | +0.440 |
anski | +0.428 |
Gat | +0.424 |
Neg logit contributions | |
Nept | -0.434 |
Reef | -0.411 |
oranges | -0.398 |
Ib | -0.398 |
Mercury | -0.386 |
Token | � |
Token ID | 564 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
Nept | +0.296 |
Reef | +0.281 |
Ib | +0.272 |
oranges | +0.267 |
Mercury | +0.263 |
Neg logit contributions | |
avage | -0.377 |
leck | -0.329 |
ghai | -0.318 |
anski | -0.310 |
Gat | -0.304 |
Token | Beth |
Token ID | 19223 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
avage | +1.277 |
leck | +1.115 |
ghai | +1.077 |
anski | +1.048 |
Gat | +1.047 |
Neg logit contributions | |
Nept | -0.975 |
Reef | -0.920 |
oranges | -0.892 |
Ib | -0.886 |
Mercury | -0.858 |
Token | une |
Token ID | 1726 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Nept | +0.803 |
Reef | +0.722 |
oranges | +0.674 |
Ib | +0.673 |
Mercury | +0.630 |
Neg logit contributions | |
avage | -2.630 |
leck | -2.384 |
ghai | -2.331 |
Gat | -2.287 |
anski | -2.275 |
Token | 's |
Token ID | 338 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
avage | +1.947 |
leck | +1.699 |
ghai | +1.639 |
anski | +1.597 |
Gat | +1.593 |
Neg logit contributions | |
Nept | -1.512 |
Reef | -1.427 |
oranges | -1.383 |
Ib | -1.374 |
Mercury | -1.332 |
Token | last |
Token ID | 938 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
avage | +1.723 |
leck | +1.505 |
ghai | +1.453 |
anski | +1.419 |
Gat | +1.417 |
Neg logit contributions | |
Nept | -1.278 |
Reef | -1.203 |
oranges | -1.166 |
Ib | -1.158 |
Mercury | -1.120 |
Token | residence |
Token ID | 11566 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
avage | +3.847 |
leck | +3.343 |
ghai | +3.206 |
Gat | +3.188 |
anski | +3.168 |
Neg logit contributions | |
Nept | -2.998 |
Reef | -2.808 |
oranges | -2.739 |
Ib | -2.715 |
adul | -2.641 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
avage | +0.326 |
leck | +0.285 |
ghai | +0.276 |
anski | +0.267 |
Gat | +0.264 |
Neg logit contributions | |
Nept | -0.262 |
Reef | -0.249 |
oranges | -0.240 |
Ib | -0.240 |
Mercury | -0.233 |
Token | 56 |
Token ID | 3980 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
avage | +14.594 |
leck | +11.605 |
sth | +11.397 |
Gat | +11.152 |
GBT | +10.950 |
Neg logit contributions | |
Nept | -20.239 |
oranges | -19.057 |
Reef | -18.361 |
Skydragon | -17.346 |
Mercury | -17.238 |
Token | ] |
Token ID | 60 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Nept | +4.789 |
Reef | +4.484 |
Ib | +4.424 |
oranges | +4.246 |
Mercury | +4.171 |
Neg logit contributions | |
avage | -9.582 |
leck | -8.587 |
ghai | -8.412 |
anski | -8.167 |
Gat | -8.057 |
Token | the |
Token ID | 262 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Nept | +2.436 |
Reef | +2.336 |
Ib | +2.260 |
Mercury | +2.206 |
oranges | +2.201 |
Neg logit contributions | |
avage | -3.235 |
leck | -2.846 |
ghai | -2.766 |
anski | -2.670 |
sth | -2.608 |
Token | N |
Token ID | 399 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Nept | +1.540 |
Reef | +1.469 |
Ib | +1.413 |
oranges | +1.389 |
Mercury | +1.379 |
Neg logit contributions | |
avage | -2.006 |
leck | -1.762 |
ghai | -1.707 |
anski | -1.641 |
sth | -1.609 |
Token | AC |
Token ID | 2246 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
Nept | +1.662 |
Reef | +1.611 |
Ib | +1.558 |
oranges | +1.554 |
Mercury | +1.515 |
Neg logit contributions | |
avage | -1.798 |
leck | -1.563 |
ghai | -1.511 |
Gat | -1.461 |
anski | -1.432 |
Token | . |
Token ID | 13 |
Feature activation | +9.64e-02 |
Pos logit contributions | |
avage | +1.847 |
leck | +1.607 |
ghai | +1.550 |
anski | +1.507 |
Gat | +1.501 |
Neg logit contributions | |
Nept | -1.516 |
Reef | -1.435 |
oranges | -1.391 |
Ib | -1.383 |
Mercury | -1.343 |
Token | At |
Token ID | 1629 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
Nept | +1.020 |
Reef | +0.976 |
Ib | +0.934 |
oranges | +0.926 |
Mercury | +0.907 |
Neg logit contributions | |
avage | -1.316 |
leck | -1.157 |
ghai | -1.108 |
anski | -1.081 |
Gat | -1.057 |
Token | roughly |
Token ID | 7323 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
avage | +10.470 |
leck | +9.072 |
Gat | +8.850 |
ghai | +8.680 |
Discover | +8.561 |
Neg logit contributions | |
Nept | -8.286 |
Reef | -7.544 |
oranges | -7.499 |
adul | -7.427 |
Ib | -7.352 |
Token | 20 |
Token ID | 1160 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
avage | +9.261 |
leck | +7.991 |
Gat | +7.736 |
ghai | +7.631 |
Discover | +7.505 |
Neg logit contributions | |
Nept | -7.085 |
Reef | -6.615 |
oranges | -6.370 |
Norn | -6.346 |
Ib | -6.280 |
Token | cents |
Token ID | 16059 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
avage | +2.217 |
leck | +1.903 |
ghai | +1.830 |
Gat | +1.774 |
anski | +1.772 |
Neg logit contributions | |
Nept | -2.146 |
Reef | -2.039 |
oranges | -1.981 |
Ib | -1.969 |
Mercury | -1.919 |
Token | per |
Token ID | 583 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
avage | +2.620 |
leck | +2.292 |
ghai | +2.216 |
anski | +2.159 |
Gat | +2.158 |
Neg logit contributions | |
Nept | -1.918 |
Reef | -1.804 |
oranges | -1.745 |
Ib | -1.734 |
Mercury | -1.679 |
Token | kil |
Token ID | 8769 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
avage | +15.396 |
Gat | +13.699 |
leck | +13.284 |
GBT | +12.985 |
Discover | +12.863 |
Neg logit contributions | |
Nept | -15.995 |
Reef | -14.770 |
Skydragon | -14.411 |
Norn | -14.394 |
oranges | -14.271 |
Token | ow |
Token ID | 322 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
avage | +3.865 |
leck | +3.296 |
ghai | +3.168 |
anski | +3.065 |
Gat | +3.033 |
Neg logit contributions | |
Nept | -4.169 |
Reef | -3.975 |
oranges | -3.864 |
Ib | -3.812 |
Norn | -3.759 |
Token | att |
Token ID | 1078 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
avage | +8.426 |
leck | +6.861 |
ghai | +6.739 |
anski | +6.515 |
Gat | +6.483 |
Neg logit contributions | |
Nept | -9.605 |
Reef | -8.969 |
oranges | -8.760 |
Norn | -8.666 |
Ib | -8.524 |
Token | - |
Token ID | 12 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
avage | +5.346 |
leck | +4.538 |
ghai | +4.363 |
Gat | +4.287 |
anski | +4.193 |
Neg logit contributions | |
Nept | -5.581 |
Reef | -5.309 |
oranges | -5.132 |
Ib | -5.077 |
Mercury | -4.999 |
Token | hour |
Token ID | 9769 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
avage | +4.815 |
leck | +4.006 |
ghai | +3.874 |
Gat | +3.692 |
anski | +3.629 |
Neg logit contributions | |
Nept | -6.440 |
Reef | -6.121 |
oranges | -5.935 |
adul | -5.803 |
Ib | -5.793 |
Token | of |
Token ID | 286 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
avage | +4.796 |
leck | +4.053 |
ghai | +3.966 |
anski | +3.822 |
Gat | +3.806 |
Neg logit contributions | |
Nept | -4.373 |
Reef | -4.141 |
oranges | -4.003 |
Ib | -3.959 |
Norn | -3.923 |
Token | the |
Token ID | 262 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
avage | +13.891 |
Gat | +11.838 |
leck | +11.672 |
Discover | +11.471 |
anski | +11.326 |
Neg logit contributions | |
Nept | -13.163 |
Reef | -13.102 |
Norn | -12.566 |
oranges | -12.274 |
Skydragon | -11.908 |
Token | firm |
Token ID | 4081 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
avage | +9.001 |
leck | +7.844 |
Gat | +7.596 |
anski | +7.588 |
ghai | +7.550 |
Neg logit contributions | |
Nept | -6.328 |
Reef | -6.043 |
oranges | -5.795 |
Norn | -5.695 |
Ib | -5.651 |
Token | � |
Token ID | 447 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
avage | +8.875 |
leck | +7.662 |
anski | +7.315 |
ghai | +7.294 |
sth | +7.163 |
Neg logit contributions | |
Nept | -8.497 |
Reef | -8.236 |
oranges | -7.890 |
Norn | -7.777 |
Ib | -7.663 |
Token | � |
Token ID | 247 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
Nept | +0.245 |
Reef | +0.237 |
oranges | +0.231 |
Ib | +0.229 |
Mercury | +0.225 |
Neg logit contributions | |
avage | -0.190 |
leck | -0.160 |
ghai | -0.151 |
anski | -0.147 |
Gat | -0.146 |
Token | s |
Token ID | 82 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
avage | +6.995 |
leck | +6.061 |
ghai | +5.906 |
anski | +5.777 |
Gat | +5.733 |
Neg logit contributions | |
Nept | -5.242 |
Reef | -4.983 |
oranges | -4.753 |
Ib | -4.741 |
Norn | -4.655 |
Token | revenues |
Token ID | 13089 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
avage | +17.292 |
Gat | +14.933 |
anski | +14.652 |
leck | +14.564 |
Discover | +14.403 |
Neg logit contributions | |
Nept | -14.009 |
Norn | -13.876 |
Reef | -13.634 |
oranges | -13.175 |
Skydragon | -12.718 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
avage | +8.303 |
leck | +6.885 |
ghai | +6.746 |
anski | +6.673 |
Gat | +6.538 |
Neg logit contributions | |
Nept | -8.509 |
Reef | -8.108 |
oranges | -7.894 |
Ib | -7.717 |
Norn | -7.635 |
Token | Richard |
Token ID | 6219 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
avage | +2.609 |
leck | +2.263 |
ghai | +2.186 |
Gat | +2.144 |
anski | +2.123 |
Neg logit contributions | |
Nept | -2.112 |
Reef | -1.996 |
oranges | -1.963 |
Ib | -1.920 |
adul | -1.872 |
Token | Marin |
Token ID | 36384 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
avage | +2.722 |
leck | +2.367 |
ghai | +2.285 |
Gat | +2.227 |
anski | +2.226 |
Neg logit contributions | |
Nept | -2.156 |
Reef | -2.035 |
oranges | -1.987 |
Ib | -1.959 |
adul | -1.903 |
Token | , |
Token ID | 11 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
avage | +6.959 |
leck | +5.980 |
anski | +5.592 |
ghai | +5.579 |
Gat | +5.566 |
Neg logit contributions | |
Nept | -6.874 |
Reef | -6.501 |
oranges | -6.381 |
Ib | -6.303 |
Norn | -6.214 |
Token | 4 |
Token ID | 19 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
avage | +5.353 |
leck | +4.618 |
ghai | +4.412 |
anski | +4.336 |
Gat | +4.267 |
Neg logit contributions | |
Nept | -5.067 |
Reef | -4.757 |
oranges | -4.734 |
Ib | -4.562 |
Mercury | -4.511 |
Token | { |
Token ID | 1391 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Nept | +0.130 |
Reef | +0.124 |
oranges | +0.121 |
Ib | +0.121 |
Mercury | +0.118 |
Neg logit contributions | |
avage | -0.114 |
leck | -0.096 |
ghai | -0.092 |
anski | -0.089 |
Gat | -0.089 |
Token | ( |
Token ID | 7 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Nept | +1.918 |
Reef | +1.833 |
Ib | +1.774 |
oranges | +1.746 |
Mercury | +1.720 |
Neg logit contributions | |
avage | -2.256 |
leck | -1.968 |
ghai | -1.891 |
anski | -1.836 |
Gat | -1.820 |
Token | 3 |
Token ID | 18 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
Nept | +2.144 |
Reef | +2.031 |
Ib | +1.968 |
oranges | +1.931 |
Mercury | +1.910 |
Neg logit contributions | |
avage | -2.874 |
leck | -2.529 |
ghai | -2.460 |
anski | -2.385 |
Gat | -2.342 |
Token | s |
Token ID | 82 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Nept | +0.296 |
Reef | +0.278 |
oranges | +0.270 |
Ib | +0.267 |
Mercury | +0.257 |
Neg logit contributions | |
avage | -0.475 |
leck | -0.420 |
ghai | -0.407 |
anski | -0.395 |
Gat | -0.395 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Nept | +1.369 |
Reef | +1.302 |
oranges | +1.257 |
Ib | +1.254 |
Mercury | +1.221 |
Neg logit contributions | |
avage | -1.638 |
leck | -1.421 |
ghai | -1.372 |
anski | -1.336 |
Gat | -1.327 |
Token | 36 |
Token ID | 4570 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
avage | +16.260 |
Gat | +13.962 |
ghai | +13.416 |
Discover | +13.385 |
leck | +13.071 |
Neg logit contributions | |
Nept | -15.524 |
Skydragon | -15.341 |
oranges | -15.046 |
Reef | -14.748 |
adul | -13.973 |
Token | . |
Token ID | 13 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
avage | +1.037 |
leck | +0.886 |
ghai | +0.857 |
Gat | +0.836 |
anski | +0.828 |
Neg logit contributions | |
Nept | -0.995 |
Reef | -0.942 |
oranges | -0.927 |
Ib | -0.907 |
adul | -0.888 |
Token | f |
Token ID | 277 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
avage | +4.464 |
leck | +3.885 |
ghai | +3.731 |
Gat | +3.727 |
anski | +3.634 |
Neg logit contributions | |
Nept | -3.725 |
Reef | -3.520 |
oranges | -3.476 |
Ib | -3.355 |
Mercury | -3.330 |
Token | 5 |
Token ID | 20 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
avage | +0.810 |
leck | +0.708 |
ghai | +0.686 |
anski | +0.667 |
Gat | +0.666 |
Neg logit contributions | |
Nept | -0.591 |
Reef | -0.558 |
oranges | -0.538 |
Ib | -0.538 |
Mercury | -0.519 |
Token | { |
Token ID | 1391 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
avage | +2.978 |
leck | +2.479 |
ghai | +2.377 |
Gat | +2.305 |
anski | +2.295 |
Neg logit contributions | |
Nept | -3.755 |
Reef | -3.598 |
oranges | -3.517 |
Ib | -3.466 |
adul | -3.414 |
Token | G |
Token ID | 38 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
avage | +5.598 |
Gat | +4.597 |
leck | +4.584 |
GBT | +4.572 |
ghai | +4.361 |
Neg logit contributions | |
Nept | -8.565 |
oranges | -8.243 |
Reef | -8.009 |
sax | -7.874 |
adul | -7.820 |
Token | ED |
Token ID | 1961 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
avage | +1.263 |
leck | +1.098 |
ghai | +1.056 |
Gat | +1.032 |
anski | +1.029 |
Neg logit contributions | |
Nept | -1.008 |
Reef | -0.949 |
oranges | -0.928 |
Ib | -0.915 |
adul | -0.890 |
Token | NET |
Token ID | 30502 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
avage | +8.403 |
leck | +6.978 |
Gat | +6.855 |
Discover | +6.695 |
GBT | +6.579 |
Neg logit contributions | |
Nept | -8.100 |
oranges | -7.817 |
Reef | -7.695 |
adul | -7.470 |
Ib | -7.389 |
Token | CALL |
Token ID | 42815 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
avage | +4.923 |
Gat | +3.925 |
leck | +3.882 |
Discover | +3.880 |
ghai | +3.652 |
Neg logit contributions | |
Nept | -7.693 |
oranges | -7.611 |
Reef | -7.219 |
adul | -7.149 |
sax | -7.119 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
avage | +2.847 |
leck | +2.277 |
ghai | +2.134 |
Gat | +2.078 |
anski | +2.043 |
Neg logit contributions | |
Nept | -4.812 |
Reef | -4.601 |
oranges | -4.540 |
Ib | -4.475 |
Mercury | -4.403 |
Token | : |
Token ID | 25 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Nept | +1.089 |
Reef | +1.029 |
Ib | +0.992 |
oranges | +0.982 |
Mercury | +0.962 |
Neg logit contributions | |
avage | -1.461 |
leck | -1.283 |
ghai | -1.240 |
anski | -1.208 |
Gat | -1.187 |
Token | 05 |
Token ID | 8870 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
avage | +14.282 |
Gat | +12.334 |
Discover | +12.017 |
leck | +11.811 |
GBT | +11.637 |
Neg logit contributions | |
Nept | -17.021 |
oranges | -16.423 |
sax | -16.122 |
Reef | -15.953 |
adul | -15.531 |
Token | 50 |
Token ID | 1120 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
avage | +8.216 |
leck | +6.631 |
Gat | +6.523 |
sth | +6.447 |
TE | +6.319 |
Neg logit contributions | |
Nept | -12.039 |
oranges | -11.649 |
Reef | -11.578 |
adul | -11.290 |
Ib | -11.183 |
Token | z |
Token ID | 89 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Nept | +2.789 |
Reef | +2.663 |
oranges | +2.602 |
Ib | +2.593 |
Mercury | +2.524 |
Neg logit contributions | |
avage | -2.592 |
leck | -2.187 |
ghai | -2.109 |
Gat | -2.025 |
anski | -2.009 |
Token | VOL |
Token ID | 38570 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
avage | +3.560 |
leck | +3.073 |
ghai | +2.928 |
Gat | +2.913 |
anski | +2.873 |
Neg logit contributions | |
Nept | -3.136 |
Reef | -2.970 |
oranges | -2.919 |
Ib | -2.853 |
adul | -2.794 |
Token | UN |
Token ID | 4944 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Nept | +1.033 |
Reef | +0.987 |
Ib | +0.958 |
oranges | +0.949 |
Mercury | +0.930 |
Neg logit contributions | |
avage | -1.037 |
leck | -0.887 |
ghai | -0.863 |
anski | -0.825 |
Gat | -0.812 |
Token | ens |
Token ID | 641 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
avage | +0.452 |
leck | +0.394 |
ghai | +0.382 |
anski | +0.371 |
Gat | +0.370 |
Neg logit contributions | |
Nept | -0.350 |
Reef | -0.331 |
oranges | -0.321 |
Ib | -0.319 |
Mercury | -0.309 |
Token | haw |
Token ID | 26615 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
avage | +0.948 |
leck | +0.832 |
ghai | +0.807 |
anski | +0.785 |
Gat | +0.781 |
Neg logit contributions | |
Nept | -0.703 |
Reef | -0.666 |
oranges | -0.645 |
Ib | -0.639 |
Mercury | -0.619 |
Token | [ |
Token ID | 685 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
avage | +0.259 |
leck | +0.225 |
ghai | +0.218 |
anski | +0.211 |
Gat | +0.210 |
Neg logit contributions | |
Nept | -0.208 |
Reef | -0.197 |
oranges | -0.190 |
Ib | -0.190 |
Mercury | -0.184 |
Token | R |
Token ID | 49 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
avage | +4.102 |
leck | +3.569 |
ghai | +3.410 |
Gat | +3.358 |
anski | +3.340 |
Neg logit contributions | |
Nept | -3.411 |
Reef | -3.212 |
oranges | -3.142 |
Ib | -3.085 |
adul | -3.027 |
Token | ab |
Token ID | 397 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
avage | +3.995 |
leck | +3.490 |
ghai | +3.380 |
anski | +3.305 |
Gat | +3.288 |
Neg logit contributions | |
Nept | -2.591 |
Reef | -2.414 |
oranges | -2.312 |
Ib | -2.298 |
adul | -2.230 |
Token | ob |
Token ID | 672 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
avage | +2.812 |
leck | +2.528 |
ghai | +2.456 |
anski | +2.412 |
Gat | +2.401 |
Neg logit contributions | |
Nept | -1.163 |
Reef | -1.057 |
oranges | -1.011 |
Ib | -0.997 |
Mercury | -0.957 |
Token | ank |
Token ID | 962 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
avage | +13.333 |
leck | +11.916 |
anski | +11.325 |
anking | +10.722 |
ansky | +10.249 |
Neg logit contributions | |
Nept | -21.397 |
Skydragon | -20.448 |
thous | -20.227 |
oranges | -19.825 |
Reef | -19.691 |
Token | team |
Token ID | 1074 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
avage | +4.580 |
leck | +4.008 |
ghai | +3.839 |
Gat | +3.807 |
anski | +3.741 |
Neg logit contributions | |
Nept | -3.692 |
Reef | -3.504 |
oranges | -3.392 |
Ib | -3.349 |
adul | -3.259 |
Token | mate |
Token ID | 16133 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
avage | +7.072 |
leck | +6.269 |
Gat | +5.924 |
ghai | +5.916 |
anski | +5.772 |
Neg logit contributions | |
Nept | -5.530 |
Reef | -5.244 |
oranges | -5.020 |
Ib | -4.923 |
adul | -4.809 |
Token | ] |
Token ID | 60 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
Nept | +0.409 |
Reef | +0.386 |
Ib | +0.374 |
oranges | +0.371 |
Mercury | +0.361 |
Neg logit contributions | |
avage | -0.605 |
leck | -0.531 |
ghai | -0.516 |
anski | -0.504 |
Gat | -0.495 |
Token | held |
Token ID | 2714 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
avage | +0.890 |
leck | +0.774 |
ghai | +0.749 |
anski | +0.728 |
Gat | +0.724 |
Neg logit contributions | |
Nept | -0.707 |
Reef | -0.668 |
oranges | -0.648 |
Ib | -0.645 |
Mercury | -0.625 |
Token | G |
Token ID | 38 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
avage | +5.364 |
leck | +4.403 |
Gat | +4.390 |
GBT | +4.343 |
ghai | +4.198 |
Neg logit contributions | |
Nept | -7.983 |
oranges | -7.673 |
Reef | -7.479 |
sax | -7.318 |
adul | -7.287 |
Token | ED |
Token ID | 1961 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
avage | +0.352 |
leck | +0.308 |
ghai | +0.297 |
anski | +0.289 |
Gat | +0.289 |
Neg logit contributions | |
Nept | -0.270 |
Reef | -0.254 |
oranges | -0.247 |
Ib | -0.245 |
Mercury | -0.237 |
Token | NET |
Token ID | 30502 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
avage | +7.942 |
leck | +6.636 |
Gat | +6.478 |
Discover | +6.319 |
ghai | +6.293 |
Neg logit contributions | |
Nept | -7.434 |
oranges | -7.137 |
Reef | -7.031 |
adul | -6.790 |
Ib | -6.727 |
Token | CALL |
Token ID | 42815 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
avage | +4.776 |
Gat | +3.812 |
leck | +3.774 |
Discover | +3.757 |
ghai | +3.573 |
Neg logit contributions | |
Nept | -7.331 |
oranges | -7.237 |
Reef | -6.879 |
adul | -6.799 |
sax | -6.748 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
avage | +2.716 |
leck | +2.180 |
ghai | +2.051 |
Gat | +1.991 |
anski | +1.963 |
Neg logit contributions | |
Nept | -4.482 |
Reef | -4.286 |
oranges | -4.227 |
Ib | -4.168 |
Mercury | -4.099 |
Token | : |
Token ID | 25 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Nept | +0.983 |
Reef | +0.929 |
Ib | +0.895 |
oranges | +0.889 |
Mercury | +0.868 |
Neg logit contributions | |
avage | -1.299 |
leck | -1.138 |
ghai | -1.099 |
anski | -1.070 |
Gat | -1.055 |
Token | 05 |
Token ID | 8870 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
avage | +14.390 |
Gat | +12.545 |
Discover | +12.177 |
leck | +12.042 |
GBT | +11.726 |
Neg logit contributions | |
Nept | -16.555 |
oranges | -16.077 |
sax | -15.840 |
Reef | -15.581 |
adul | -15.145 |
Token | 43 |
Token ID | 3559 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
avage | +7.061 |
leck | +5.940 |
sth | +5.670 |
Gat | +5.640 |
ghai | +5.619 |
Neg logit contributions | |
Nept | -7.340 |
oranges | -6.942 |
Reef | -6.941 |
Ib | -6.719 |
adul | -6.696 |
Token | z |
Token ID | 89 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Nept | +5.285 |
Reef | +5.033 |
oranges | +4.944 |
Ib | +4.889 |
Mercury | +4.766 |
Neg logit contributions | |
avage | -5.575 |
leck | -4.700 |
ghai | -4.579 |
GBT | -4.477 |
Gat | -4.415 |
Token | ST |
Token ID | 3563 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
avage | +2.338 |
leck | +2.017 |
ghai | +1.931 |
Gat | +1.892 |
anski | +1.883 |
Neg logit contributions | |
Nept | -2.114 |
Reef | -2.005 |
oranges | -1.959 |
Ib | -1.931 |
adul | -1.881 |
Token | OW |
Token ID | 3913 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Nept | +4.394 |
Reef | +4.287 |
Ib | +4.141 |
oranges | +4.090 |
Norn | +3.977 |
Neg logit contributions | |
avage | -4.173 |
leck | -3.548 |
ghai | -3.540 |
Gat | -3.304 |
anski | -3.287 |
Token | G |
Token ID | 38 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
avage | +4.118 |
leck | +3.446 |
Gat | +3.334 |
ghai | +3.295 |
GBT | +3.266 |
Neg logit contributions | |
Nept | -5.279 |
oranges | -4.998 |
Reef | -4.973 |
Ib | -4.816 |
adul | -4.790 |
Token | ED |
Token ID | 1961 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
avage | +0.223 |
leck | +0.195 |
ghai | +0.189 |
anski | +0.184 |
Gat | +0.183 |
Neg logit contributions | |
Nept | -0.167 |
Reef | -0.158 |
oranges | -0.153 |
Ib | -0.152 |
Mercury | -0.147 |
Token | NET |
Token ID | 30502 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
avage | +4.377 |
leck | +3.754 |
ghai | +3.582 |
Gat | +3.567 |
anski | +3.499 |
Neg logit contributions | |
Nept | -3.839 |
Reef | -3.642 |
oranges | -3.590 |
Ib | -3.495 |
adul | -3.434 |
Token | CALL |
Token ID | 42815 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
avage | +3.868 |
leck | +3.177 |
ghai | +3.017 |
Gat | +2.982 |
anski | +2.896 |
Neg logit contributions | |
Nept | -5.160 |
oranges | -4.908 |
Reef | -4.901 |
Ib | -4.748 |
adul | -4.709 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
avage | +1.834 |
leck | +1.521 |
ghai | +1.447 |
Gat | +1.395 |
anski | +1.393 |
Neg logit contributions | |
Nept | -2.486 |
Reef | -2.379 |
oranges | -2.329 |
Ib | -2.311 |
Mercury | -2.261 |
Token | : |
Token ID | 25 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Nept | +1.942 |
Reef | +1.817 |
Ib | +1.770 |
oranges | +1.746 |
Mercury | +1.699 |
Neg logit contributions | |
avage | -2.774 |
leck | -2.443 |
ghai | -2.377 |
anski | -2.312 |
Gat | -2.263 |
Token | 05 |
Token ID | 8870 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
avage | +14.772 |
Gat | +13.053 |
Discover | +12.715 |
leck | +12.414 |
GBT | +12.207 |
Neg logit contributions | |
Nept | -16.019 |
oranges | -15.677 |
sax | -15.394 |
Reef | -15.128 |
adul | -14.768 |
Token | 42 |
Token ID | 3682 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
avage | +7.635 |
leck | +6.311 |
sth | +6.096 |
Gat | +6.031 |
ghai | +5.908 |
Neg logit contributions | |
Nept | -8.898 |
oranges | -8.470 |
Reef | -8.466 |
adul | -8.184 |
Ib | -8.139 |
Token | z |
Token ID | 89 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Nept | +5.973 |
Reef | +5.644 |
oranges | +5.552 |
Ib | +5.516 |
Mercury | +5.372 |
Neg logit contributions | |
avage | -6.505 |
leck | -5.503 |
ghai | -5.358 |
GBT | -5.278 |
Gat | -5.144 |
Token | SH |
Token ID | 6006 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
avage | +1.924 |
leck | +1.658 |
ghai | +1.590 |
Gat | +1.553 |
anski | +1.549 |
Neg logit contributions | |
Nept | -1.745 |
Reef | -1.657 |
oranges | -1.616 |
Ib | -1.597 |
Mercury | -1.554 |
Token | AM |
Token ID | 2390 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
avage | +2.207 |
leck | +1.917 |
ghai | +1.844 |
Gat | +1.801 |
anski | +1.799 |
Neg logit contributions | |
Nept | -1.770 |
Reef | -1.664 |
oranges | -1.625 |
Ib | -1.605 |
Mercury | -1.561 |
Token | gains |
Token ID | 8810 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
avage | +5.783 |
leck | +4.970 |
ghai | +4.792 |
Gat | +4.732 |
anski | +4.667 |
Neg logit contributions | |
Nept | -5.146 |
Reef | -4.854 |
Ib | -4.673 |
Norn | -4.613 |
oranges | -4.586 |
Token | , |
Token ID | 11 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
Nept | +2.422 |
Reef | +2.305 |
oranges | +2.214 |
Ib | +2.208 |
Mercury | +2.154 |
Neg logit contributions | |
avage | -3.239 |
leck | -2.822 |
ghai | -2.728 |
anski | -2.667 |
Gat | -2.620 |
Token | � |
Token ID | 447 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
avage | +6.621 |
leck | +5.669 |
Gat | +5.395 |
ghai | +5.364 |
anski | +5.351 |
Neg logit contributions | |
Nept | -6.330 |
Reef | -6.000 |
oranges | -5.883 |
Ib | -5.802 |
adul | -5.731 |
Token | � |
Token ID | 251 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Nept | +2.222 |
Reef | +2.167 |
Ib | +2.103 |
oranges | +2.098 |
Mercury | +2.038 |
Neg logit contributions | |
avage | -1.980 |
leck | -1.675 |
ghai | -1.608 |
anski | -1.581 |
Gat | -1.534 |
Token | says |
Token ID | 1139 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
avage | +5.487 |
leck | +4.682 |
ghai | +4.404 |
Gat | +4.399 |
anski | +4.383 |
Neg logit contributions | |
Nept | -5.943 |
Reef | -5.670 |
oranges | -5.524 |
Ib | -5.478 |
adul | -5.425 |
Token | Br |
Token ID | 1709 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
avage | +8.581 |
leck | +7.546 |
Gat | +7.297 |
anski | +7.182 |
ghai | +7.102 |
Neg logit contributions | |
Nept | -5.848 |
Reef | -5.466 |
oranges | -5.411 |
adul | -5.276 |
Ib | -5.250 |
Token | unt |
Token ID | 2797 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
avage | +12.366 |
leck | +9.373 |
anski | +8.268 |
ansky | +8.184 |
anking | +8.082 |
Neg logit contributions | |
Nept | -21.988 |
thous | -21.379 |
Reef | -21.267 |
Skydragon | -20.748 |
Ib | -20.476 |
Token | . |
Token ID | 13 |
Feature activation | -6.86e-03 |
Pos logit contributions | |
avage | +3.488 |
leck | +2.947 |
ghai | +2.840 |
anski | +2.782 |
Gat | +2.767 |
Neg logit contributions | |
Nept | -3.365 |
Reef | -3.201 |
oranges | -3.122 |
Ib | -3.077 |
adul | -3.016 |
Token |
|
Token ID | 198 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
avage | +0.091 |
leck | +0.079 |
ghai | +0.076 |
anski | +0.074 |
Gat | +0.073 |
Neg logit contributions | |
Nept | -0.076 |
Reef | -0.072 |
Ib | -0.069 |
oranges | -0.068 |
Mercury | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
avage | +2.983 |
leck | +2.480 |
ghai | +2.398 |
Gat | +2.390 |
sth | +2.331 |
Neg logit contributions | |
Nept | -3.192 |
oranges | -2.993 |
Reef | -2.981 |
Ib | -2.878 |
sax | -2.842 |
Token | The |
Token ID | 464 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
avage | +1.619 |
leck | +1.403 |
ghai | +1.353 |
anski | +1.314 |
Gat | +1.309 |
Neg logit contributions | |
Nept | -1.399 |
Reef | -1.326 |
oranges | -1.286 |
Ib | -1.280 |
Mercury | -1.243 |
Token | � |
Token ID | 447 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
avage | +3.924 |
leck | +3.405 |
ghai | +3.266 |
Gat | +3.206 |
anski | +3.185 |
Neg logit contributions | |
Nept | -3.418 |
Reef | -3.229 |
oranges | -3.132 |
Ib | -3.114 |
Mercury | -3.033 |
Token | � |
Token ID | 247 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Nept | +3.411 |
Reef | +3.373 |
oranges | +3.214 |
Ib | +3.193 |
Mercury | +3.136 |
Neg logit contributions | |
avage | -3.196 |
leck | -2.741 |
ghai | -2.596 |
anski | -2.561 |
Gat | -2.529 |
Token | s |
Token ID | 82 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
Nept | +2.960 |
Reef | +2.784 |
oranges | +2.647 |
Ib | +2.608 |
Mercury | +2.574 |
Neg logit contributions | |
avage | -5.709 |
leck | -5.119 |
ghai | -4.932 |
anski | -4.890 |
Gat | -4.825 |
Token | Liberals |
Token ID | 20162 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
avage | +8.121 |
leck | +6.925 |
Gat | +6.881 |
anski | +6.711 |
ghai | +6.611 |
Neg logit contributions | |
Nept | -6.337 |
Reef | -6.093 |
oranges | -5.934 |
Ib | -5.839 |
adul | -5.755 |
Token | approved |
Token ID | 6325 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
avage | +7.012 |
leck | +6.031 |
Gat | +5.713 |
ghai | +5.708 |
anski | +5.661 |
Neg logit contributions | |
Nept | -6.072 |
Reef | -5.770 |
Ib | -5.598 |
oranges | -5.579 |
Mercury | -5.449 |
Token | last |
Token ID | 938 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
avage | +9.692 |
leck | +8.275 |
Gat | +8.108 |
ghai | +8.097 |
anski | +7.734 |
Neg logit contributions | |
Nept | -8.680 |
Reef | -8.292 |
oranges | -8.165 |
Ib | -7.974 |
Norn | -7.953 |
Token | year |
Token ID | 614 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
avage | +11.604 |
Gat | +11.575 |
leck | +10.326 |
sth | +9.872 |
Discover | +9.495 |
Neg logit contributions | |
Nept | -17.876 |
Reef | -17.223 |
oranges | -17.034 |
Skydragon | -16.915 |
Û | -16.659 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
avage | +9.919 |
leck | +8.430 |
Gat | +8.095 |
ghai | +8.087 |
anski | +7.813 |
Neg logit contributions | |
Nept | -10.732 |
Reef | -10.150 |
oranges | -10.099 |
Ib | -9.844 |
Norn | -9.748 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
avage | +3.305 |
leck | +2.850 |
ghai | +2.737 |
Gat | +2.720 |
anski | +2.674 |
Neg logit contributions | |
Nept | -2.789 |
Reef | -2.636 |
oranges | -2.626 |
Ib | -2.544 |
adul | -2.500 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
avage | +1.229 |
leck | +1.044 |
ghai | +1.009 |
Gat | +0.992 |
anski | +0.976 |
Neg logit contributions | |
Nept | -1.192 |
Reef | -1.121 |
oranges | -1.108 |
Ib | -1.083 |
adul | -1.060 |
Token | In |
Token ID | 818 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
avage | +2.273 |
leck | +1.983 |
ghai | +1.913 |
anski | +1.863 |
Gat | +1.858 |
Neg logit contributions | |
Nept | -1.770 |
Reef | -1.672 |
oranges | -1.622 |
Ib | -1.610 |
Mercury | -1.561 |
Token | connected |
Token ID | 15236 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
avage | +8.949 |
leck | +7.478 |
sth | +7.351 |
ghai | +7.296 |
anski | +7.287 |
Neg logit contributions | |
Nept | -7.751 |
Reef | -7.276 |
oranges | -7.160 |
Ib | -6.968 |
sax | -6.851 |
Token | " |
Token ID | 1 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
avage | +4.217 |
leck | +3.664 |
ghai | +3.553 |
Gat | +3.477 |
anski | +3.470 |
Neg logit contributions | |
Nept | -3.147 |
Reef | -2.955 |
oranges | -2.867 |
Ib | -2.839 |
adul | -2.750 |
Token | in |
Token ID | 287 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
avage | +9.771 |
leck | +8.254 |
ghai | +8.004 |
Gat | +7.997 |
Discover | +7.964 |
Neg logit contributions | |
Nept | -9.267 |
Reef | -8.724 |
oranges | -8.662 |
Ib | -8.443 |
sax | -8.305 |
Token | the |
Token ID | 262 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
avage | +12.130 |
Gat | +10.602 |
Discover | +10.366 |
leck | +9.976 |
anski | +9.936 |
Neg logit contributions | |
Nept | -10.736 |
oranges | -10.025 |
Reef | -9.868 |
sax | -9.670 |
adul | -9.623 |
Token | list |
Token ID | 1351 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
avage | +15.202 |
Gat | +13.660 |
Discover | +13.584 |
anski | +13.004 |
leck | +12.941 |
Neg logit contributions | |
Nept | -11.763 |
oranges | -10.892 |
Reef | -10.673 |
sax | -10.467 |
Norn | -10.350 |
Token | of |
Token ID | 286 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
avage | +10.891 |
leck | +9.020 |
ghai | +8.827 |
Gat | +8.529 |
anski | +8.516 |
Neg logit contributions | |
Nept | -12.159 |
Reef | -11.456 |
oranges | -11.085 |
Ib | -10.991 |
Mercury | -10.847 |
Token | network |
Token ID | 3127 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
avage | +16.100 |
Gat | +14.730 |
Discover | +14.559 |
ghai | +13.791 |
sth | +13.608 |
Neg logit contributions | |
Nept | -13.952 |
Reef | -13.011 |
oranges | -12.993 |
Ib | -12.582 |
sax | -12.353 |
Token | interfaces |
Token ID | 20314 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
avage | +8.932 |
leck | +7.360 |
ghai | +7.300 |
Discover | +7.233 |
Gat | +7.218 |
Neg logit contributions | |
Nept | -9.589 |
Reef | -9.155 |
oranges | -8.746 |
Norn | -8.717 |
Ib | -8.697 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
avage | +5.822 |
leck | +4.930 |
ghai | +4.775 |
Gat | +4.701 |
anski | +4.688 |
Neg logit contributions | |
Nept | -5.841 |
Reef | -5.556 |
oranges | -5.389 |
Ib | -5.331 |
Norn | -5.183 |
Token | Config |
Token ID | 17056 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
avage | +1.759 |
leck | +1.523 |
ghai | +1.469 |
anski | +1.427 |
Gat | +1.424 |
Neg logit contributions | |
Nept | -1.516 |
Reef | -1.436 |
oranges | -1.396 |
Ib | -1.386 |
Mercury | -1.346 |
Token | ure |
Token ID | 495 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
Nept | +0.595 |
Reef | +0.568 |
oranges | +0.549 |
Ib | +0.547 |
Mercury | +0.532 |
Neg logit contributions | |
avage | -0.708 |
leck | -0.620 |
ghai | -0.598 |
anski | -0.576 |
Gat | -0.576 |
Token | Colorado |
Token ID | 7492 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Nept | +3.049 |
Reef | +2.960 |
Ib | +2.862 |
oranges | +2.826 |
Mercury | +2.777 |
Neg logit contributions | |
avage | -3.218 |
leck | -2.776 |
ghai | -2.706 |
anski | -2.587 |
GBT | -2.504 |
Token | decide |
Token ID | 5409 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
avage | +3.296 |
leck | +2.816 |
ghai | +2.707 |
anski | +2.642 |
Gat | +2.631 |
Neg logit contributions | |
Nept | -3.167 |
Reef | -3.005 |
oranges | -2.906 |
Ib | -2.893 |
Mercury | -2.822 |
Token | they |
Token ID | 484 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
avage | +5.877 |
leck | +5.042 |
ghai | +4.820 |
Gat | +4.765 |
anski | +4.739 |
Neg logit contributions | |
Nept | -5.425 |
Reef | -5.134 |
oranges | -5.001 |
Ib | -4.947 |
Mercury | -4.850 |
Token | want |
Token ID | 765 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
avage | +5.231 |
leck | +4.286 |
ghai | +4.188 |
anski | +4.111 |
Gat | +4.050 |
Neg logit contributions | |
Nept | -6.272 |
Reef | -6.031 |
Ib | -5.786 |
oranges | -5.767 |
Norn | -5.680 |
Token | to |
Token ID | 284 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
avage | +9.841 |
leck | +8.481 |
Gat | +8.222 |
sth | +8.015 |
ghai | +7.907 |
Neg logit contributions | |
Nept | -10.631 |
Reef | -9.628 |
Norn | -9.539 |
oranges | -9.490 |
Mercury | -9.440 |
Token | go |
Token ID | 467 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
avage | +6.203 |
leck | +5.163 |
ghai | +5.089 |
anski | +5.065 |
Gat | +4.999 |
Neg logit contributions | |
Nept | -6.154 |
Reef | -5.767 |
oranges | -5.642 |
Ib | -5.568 |
Norn | -5.532 |
Token | down |
Token ID | 866 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
avage | +15.998 |
Gat | +13.850 |
anski | +13.786 |
Discover | +13.416 |
leck | +13.341 |
Neg logit contributions | |
Nept | -14.994 |
Norn | -13.610 |
Skydragon | -13.569 |
oranges | -13.070 |
Reef | -12.772 |
Token | that |
Token ID | 326 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
avage | +1.570 |
leck | +1.360 |
ghai | +1.311 |
anski | +1.275 |
Gat | +1.271 |
Neg logit contributions | |
Nept | -1.349 |
Reef | -1.277 |
oranges | -1.239 |
Ib | -1.232 |
Mercury | -1.197 |
Token | road |
Token ID | 2975 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
avage | +4.808 |
leck | +4.203 |
ghai | +4.009 |
Gat | +3.970 |
anski | +3.936 |
Neg logit contributions | |
Nept | -3.871 |
Reef | -3.606 |
oranges | -3.487 |
Ib | -3.474 |
Norn | -3.392 |
Token | , |
Token ID | 11 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
avage | +7.269 |
leck | +6.267 |
ghai | +6.059 |
Gat | +5.982 |
anski | +5.970 |
Neg logit contributions | |
Nept | -6.696 |
Reef | -6.365 |
oranges | -6.192 |
Ib | -6.060 |
Mercury | -5.955 |
Token | that |
Token ID | 326 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
avage | +6.637 |
leck | +5.746 |
Gat | +5.450 |
ghai | +5.432 |
anski | +5.405 |
Neg logit contributions | |
Nept | -6.074 |
Reef | -5.666 |
oranges | -5.504 |
Ib | -5.440 |
Mercury | -5.340 |
Token | point |
Token ID | 966 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Nept | +1.428 |
Reef | +1.295 |
oranges | +1.246 |
Ib | +1.240 |
Mercury | +1.209 |
Neg logit contributions | |
avage | -3.125 |
leck | -2.787 |
ghai | -2.731 |
anski | -2.677 |
Gat | -2.604 |
Token | , |
Token ID | 11 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
avage | +2.219 |
leck | +1.923 |
ghai | +1.851 |
Gat | +1.800 |
anski | +1.797 |
Neg logit contributions | |
Nept | -1.934 |
Reef | -1.831 |
oranges | -1.779 |
Ib | -1.768 |
Mercury | -1.713 |
Token | the |
Token ID | 262 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
avage | +5.976 |
leck | +5.292 |
Gat | +4.993 |
ghai | +4.982 |
anski | +4.849 |
Neg logit contributions | |
Nept | -5.273 |
Reef | -4.970 |
oranges | -4.862 |
Ib | -4.825 |
Norn | -4.707 |
Token | government |
Token ID | 1230 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
avage | +5.269 |
leck | +4.605 |
ghai | +4.381 |
Gat | +4.377 |
anski | +4.293 |
Neg logit contributions | |
Nept | -4.387 |
Reef | -4.121 |
oranges | -3.999 |
Ib | -3.992 |
Norn | -3.839 |
Token | would |
Token ID | 561 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
avage | +7.360 |
leck | +6.459 |
Gat | +6.211 |
ghai | +6.099 |
sth | +6.057 |
Neg logit contributions | |
Nept | -6.150 |
Reef | -5.771 |
Ib | -5.520 |
oranges | -5.439 |
Norn | -5.333 |
Token | only |
Token ID | 691 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
avage | +9.756 |
anski | +7.862 |
Discover | +7.830 |
sth | +7.753 |
Gat | +7.708 |
Neg logit contributions | |
Nept | -11.978 |
Reef | -11.226 |
Ib | -10.755 |
Skydragon | -10.610 |
Norn | -10.600 |
Token | be |
Token ID | 307 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
avage | +13.173 |
Discover | +11.313 |
anski | +10.910 |
Gat | +10.626 |
sth | +10.512 |
Neg logit contributions | |
Nept | -17.420 |
Reef | -16.075 |
Norn | -15.721 |
Û | -15.653 |
Skydragon | -15.269 |
Token | able |
Token ID | 1498 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
avage | +11.913 |
leck | +10.025 |
Gat | +10.022 |
Discover | +9.835 |
ghai | +9.657 |
Neg logit contributions | |
Nept | -13.163 |
Reef | -12.031 |
Norn | -11.800 |
oranges | -11.685 |
Ib | -11.420 |
Token | to |
Token ID | 284 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
avage | +1.629 |
leck | +1.415 |
ghai | +1.361 |
Gat | +1.328 |
anski | +1.328 |
Neg logit contributions | |
Nept | -1.411 |
Reef | -1.335 |
oranges | -1.290 |
Ib | -1.286 |
Mercury | -1.248 |
Token | pay |
Token ID | 1414 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
avage | +6.176 |
leck | +5.174 |
anski | +5.058 |
ghai | +5.054 |
Gat | +4.974 |
Neg logit contributions | |
Nept | -6.759 |
Reef | -6.401 |
oranges | -6.139 |
Ib | -6.134 |
Norn | -6.098 |
Token | as |
Token ID | 355 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
avage | +4.872 |
leck | +4.263 |
ghai | +4.100 |
Gat | +4.056 |
anski | +3.977 |
Neg logit contributions | |
Nept | -4.152 |
Reef | -3.942 |
Ib | -3.774 |
oranges | -3.770 |
Norn | -3.666 |
Token | us |
Token ID | 514 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
avage | +6.471 |
leck | +5.612 |
Gat | +5.481 |
ghai | +5.303 |
Discover | +5.178 |
Neg logit contributions | |
Nept | -5.901 |
Reef | -5.438 |
oranges | -5.350 |
Ib | -5.276 |
adul | -5.240 |
Token | did |
Token ID | 750 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
avage | +7.782 |
leck | +6.640 |
Gat | +6.526 |
ghai | +6.359 |
anski | +6.266 |
Neg logit contributions | |
Nept | -6.722 |
Reef | -6.365 |
oranges | -6.101 |
Ib | -5.987 |
Norn | -5.980 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
avage | +11.398 |
Gat | +9.645 |
leck | +9.499 |
ghai | +9.217 |
sth | +9.152 |
Neg logit contributions | |
Nept | -9.643 |
Reef | -8.952 |
oranges | -8.657 |
Norn | -8.626 |
adul | -8.502 |
Token | full |
Token ID | 1336 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
avage | +16.917 |
Gat | +15.274 |
leck | +14.325 |
Discover | +14.064 |
ghai | +13.565 |
Neg logit contributions | |
Nept | -11.544 |
oranges | -10.194 |
Reef | -10.120 |
Norn | -10.083 |
adul | -9.985 |
Token | B |
Token ID | 347 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
avage | +17.255 |
Gat | +15.305 |
leck | +14.753 |
Discover | +14.193 |
ghai | +14.028 |
Neg logit contributions | |
Nept | -11.450 |
Norn | -10.229 |
oranges | -10.035 |
Reef | -10.015 |
adul | -9.857 |
Token | FT |
Token ID | 9792 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
avage | +6.920 |
leck | +5.414 |
GBT | +4.863 |
sth | +4.688 |
ghai | +4.655 |
Neg logit contributions | |
Nept | -13.826 |
oranges | -13.126 |
sax | -12.716 |
Reef | -12.670 |
Ib | -12.657 |
Token | loop |
Token ID | 9052 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
avage | +17.477 |
Gat | +15.358 |
leck | +14.571 |
Discover | +14.215 |
ghai | +14.114 |
Neg logit contributions | |
Nept | -13.658 |
oranges | -12.259 |
Reef | -12.052 |
adul | -11.914 |
Norn | -11.831 |
Token | ( |
Token ID | 357 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
avage | +13.661 |
leck | +11.665 |
Gat | +11.658 |
ghai | +11.369 |
sth | +11.201 |
Neg logit contributions | |
Nept | -10.097 |
Reef | -9.319 |
oranges | -9.199 |
Norn | -8.997 |
Skydragon | -8.895 |
Token | North |
Token ID | 14157 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
avage | +11.304 |
leck | +9.847 |
Gat | +9.324 |
ghai | +9.302 |
sth | +9.248 |
Neg logit contributions | |
Nept | -8.810 |
Reef | -8.033 |
oranges | -7.932 |
adul | -7.777 |
Ib | -7.657 |
Token | and |
Token ID | 290 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
avage | +8.227 |
leck | +7.099 |
Gat | +6.914 |
ghai | +6.853 |
anski | +6.640 |
Neg logit contributions | |
Nept | -6.470 |
Reef | -5.941 |
oranges | -5.930 |
adul | -5.715 |
Ib | -5.689 |
Token | South |
Token ID | 2520 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
avage | +3.120 |
leck | +2.709 |
ghai | +2.614 |
Gat | +2.556 |
anski | +2.541 |
Neg logit contributions | |
Nept | -2.665 |
Reef | -2.516 |
oranges | -2.457 |
Ib | -2.426 |
adul | -2.374 |
Token | more |
Token ID | 517 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
Nept | +4.741 |
Reef | +4.608 |
oranges | +4.367 |
Ib | +4.310 |
adul | +4.236 |
Neg logit contributions | |
avage | -7.939 |
leck | -7.013 |
ghai | -6.724 |
anski | -6.686 |
sth | -6.495 |
Token | than |
Token ID | 621 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
avage | +0.236 |
leck | +0.201 |
ghai | +0.193 |
anski | +0.187 |
Gat | +0.185 |
Neg logit contributions | |
Nept | -0.247 |
Reef | -0.236 |
oranges | -0.230 |
Ib | -0.228 |
Mercury | -0.223 |
Token | 100 |
Token ID | 1802 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Nept | +0.517 |
Reef | +0.488 |
oranges | +0.470 |
Ib | +0.468 |
Mercury | +0.452 |
Neg logit contributions | |
avage | -0.841 |
leck | -0.745 |
ghai | -0.722 |
anski | -0.705 |
sth | -0.692 |
Token | per |
Token ID | 583 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Nept | +2.823 |
Reef | +2.715 |
Ib | +2.603 |
oranges | +2.576 |
Mercury | +2.479 |
Neg logit contributions | |
avage | -4.998 |
leck | -4.492 |
ghai | -4.398 |
anski | -4.231 |
sth | -4.135 |
Token | cent |
Token ID | 1247 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
avage | +1.589 |
leck | +1.399 |
ghai | +1.356 |
Gat | +1.323 |
anski | +1.317 |
Neg logit contributions | |
Nept | -1.064 |
Reef | -0.992 |
oranges | -0.963 |
Ib | -0.952 |
adul | -0.920 |
Token | in |
Token ID | 287 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Reef | +5.982 |
Nept | +5.927 |
Ib | +5.586 |
oranges | +5.424 |
Mercury | +5.371 |
Neg logit contributions | |
avage | -12.653 |
leck | -11.570 |
anski | -10.993 |
ghai | -10.904 |
GBT | -10.698 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Reef | +9.329 |
Nept | +9.164 |
Ib | +9.091 |
Mercury | +8.791 |
oranges | +8.778 |
Neg logit contributions | |
avage | -17.800 |
leck | -16.269 |
ghai | -15.810 |
anski | -15.701 |
Interstitial | -15.474 |
Token | last |
Token ID | 938 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Nept | +8.403 |
Reef | +8.253 |
Mercury | +7.938 |
Ib | +7.912 |
oranges | +7.649 |
Neg logit contributions | |
avage | -15.121 |
leck | -13.681 |
ghai | -13.175 |
anski | -12.885 |
Interstitial | -12.763 |
Token | year |
Token ID | 614 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
Nept | +2.105 |
Reef | +1.994 |
Ib | +1.944 |
oranges | +1.933 |
Mercury | +1.880 |
Neg logit contributions | |
avage | -3.340 |
leck | -2.942 |
ghai | -2.861 |
anski | -2.783 |
sth | -2.727 |
Token | . |
Token ID | 13 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
avage | +0.865 |
leck | +0.751 |
ghai | +0.724 |
anski | +0.704 |
Gat | +0.700 |
Neg logit contributions | |
Nept | -0.730 |
Reef | -0.692 |
oranges | -0.671 |
Ib | -0.668 |
Mercury | -0.649 |
Token |
|
Token ID | 198 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
Nept | +7.720 |
Reef | +7.601 |
Ib | +7.323 |
Mercury | +7.131 |
Dian | +6.734 |
Neg logit contributions | |
avage | -12.847 |
leck | -11.984 |
ghai | -11.290 |
GBT | -11.027 |
anski | -10.957 |
Token | shalt |
Token ID | 36258 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Nept | +5.738 |
Reef | +5.444 |
Ib | +5.379 |
adul | +5.370 |
oranges | +5.302 |
Neg logit contributions | |
avage | -8.003 |
leck | -7.136 |
ghai | -6.973 |
anski | -6.751 |
GBT | -6.688 |
Token | thou |
Token ID | 14210 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Nept | +2.726 |
Reef | +2.572 |
oranges | +2.503 |
Ib | +2.493 |
adul | +2.477 |
Neg logit contributions | |
avage | -3.513 |
leck | -3.143 |
ghai | -3.006 |
Gat | -2.903 |
anski | -2.899 |
Token | take |
Token ID | 1011 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
Nept | +2.110 |
Reef | +1.993 |
oranges | +1.944 |
Ib | +1.925 |
adul | +1.918 |
Neg logit contributions | |
avage | -2.967 |
leck | -2.663 |
ghai | -2.563 |
anski | -2.469 |
Gat | -2.444 |
Token | unto |
Token ID | 12722 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
Nept | +6.884 |
Reef | +6.553 |
oranges | +6.459 |
Ib | +6.414 |
adul | +6.387 |
Neg logit contributions | |
avage | -11.284 |
leck | -10.291 |
ghai | -10.018 |
GBT | -9.723 |
Interstitial | -9.459 |
Token | thy |
Token ID | 11906 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Nept | +6.103 |
Reef | +5.723 |
oranges | +5.615 |
Ib | +5.600 |
adul | +5.591 |
Neg logit contributions | |
avage | -12.311 |
leck | -11.502 |
ghai | -11.306 |
Interstitial | -10.631 |
GBT | -10.526 |
Token | self |
Token ID | 944 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Nept | +3.838 |
Reef | +3.620 |
oranges | +3.561 |
Ib | +3.538 |
adul | +3.500 |
Neg logit contributions | |
avage | -5.009 |
leck | -4.542 |
ghai | -4.496 |
anski | -4.195 |
GBT | -4.131 |
Token | . |
Token ID | 13 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
Nept | +8.488 |
oranges | +8.185 |
adul | +8.091 |
Reef | +8.050 |
Mercury | +7.898 |
Neg logit contributions | |
avage | -12.944 |
ghai | -11.925 |
leck | -11.763 |
GBT | -11.236 |
anski | -10.938 |
Token | De |
Token ID | 1024 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
Nept | +4.493 |
Reef | +4.301 |
Ib | +4.221 |
Mercury | +3.991 |
oranges | +3.883 |
Neg logit contributions | |
avage | -7.067 |
leck | -6.248 |
ghai | -6.130 |
anski | -6.010 |
GBT | -5.812 |
Token | uter |
Token ID | 11894 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Nept | +8.351 |
Reef | +8.328 |
Ib | +8.221 |
adul | +8.143 |
oranges | +7.747 |
Neg logit contributions | |
avage | -10.316 |
ghai | -9.030 |
anski | -9.025 |
leck | -9.006 |
Interstitial | -8.662 |
Token | onomy |
Token ID | 30565 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
Nept | +5.113 |
oranges | +4.844 |
Ib | +4.804 |
Reef | +4.802 |
adul | +4.678 |
Neg logit contributions | |
avage | -5.491 |
leck | -4.841 |
ghai | -4.625 |
GBT | -4.481 |
anski | -4.474 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
Nept | +4.808 |
Ib | +4.446 |
Reef | +4.398 |
Mercury | +4.246 |
adul | +4.078 |
Neg logit contributions | |
avage | -10.809 |
leck | -9.724 |
ghai | -9.528 |
anski | -9.291 |
etheless | -9.139 |
Token | 's |
Token ID | 338 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
Nept | +0.887 |
Reef | +0.834 |
Ib | +0.806 |
oranges | +0.804 |
Mercury | +0.789 |
Neg logit contributions | |
avage | -1.087 |
leck | -0.932 |
ghai | -0.916 |
anski | -0.887 |
Gat | -0.871 |
Token | cod |
Token ID | 14873 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Nept | +0.303 |
Reef | +0.284 |
oranges | +0.274 |
Ib | +0.274 |
Mercury | +0.266 |
Neg logit contributions | |
avage | -0.439 |
leck | -0.385 |
ghai | -0.374 |
anski | -0.364 |
Gat | -0.358 |
Token | ename |
Token ID | 12453 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Nept | +2.838 |
Reef | +2.670 |
Ib | +2.594 |
oranges | +2.567 |
Mercury | +2.525 |
Neg logit contributions | |
avage | -3.331 |
leck | -2.885 |
ghai | -2.790 |
anski | -2.692 |
Gat | -2.682 |
Token | . |
Token ID | 13 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
Nept | +3.495 |
Reef | +3.300 |
Ib | +3.174 |
Mercury | +3.112 |
oranges | +3.097 |
Neg logit contributions | |
avage | -4.645 |
leck | -4.065 |
ghai | -3.992 |
anski | -3.829 |
sth | -3.774 |
Token | The |
Token ID | 383 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
Nept | +8.231 |
Reef | +7.720 |
Mercury | +7.552 |
Ib | +7.458 |
Ox | +7.061 |
Neg logit contributions | |
avage | -11.593 |
leck | -10.306 |
ghai | -10.284 |
anski | -9.679 |
etheless | -9.561 |
Token | first |
Token ID | 717 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
Nept | +5.203 |
Reef | +4.722 |
Ib | +4.642 |
Mercury | +4.640 |
oranges | +4.551 |
Neg logit contributions | |
avage | -7.948 |
leck | -6.979 |
ghai | -6.954 |
anski | -6.586 |
sth | -6.520 |
Token | game |
Token ID | 983 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
Nept | +9.120 |
Reef | +8.588 |
Mercury | +8.408 |
Ib | +8.041 |
Ox | +7.783 |
Neg logit contributions | |
avage | -13.153 |
ghai | -11.897 |
leck | -11.651 |
sth | -11.080 |
anski | -11.025 |
Token | in |
Token ID | 287 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
Nept | +6.936 |
Reef | +6.472 |
Mercury | +6.214 |
Ib | +6.140 |
oranges | +5.992 |
Neg logit contributions | |
avage | -10.346 |
ghai | -9.186 |
leck | -8.834 |
sth | -8.497 |
anski | -8.482 |
Token | the |
Token ID | 262 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
Nept | +6.233 |
Reef | +5.767 |
Mercury | +5.553 |
Ib | +5.495 |
oranges | +5.392 |
Neg logit contributions | |
avage | -8.956 |
ghai | -8.088 |
leck | -7.990 |
anski | -7.461 |
sth | -7.374 |
Token | " |
Token ID | 366 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
Nept | +5.737 |
Reef | +5.251 |
Ib | +5.095 |
Mercury | +5.090 |
oranges | +4.975 |
Neg logit contributions | |
avage | -8.997 |
leck | -8.030 |
ghai | -8.026 |
sth | -7.510 |
anski | -7.510 |
Token | sci |
Token ID | 36216 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Nept | +4.725 |
Reef | +4.500 |
Ib | +4.328 |
Mercury | +4.300 |
oranges | +4.251 |
Neg logit contributions | |
avage | -5.385 |
leck | -4.727 |
ghai | -4.619 |
anski | -4.397 |
Gat | -4.371 |
Token | The |
Token ID | 383 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
Nept | +5.576 |
Reef | +5.411 |
Mercury | +5.088 |
Ib | +5.084 |
Norn | +4.792 |
Neg logit contributions | |
avage | -7.766 |
leck | -6.908 |
ghai | -6.814 |
anski | -6.544 |
etheless | -6.381 |
Token | revelation |
Token ID | 16084 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Nept | +4.533 |
Reef | +4.332 |
Mercury | +4.115 |
oranges | +4.075 |
Ib | +4.074 |
Neg logit contributions | |
avage | -6.488 |
leck | -5.751 |
ghai | -5.621 |
anski | -5.412 |
sth | -5.270 |
Token | that |
Token ID | 326 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Nept | +1.531 |
Reef | +1.446 |
oranges | +1.384 |
Ib | +1.383 |
Mercury | +1.356 |
Neg logit contributions | |
avage | -1.973 |
leck | -1.721 |
ghai | -1.674 |
anski | -1.629 |
GBT | -1.589 |
Token | a |
Token ID | 257 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Nept | +4.481 |
Reef | +4.288 |
oranges | +4.110 |
Mercury | +4.085 |
Ib | +4.063 |
Neg logit contributions | |
avage | -6.233 |
leck | -5.472 |
ghai | -5.356 |
anski | -5.126 |
sth | -5.104 |
Token | murdered |
Token ID | 12864 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
Nept | +4.324 |
Reef | +4.101 |
Mercury | +3.921 |
Ib | +3.877 |
oranges | +3.854 |
Neg logit contributions | |
avage | -6.126 |
leck | -5.409 |
ghai | -5.322 |
anski | -5.100 |
sth | -5.061 |
Token | Fresno |
Token ID | 39927 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Nept | +5.368 |
Reef | +5.190 |
Ib | +4.955 |
Mercury | +4.877 |
oranges | +4.864 |
Neg logit contributions | |
avage | -8.277 |
leck | -7.316 |
ghai | -7.191 |
anski | -6.850 |
sth | -6.825 |
Token | woman |
Token ID | 2415 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
Nept | +8.308 |
Reef | +8.174 |
Mercury | +8.085 |
oranges | +7.764 |
Ib | +7.728 |
Neg logit contributions | |
avage | -14.370 |
leck | -13.083 |
ghai | -12.710 |
sth | -12.314 |
etheless | -11.940 |
Token | was |
Token ID | 373 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Nept | +0.968 |
Reef | +0.920 |
oranges | +0.890 |
Ib | +0.888 |
adul | +0.861 |
Neg logit contributions | |
avage | -1.289 |
leck | -1.126 |
ghai | -1.090 |
anski | -1.056 |
Gat | -1.043 |
Token | sold |
Token ID | 2702 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Nept | +2.396 |
Reef | +2.254 |
Ib | +2.206 |
oranges | +2.179 |
adul | +2.159 |
Neg logit contributions | |
avage | -3.317 |
leck | -2.929 |
ghai | -2.821 |
anski | -2.716 |
sth | -2.672 |
Token | to |
Token ID | 284 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
Nept | +1.196 |
Reef | +1.128 |
oranges | +1.107 |
Ib | +1.092 |
adul | +1.070 |
Neg logit contributions | |
avage | -1.604 |
leck | -1.415 |
ghai | -1.380 |
anski | -1.329 |
Gat | -1.312 |
Token | the |
Token ID | 262 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
avage | +0.327 |
leck | +0.286 |
ghai | +0.276 |
anski | +0.268 |
Gat | +0.267 |
Neg logit contributions | |
Nept | -0.254 |
Reef | -0.240 |
oranges | -0.232 |
Ib | -0.231 |
Mercury | -0.224 |
Token | � |
Token ID | 447 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
Nept | +3.092 |
Reef | +2.908 |
oranges | +2.835 |
Ib | +2.810 |
Mercury | +2.732 |
Neg logit contributions | |
avage | -3.877 |
leck | -3.335 |
ghai | -3.246 |
Gat | -3.139 |
anski | -3.127 |
Token | � |
Token ID | 247 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
Nept | +0.182 |
Reef | +0.176 |
oranges | +0.171 |
Ib | +0.170 |
Mercury | +0.166 |
Neg logit contributions | |
avage | -0.146 |
leck | -0.122 |
ghai | -0.117 |
anski | -0.113 |
Gat | -0.112 |
Token | s |
Token ID | 82 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
avage | +0.313 |
leck | +0.276 |
ghai | +0.268 |
anski | +0.261 |
Gat | +0.261 |
Neg logit contributions | |
Nept | -0.194 |
Reef | -0.182 |
oranges | -0.175 |
Ib | -0.173 |
Mercury | -0.168 |
Token | such |
Token ID | 884 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
Nept | +2.443 |
Reef | +2.281 |
oranges | +2.229 |
Ib | +2.209 |
Mercury | +2.145 |
Neg logit contributions | |
avage | -3.224 |
leck | -2.797 |
ghai | -2.743 |
anski | -2.642 |
sth | -2.574 |
Token | a |
Token ID | 257 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
Nept | +0.331 |
Reef | +0.312 |
oranges | +0.304 |
Ib | +0.301 |
Mercury | +0.292 |
Neg logit contributions | |
avage | -0.426 |
leck | -0.372 |
ghai | -0.361 |
anski | -0.350 |
Gat | -0.346 |
Token | direct |
Token ID | 1277 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Nept | +3.526 |
Reef | +3.292 |
oranges | +3.177 |
Ib | +3.151 |
Mercury | +3.071 |
Neg logit contributions | |
avage | -4.864 |
leck | -4.276 |
ghai | -4.177 |
anski | -4.008 |
sth | -3.946 |
Token | homage |
Token ID | 31044 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Nept | +9.334 |
Reef | +8.911 |
oranges | +8.565 |
adul | +8.561 |
Ib | +8.539 |
Neg logit contributions | |
avage | -12.615 |
leck | -11.340 |
ghai | -11.046 |
anski | -10.447 |
GBT | -10.311 |
Token | to |
Token ID | 284 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Nept | +5.838 |
Reef | +5.337 |
Ib | +5.213 |
oranges | +5.147 |
Mercury | +5.007 |
Neg logit contributions | |
avage | -9.285 |
leck | -8.245 |
ghai | -8.019 |
GBT | -7.703 |
anski | -7.639 |
Token | an |
Token ID | 281 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Nept | +4.000 |
Reef | +3.777 |
Ib | +3.568 |
oranges | +3.560 |
Mercury | +3.534 |
Neg logit contributions | |
avage | -5.440 |
leck | -4.800 |
ghai | -4.726 |
anski | -4.439 |
GBT | -4.402 |
Token | earlier |
Token ID | 2961 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Nept | +1.435 |
Reef | +1.339 |
Ib | +1.303 |
oranges | +1.296 |
adul | +1.260 |
Neg logit contributions | |
avage | -1.886 |
leck | -1.661 |
ghai | -1.588 |
anski | -1.536 |
Gat | -1.519 |
Token | project |
Token ID | 1628 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Nept | +1.714 |
Reef | +1.602 |
Ib | +1.524 |
oranges | +1.511 |
Mercury | +1.489 |
Neg logit contributions | |
avage | -2.366 |
leck | -2.103 |
ghai | -2.042 |
anski | -1.958 |
sth | -1.920 |
Token | reprim |
Token ID | 41929 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
avage | +3.260 |
leck | +2.836 |
ghai | +2.730 |
anski | +2.663 |
Gat | +2.660 |
Neg logit contributions | |
Nept | -2.648 |
Reef | -2.514 |
oranges | -2.427 |
Ib | -2.410 |
Norn | -2.343 |
Token | anded |
Token ID | 12249 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Nept | +1.505 |
Reef | +1.443 |
oranges | +1.408 |
Ib | +1.403 |
Mercury | +1.371 |
Neg logit contributions | |
avage | -1.092 |
leck | -0.904 |
ghai | -0.865 |
anski | -0.828 |
Gat | -0.828 |
Token | . |
Token ID | 13 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
avage | +2.322 |
leck | +2.014 |
ghai | +1.929 |
anski | +1.882 |
Gat | +1.882 |
Neg logit contributions | |
Nept | -2.033 |
Reef | -1.928 |
oranges | -1.875 |
Ib | -1.860 |
adul | -1.802 |
Token | J |
Token ID | 449 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
Nept | +5.699 |
Ib | +5.494 |
Reef | +5.440 |
Mercury | +5.238 |
Norn | +5.018 |
Neg logit contributions | |
avage | -7.839 |
leck | -6.914 |
ghai | -6.823 |
sth | -6.452 |
anski | -6.448 |
Token | SO |
Token ID | 15821 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Nept | +3.943 |
Reef | +3.792 |
Ib | +3.734 |
oranges | +3.726 |
Mercury | +3.610 |
Neg logit contributions | |
avage | -4.203 |
leck | -3.664 |
ghai | -3.585 |
Gat | -3.412 |
anski | -3.335 |
Token | said |
Token ID | 531 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Nept | +3.806 |
Reef | +3.584 |
Ib | +3.452 |
oranges | +3.407 |
Mercury | +3.345 |
Neg logit contributions | |
avage | -5.296 |
leck | -4.652 |
ghai | -4.584 |
anski | -4.364 |
sth | -4.294 |
Token | since |
Token ID | 1201 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
Nept | +4.857 |
Ib | +4.626 |
Reef | +4.574 |
Mercury | +4.428 |
oranges | +4.395 |
Neg logit contributions | |
avage | -6.915 |
leck | -6.020 |
ghai | -5.957 |
sth | -5.661 |
anski | -5.642 |
Token | one |
Token ID | 530 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
Nept | +1.035 |
Reef | +0.977 |
Ib | +0.958 |
oranges | +0.948 |
Mercury | +0.925 |
Neg logit contributions | |
avage | -1.353 |
leck | -1.178 |
ghai | -1.145 |
anski | -1.110 |
sth | -1.094 |
Token | of |
Token ID | 286 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
avage | +0.402 |
leck | +0.351 |
ghai | +0.340 |
anski | +0.330 |
Gat | +0.328 |
Neg logit contributions | |
Nept | -0.308 |
Reef | -0.291 |
oranges | -0.281 |
Ib | -0.280 |
Mercury | -0.272 |
Token | the |
Token ID | 262 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Nept | +5.162 |
Ib | +4.950 |
Reef | +4.883 |
oranges | +4.685 |
Mercury | +4.680 |
Neg logit contributions | |
avage | -8.774 |
ghai | -7.640 |
leck | -7.599 |
anski | -7.261 |
sth | -7.223 |
Token | officers |
Token ID | 3790 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Nept | +2.689 |
Reef | +2.525 |
Ib | +2.442 |
oranges | +2.438 |
Mercury | +2.385 |
Neg logit contributions | |
avage | -3.914 |
leck | -3.403 |
ghai | -3.356 |
anski | -3.216 |
sth | -3.179 |
Token | � |
Token ID | 447 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
avage | +3.561 |
leck | +3.072 |
ghai | +2.957 |
Gat | +2.881 |
anski | +2.878 |
Neg logit contributions | |
Nept | -3.181 |
Reef | -3.019 |
oranges | -2.937 |
Ib | -2.911 |
Mercury | -2.827 |
Token | � |
Token ID | 251 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
avage | +0.832 |
leck | +0.699 |
ghai | +0.666 |
anski | +0.646 |
Gat | +0.640 |
Neg logit contributions | |
Nept | -1.047 |
Reef | -1.005 |
oranges | -0.979 |
Ib | -0.975 |
Mercury | -0.952 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
Nept | +0.970 |
Reef | +0.916 |
Ib | +0.884 |
oranges | +0.884 |
Mercury | +0.859 |
Neg logit contributions | |
avage | -1.242 |
leck | -1.083 |
ghai | -1.047 |
anski | -1.017 |
Gat | -1.011 |
Token | alleg |
Token ID | 2868 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
avage | +0.334 |
leck | +0.292 |
ghai | +0.284 |
anski | +0.275 |
Gat | +0.273 |
Neg logit contributions | |
Nept | -0.243 |
Reef | -0.228 |
oranges | -0.221 |
Ib | -0.221 |
Mercury | -0.214 |
Token | ory |
Token ID | 652 |
Feature activation | +9.49e-03 |
Pos logit contributions | |
Nept | +1.052 |
Reef | +0.990 |
oranges | +0.960 |
Ib | +0.959 |
Mercury | +0.931 |
Neg logit contributions | |
avage | -1.370 |
leck | -1.204 |
ghai | -1.160 |
Gat | -1.132 |
anski | -1.127 |
Token | ( |
Token ID | 357 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Nept | +0.102 |
Reef | +0.096 |
oranges | +0.093 |
Ib | +0.093 |
adul | +0.090 |
Neg logit contributions | |
avage | -0.128 |
leck | -0.111 |
ghai | -0.108 |
anski | -0.105 |
Gat | -0.104 |
Token | in |
Token ID | 259 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Nept | +1.481 |
Reef | +1.398 |
Ib | +1.363 |
oranges | +1.354 |
Mercury | +1.325 |
Neg logit contributions | |
avage | -1.792 |
leck | -1.567 |
ghai | -1.515 |
Gat | -1.469 |
anski | -1.464 |
Token | Greek |
Token ID | 8312 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Nept | +3.178 |
Reef | +2.930 |
Ib | +2.902 |
oranges | +2.837 |
Mercury | +2.793 |
Neg logit contributions | |
avage | -4.400 |
leck | -3.891 |
ghai | -3.821 |
anski | -3.691 |
Gat | -3.597 |
Token | h |
Token ID | 289 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Nept | +2.803 |
Reef | +2.569 |
oranges | +2.528 |
Ib | +2.515 |
Mercury | +2.461 |
Neg logit contributions | |
avage | -3.713 |
leck | -3.292 |
ghai | -3.180 |
anski | -3.087 |
Gat | -3.024 |
Token | upon |
Token ID | 27287 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
Nept | +1.797 |
Reef | +1.679 |
oranges | +1.654 |
Ib | +1.653 |
Mercury | +1.592 |
Neg logit contributions | |
avage | -2.285 |
leck | -1.978 |
ghai | -1.947 |
Gat | -1.885 |
anski | -1.852 |
Token | o |
Token ID | 78 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
avage | +0.828 |
leck | +0.722 |
ghai | +0.699 |
anski | +0.678 |
Gat | +0.678 |
Neg logit contributions | |
Nept | -0.643 |
Reef | -0.605 |
oranges | -0.587 |
Ib | -0.584 |
Mercury | -0.567 |
Token | sheriff |
Token ID | 16570 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
avage | +2.638 |
leck | +2.312 |
ghai | +2.235 |
Gat | +2.196 |
anski | +2.185 |
Neg logit contributions | |
Nept | -1.833 |
Reef | -1.724 |
oranges | -1.675 |
Ib | -1.655 |
adul | -1.590 |
Token | 's |
Token ID | 338 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
Nept | +2.160 |
Reef | +2.020 |
oranges | +1.980 |
Ib | +1.949 |
Mercury | +1.902 |
Neg logit contributions | |
avage | -3.365 |
leck | -2.969 |
ghai | -2.884 |
anski | -2.781 |
Gat | -2.777 |
Token | office |
Token ID | 2607 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Nept | +3.243 |
Reef | +3.016 |
oranges | +2.989 |
Mercury | +2.889 |
Ib | +2.886 |
Neg logit contributions | |
avage | -10.003 |
leck | -9.119 |
ghai | -8.893 |
Interstitial | -8.559 |
sth | -8.550 |
Token | said |
Token ID | 531 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
avage | +3.329 |
leck | +2.803 |
ghai | +2.658 |
Gat | +2.631 |
anski | +2.603 |
Neg logit contributions | |
Nept | -3.908 |
Reef | -3.739 |
oranges | -3.632 |
Ib | -3.606 |
adul | -3.514 |
Token | . |
Token ID | 13 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
avage | +2.655 |
leck | +2.287 |
ghai | +2.209 |
anski | +2.152 |
Gat | +2.143 |
Neg logit contributions | |
Nept | -2.371 |
Reef | -2.240 |
oranges | -2.188 |
Ib | -2.160 |
adul | -2.102 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Nept | +0.619 |
Reef | +0.588 |
Ib | +0.568 |
oranges | +0.557 |
Mercury | +0.551 |
Neg logit contributions | |
avage | -0.763 |
leck | -0.668 |
ghai | -0.645 |
anski | -0.625 |
Gat | -0.613 |
Token |
|
Token ID | 198 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
Nept | +1.206 |
Reef | +1.147 |
Ib | +1.107 |
oranges | +1.103 |
Mercury | +1.077 |
Neg logit contributions | |
avage | -1.442 |
leck | -1.258 |
ghai | -1.212 |
anski | -1.177 |
Gat | -1.165 |
Token | We |
Token ID | 1135 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
Nept | +0.055 |
Reef | +0.052 |
Ib | +0.050 |
oranges | +0.050 |
Mercury | +0.049 |
Neg logit contributions | |
avage | -0.070 |
leck | -0.061 |
ghai | -0.059 |
anski | -0.057 |
Gat | -0.057 |
Token | ird |
Token ID | 1447 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
avage | +0.775 |
leck | +0.675 |
ghai | +0.651 |
anski | +0.631 |
Gat | +0.630 |
Neg logit contributions | |
Nept | -0.640 |
Reef | -0.606 |
oranges | -0.587 |
Ib | -0.586 |
Mercury | -0.568 |
Token | News |
Token ID | 3000 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
Nept | +2.953 |
Reef | +2.781 |
Ib | +2.686 |
oranges | +2.674 |
Mercury | +2.647 |
Neg logit contributions | |
avage | -3.577 |
leck | -3.153 |
ghai | -3.031 |
anski | -2.933 |
Gat | -2.897 |
Token | Photos |
Token ID | 9434 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
avage | +3.536 |
leck | +2.982 |
ghai | +2.873 |
anski | +2.782 |
Gat | +2.777 |
Neg logit contributions | |
Nept | -3.632 |
Reef | -3.412 |
oranges | -3.391 |
Ib | -3.308 |
adul | -3.263 |
Token | latest |
Token ID | 3452 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
Nept | +1.501 |
Reef | +1.416 |
oranges | +1.382 |
Ib | +1.372 |
Mercury | +1.343 |
Neg logit contributions | |
avage | -1.842 |
leck | -1.627 |
ghai | -1.579 |
anski | -1.524 |
Gat | -1.488 |
Token | press |
Token ID | 1803 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Nept | +0.054 |
Reef | +0.051 |
oranges | +0.050 |
Ib | +0.049 |
Mercury | +0.048 |
Neg logit contributions | |
avage | -0.065 |
leck | -0.057 |
ghai | -0.055 |
anski | -0.053 |
Gat | -0.053 |
Token | tour |
Token ID | 4205 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
avage | +4.945 |
leck | +4.348 |
ghai | +4.142 |
Gat | +4.065 |
anski | +4.043 |
Neg logit contributions | |
Nept | -3.329 |
Reef | -3.121 |
oranges | -3.017 |
Ib | -2.974 |
Mercury | -2.883 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
avage | +1.041 |
leck | +0.908 |
ghai | +0.878 |
anski | +0.854 |
Gat | +0.848 |
Neg logit contributions | |
Nept | -0.837 |
Reef | -0.790 |
oranges | -0.766 |
Ib | -0.763 |
Mercury | -0.740 |
Token | too |
Token ID | 1165 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Nept | +1.591 |
Reef | +1.517 |
oranges | +1.466 |
Ib | +1.464 |
adul | +1.425 |
Neg logit contributions | |
avage | -1.937 |
leck | -1.690 |
ghai | -1.638 |
anski | -1.579 |
Gat | -1.560 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
avage | +3.849 |
leck | +3.321 |
ghai | +3.178 |
Gat | +3.108 |
anski | +3.106 |
Neg logit contributions | |
Nept | -3.502 |
Reef | -3.330 |
oranges | -3.228 |
Ib | -3.211 |
Mercury | -3.109 |
Token | with |
Token ID | 351 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Nept | +0.335 |
Reef | +0.318 |
oranges | +0.308 |
Ib | +0.307 |
Mercury | +0.298 |
Neg logit contributions | |
avage | -0.412 |
leck | -0.360 |
ghai | -0.348 |
anski | -0.337 |
Gat | -0.333 |
Token | an |
Token ID | 281 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Nept | +1.452 |
Reef | +1.372 |
oranges | +1.331 |
Ib | +1.329 |
Mercury | +1.294 |
Neg logit contributions | |
avage | -1.921 |
leck | -1.693 |
ghai | -1.648 |
anski | -1.588 |
sth | -1.559 |
Token | argument |
Token ID | 4578 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
avage | +1.582 |
leck | +1.365 |
ghai | +1.315 |
anski | +1.276 |
Gat | +1.272 |
Neg logit contributions | |
Nept | -1.436 |
Reef | -1.363 |
oranges | -1.324 |
Ib | -1.316 |
Mercury | -1.280 |
Token | that |
Token ID | 326 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Nept | +0.325 |
Reef | +0.308 |
oranges | +0.298 |
Ib | +0.297 |
Mercury | +0.288 |
Neg logit contributions | |
avage | -0.401 |
leck | -0.350 |
ghai | -0.340 |
anski | -0.327 |
Gat | -0.324 |
Token | � |
Token ID | 447 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
avage | +2.966 |
leck | +2.568 |
ghai | +2.476 |
Gat | +2.424 |
anski | +2.420 |
Neg logit contributions | |
Nept | -2.396 |
Reef | -2.268 |
oranges | -2.191 |
Ib | -2.185 |
Mercury | -2.114 |
Token |
|
Token ID | 198 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Nept | +0.717 |
Reef | +0.681 |
oranges | +0.658 |
Ib | +0.657 |
Mercury | +0.639 |
Neg logit contributions | |
avage | -0.836 |
leck | -0.726 |
ghai | -0.699 |
anski | -0.680 |
Gat | -0.675 |
Token | Ten |
Token ID | 24893 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
avage | +3.569 |
leck | +3.089 |
ghai | +2.998 |
anski | +2.909 |
Gat | +2.897 |
Neg logit contributions | |
Nept | -2.979 |
Reef | -2.808 |
oranges | -2.748 |
Ib | -2.716 |
adul | -2.629 |
Token | � |
Token ID | 564 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
avage | +7.498 |
leck | +6.507 |
ghai | +6.412 |
Gat | +6.165 |
anski | +6.145 |
Neg logit contributions | |
Nept | -5.826 |
Reef | -5.512 |
oranges | -5.391 |
Ib | -5.369 |
Norn | -5.286 |
Token | � |
Token ID | 250 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
avage | +3.575 |
leck | +2.957 |
ghai | +2.836 |
Gat | +2.687 |
anski | +2.680 |
Neg logit contributions | |
Nept | -4.961 |
Reef | -4.706 |
oranges | -4.598 |
Ib | -4.562 |
Mercury | -4.501 |
Token | cent |
Token ID | 1087 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
avage | +5.290 |
leck | +4.593 |
ghai | +4.462 |
anski | +4.342 |
Gat | +4.285 |
Neg logit contributions | |
Nept | -4.007 |
Reef | -3.792 |
oranges | -3.683 |
Ib | -3.632 |
Norn | -3.525 |
Token | r |
Token ID | 81 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Nept | +1.727 |
Reef | +1.618 |
oranges | +1.579 |
Ib | +1.552 |
Mercury | +1.523 |
Neg logit contributions | |
avage | -2.355 |
leck | -2.061 |
ghai | -1.984 |
Gat | -1.939 |
anski | -1.929 |
Token | ally |
Token ID | 453 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Nept | +1.764 |
Reef | +1.662 |
oranges | +1.604 |
Ib | +1.596 |
adul | +1.545 |
Neg logit contributions | |
avage | -2.501 |
leck | -2.211 |
ghai | -2.144 |
Gat | -2.088 |
anski | -2.074 |
Token | appointed |
Token ID | 9899 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
Nept | +1.183 |
Reef | +1.115 |
Ib | +1.080 |
oranges | +1.079 |
adul | +1.048 |
Neg logit contributions | |
avage | -1.596 |
leck | -1.404 |
ghai | -1.352 |
anski | -1.314 |
Gat | -1.312 |
Token | and |
Token ID | 290 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
avage | +1.203 |
leck | +1.043 |
ghai | +1.006 |
anski | +0.977 |
Gat | +0.974 |
Neg logit contributions | |
Nept | -1.017 |
Reef | -0.963 |
oranges | -0.935 |
Ib | -0.929 |
Mercury | -0.903 |
Token | administered |
Token ID | 17169 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
avage | +3.947 |
leck | +3.464 |
ghai | +3.358 |
Gat | +3.275 |
anski | +3.271 |
Neg logit contributions | |
Nept | -2.983 |
Reef | -2.838 |
oranges | -2.769 |
Ib | -2.721 |
Norn | -2.641 |
Token | officials |
Token ID | 2828 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Nept | +0.293 |
Reef | +0.275 |
oranges | +0.266 |
Ib | +0.264 |
Mercury | +0.258 |
Neg logit contributions | |
avage | -0.388 |
leck | -0.339 |
ghai | -0.325 |
anski | -0.317 |
Gat | -0.314 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Nept | +1.212 |
Reef | +1.165 |
Ib | +1.117 |
oranges | +1.088 |
Mercury | +1.087 |
Neg logit contributions | |
avage | -1.502 |
leck | -1.317 |
ghai | -1.260 |
anski | -1.231 |
sth | -1.197 |
Token |
|
Token ID | 198 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
Nept | +1.476 |
Reef | +1.410 |
Ib | +1.359 |
oranges | +1.347 |
Mercury | +1.323 |
Neg logit contributions | |
avage | -1.819 |
leck | -1.595 |
ghai | -1.536 |
anski | -1.495 |
Gat | -1.471 |
Token | H |
Token ID | 39 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
Nept | +0.250 |
Reef | +0.239 |
Ib | +0.230 |
oranges | +0.227 |
Mercury | +0.223 |
Neg logit contributions | |
avage | -0.329 |
leck | -0.288 |
ghai | -0.278 |
anski | -0.271 |
Gat | -0.268 |
Token | emp |
Token ID | 45787 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
avage | +0.726 |
leck | +0.608 |
ghai | +0.581 |
anski | +0.560 |
Gat | +0.558 |
Neg logit contributions | |
Nept | -0.908 |
Reef | -0.868 |
oranges | -0.847 |
Ib | -0.843 |
Mercury | -0.823 |
Token | Supporters |
Token ID | 39995 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
avage | +0.728 |
leck | +0.635 |
ghai | +0.612 |
anski | +0.595 |
Gat | +0.591 |
Neg logit contributions | |
Nept | -0.580 |
Reef | -0.551 |
oranges | -0.533 |
Ib | -0.529 |
Mercury | -0.514 |
Token | State |
Token ID | 1812 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
avage | +4.434 |
leck | +3.838 |
ghai | +3.725 |
Gat | +3.648 |
anski | +3.598 |
Neg logit contributions | |
Nept | -3.613 |
Reef | -3.387 |
oranges | -3.339 |
Ib | -3.276 |
adul | -3.209 |
Token | Senators |
Token ID | 22195 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
avage | +0.978 |
leck | +0.856 |
ghai | +0.828 |
anski | +0.810 |
Gat | +0.804 |
Neg logit contributions | |
Nept | -0.700 |
Reef | -0.662 |
Ib | -0.636 |
oranges | -0.636 |
Mercury | -0.616 |
Token | Russell |
Token ID | 11563 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Nept | +2.536 |
Reef | +2.440 |
Ib | +2.351 |
Mercury | +2.290 |
oranges | +2.285 |
Neg logit contributions | |
avage | -3.131 |
leck | -2.742 |
ghai | -2.625 |
anski | -2.561 |
sth | -2.504 |
Token | Rud |
Token ID | 17421 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Nept | +1.571 |
Reef | +1.493 |
Ib | +1.435 |
oranges | +1.419 |
Mercury | +1.398 |
Neg logit contributions | |
avage | -2.061 |
leck | -1.819 |
ghai | -1.735 |
anski | -1.697 |
Gat | -1.672 |
Token | erman |
Token ID | 2224 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
avage | +7.062 |
leck | +6.171 |
ghai | +5.859 |
anski | +5.841 |
sth | +5.659 |
Neg logit contributions | |
Nept | -6.247 |
Reef | -5.869 |
oranges | -5.850 |
Ib | -5.746 |
Mercury | -5.538 |
Token | and |
Token ID | 290 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Nept | +0.976 |
Reef | +0.927 |
Ib | +0.893 |
oranges | +0.888 |
Mercury | +0.863 |
Neg logit contributions | |
avage | -1.301 |
leck | -1.140 |
ghai | -1.097 |
anski | -1.064 |
Gat | -1.059 |
Token | Smith |
Token ID | 17919 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
avage | +0.873 |
leck | +0.747 |
ghai | +0.720 |
anski | +0.697 |
Gat | +0.692 |
Neg logit contributions | |
Nept | -0.871 |
Reef | -0.829 |
oranges | -0.804 |
Ib | -0.802 |
Mercury | -0.783 |
Token | sonian |
Token ID | 35202 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
avage | +2.463 |
leck | +2.115 |
ghai | +2.054 |
anski | +2.014 |
Gat | +1.981 |
Neg logit contributions | |
Nept | -2.071 |
Reef | -1.942 |
oranges | -1.913 |
Ib | -1.898 |
adul | -1.837 |
Token | Center |
Token ID | 3337 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
avage | +2.932 |
leck | +2.571 |
ghai | +2.479 |
Gat | +2.442 |
anski | +2.415 |
Neg logit contributions | |
Nept | -2.115 |
Reef | -1.987 |
oranges | -1.950 |
Ib | -1.910 |
adul | -1.871 |
Token | for |
Token ID | 329 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
avage | +3.662 |
leck | +3.122 |
ghai | +3.004 |
Gat | +2.957 |
anski | +2.920 |
Neg logit contributions | |
Nept | -3.443 |
Reef | -3.242 |
oranges | -3.179 |
Ib | -3.138 |
adul | -3.076 |
Token | Ast |
Token ID | 8304 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Nept | +1.460 |
Reef | +1.367 |
Ib | +1.306 |
oranges | +1.288 |
Mercury | +1.280 |
Neg logit contributions | |
avage | -2.603 |
leck | -2.320 |
ghai | -2.241 |
anski | -2.203 |
sth | -2.152 |
Token | roph |
Token ID | 10051 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
avage | +3.263 |
leck | +2.357 |
ghai | +2.143 |
sth | +1.955 |
Gat | +1.944 |
Neg logit contributions | |
Nept | -8.965 |
oranges | -8.664 |
Reef | -8.593 |
Ib | -8.507 |
Norn | -8.350 |
Token | ysics |
Token ID | 23154 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
avage | +6.659 |
leck | +5.062 |
ghai | +5.017 |
anski | +4.811 |
Discover | +4.712 |
Neg logit contributions | |
Nept | -9.709 |
oranges | -9.148 |
Reef | -9.138 |
Ib | -8.850 |
Norn | -8.797 |
Token | added |
Token ID | 2087 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
avage | +4.495 |
leck | +3.885 |
ghai | +3.743 |
Gat | +3.703 |
anski | +3.650 |
Neg logit contributions | |
Nept | -4.054 |
Reef | -3.852 |
oranges | -3.757 |
Ib | -3.694 |
adul | -3.615 |
Token | : |
Token ID | 25 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
avage | +0.170 |
leck | +0.148 |
ghai | +0.144 |
anski | +0.140 |
Gat | +0.138 |
Neg logit contributions | |
Nept | -0.134 |
Reef | -0.127 |
oranges | -0.123 |
Ib | -0.122 |
Mercury | -0.119 |
Token | � |
Token ID | 564 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
avage | +0.548 |
leck | +0.476 |
ghai | +0.460 |
anski | +0.447 |
Gat | +0.445 |
Neg logit contributions | |
Nept | -0.448 |
Reef | -0.425 |
oranges | -0.411 |
Ib | -0.409 |
Mercury | -0.397 |
Token | � |
Token ID | 250 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
avage | +1.228 |
leck | +1.022 |
ghai | +0.970 |
anski | +0.936 |
Gat | +0.928 |
Neg logit contributions | |
Nept | -1.686 |
Reef | -1.620 |
oranges | -1.583 |
Ib | -1.578 |
Mercury | -1.538 |
Token | in |
Token ID | 287 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
avage | +2.913 |
leck | +2.542 |
ghai | +2.451 |
Gat | +2.389 |
anski | +2.389 |
Neg logit contributions | |
Nept | -2.306 |
Reef | -2.174 |
oranges | -2.106 |
Ib | -2.088 |
Mercury | -2.025 |
Token | its |
Token ID | 663 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Nept | +1.496 |
Reef | +1.417 |
oranges | +1.370 |
Ib | +1.369 |
Mercury | +1.325 |
Neg logit contributions | |
avage | -2.019 |
leck | -1.784 |
ghai | -1.737 |
anski | -1.683 |
Gat | -1.649 |
Token | � |
Token ID | 564 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Nept | +3.553 |
Reef | +3.379 |
oranges | +3.307 |
Ib | +3.284 |
Mercury | +3.194 |
Neg logit contributions | |
avage | -4.697 |
leck | -4.127 |
ghai | -4.020 |
anski | -3.878 |
GBT | -3.816 |
Token | � |
Token ID | 250 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
avage | +2.591 |
leck | +2.148 |
ghai | +2.054 |
Gat | +1.967 |
anski | +1.964 |
Neg logit contributions | |
Nept | -3.322 |
Reef | -3.163 |
oranges | -3.097 |
Ib | -3.067 |
Mercury | -3.011 |
Token | active |
Token ID | 5275 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
avage | +5.305 |
leck | +4.595 |
ghai | +4.425 |
anski | +4.306 |
Gat | +4.268 |
Neg logit contributions | |
Nept | -4.056 |
Reef | -3.844 |
oranges | -3.759 |
Ib | -3.691 |
Norn | -3.582 |
Token | � |
Token ID | 447 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
Nept | +3.536 |
Reef | +3.354 |
oranges | +3.288 |
Ib | +3.254 |
Mercury | +3.200 |
Neg logit contributions | |
avage | -3.969 |
leck | -3.533 |
ghai | -3.392 |
anski | -3.282 |
Gat | -3.247 |
Token | � |
Token ID | 251 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
avage | +3.217 |
leck | +2.632 |
ghai | +2.505 |
Gat | +2.388 |
anski | +2.356 |
Neg logit contributions | |
Nept | -4.726 |
Reef | -4.482 |
oranges | -4.413 |
Ib | -4.372 |
adul | -4.292 |
Token | state |
Token ID | 1181 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
avage | +0.887 |
leck | +0.773 |
ghai | +0.746 |
anski | +0.726 |
Gat | +0.722 |
Neg logit contributions | |
Nept | -0.741 |
Reef | -0.702 |
oranges | -0.679 |
Ib | -0.676 |
Mercury | -0.657 |
Token | . |
Token ID | 13 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
avage | +2.384 |
leck | +2.063 |
ghai | +1.984 |
anski | +1.928 |
Gat | +1.924 |
Neg logit contributions | |
Nept | -2.061 |
Reef | -1.952 |
oranges | -1.897 |
Ib | -1.883 |
Mercury | -1.829 |
Token |
|
Token ID | 198 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Nept | +0.347 |
Reef | +0.328 |
Ib | +0.318 |
oranges | +0.315 |
Mercury | +0.308 |
Neg logit contributions | |
avage | -0.427 |
leck | -0.373 |
ghai | -0.360 |
anski | -0.350 |
Gat | -0.344 |
Token |
|
Token ID | 198 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
Nept | +3.517 |
Reef | +3.414 |
Ib | +3.283 |
Mercury | +3.191 |
oranges | +3.141 |
Neg logit contributions | |
avage | -5.034 |
leck | -4.516 |
ghai | -4.363 |
anski | -4.243 |
etheless | -4.185 |
Token | in |
Token ID | 287 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Nept | +1.386 |
Reef | +1.312 |
oranges | +1.248 |
Ib | +1.243 |
Mercury | +1.212 |
Neg logit contributions | |
avage | -2.146 |
leck | -1.903 |
ghai | -1.844 |
anski | -1.788 |
Gat | -1.772 |
Token | the |
Token ID | 262 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Nept | +1.272 |
Reef | +1.213 |
Ib | +1.173 |
oranges | +1.164 |
Mercury | +1.133 |
Neg logit contributions | |
avage | -1.761 |
leck | -1.540 |
ghai | -1.513 |
anski | -1.455 |
Gat | -1.416 |
Token | polls |
Token ID | 9231 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
avage | +2.516 |
leck | +2.196 |
ghai | +2.118 |
Gat | +2.070 |
anski | +2.066 |
Neg logit contributions | |
Nept | -1.906 |
Reef | -1.790 |
oranges | -1.738 |
Ib | -1.726 |
Mercury | -1.669 |
Token | . |
Token ID | 13 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
Nept | +1.840 |
Reef | +1.739 |
Ib | +1.695 |
oranges | +1.686 |
adul | +1.637 |
Neg logit contributions | |
avage | -2.432 |
leck | -2.128 |
ghai | -2.061 |
anski | -2.012 |
Gat | -1.984 |
Token | And |
Token ID | 843 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
avage | +1.173 |
leck | +1.021 |
ghai | +0.986 |
anski | +0.959 |
Gat | +0.958 |
Neg logit contributions | |
Nept | -0.931 |
Reef | -0.880 |
oranges | -0.854 |
Ib | -0.848 |
Mercury | -0.822 |
Token | Ign |
Token ID | 16583 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Nept | +0.147 |
Reef | +0.139 |
Ib | +0.135 |
oranges | +0.135 |
Mercury | +0.131 |
Neg logit contributions | |
avage | -0.193 |
leck | -0.167 |
ghai | -0.163 |
anski | -0.157 |
Gat | -0.155 |
Token | at |
Token ID | 265 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
avage | +1.940 |
leck | +1.677 |
ghai | +1.607 |
Gat | +1.573 |
anski | +1.564 |
Neg logit contributions | |
Nept | -1.736 |
Reef | -1.629 |
oranges | -1.597 |
Ib | -1.568 |
Mercury | -1.528 |
Token | ie |
Token ID | 494 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
Nept | +1.479 |
Reef | +1.413 |
oranges | +1.361 |
Ib | +1.359 |
Mercury | +1.319 |
Neg logit contributions | |
avage | -1.763 |
leck | -1.524 |
ghai | -1.474 |
anski | -1.432 |
Gat | -1.428 |
Token | ff |
Token ID | 487 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Reef | +5.688 |
Nept | +5.681 |
Mercury | +5.316 |
Ib | +5.275 |
oranges | +5.092 |
Neg logit contributions | |
avage | -9.231 |
ghai | -7.902 |
GBT | -7.804 |
leck | -7.741 |
etheless | -7.730 |
Token | , |
Token ID | 11 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
avage | +4.335 |
leck | +3.771 |
ghai | +3.594 |
Gat | +3.523 |
anski | +3.500 |
Neg logit contributions | |
Nept | -3.853 |
Reef | -3.641 |
oranges | -3.524 |
Ib | -3.498 |
Mercury | -3.398 |
Token | who |
Token ID | 508 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
avage | +6.668 |
leck | +5.873 |
Gat | +5.613 |
ghai | +5.504 |
anski | +5.387 |
Neg logit contributions | |
Nept | -6.153 |
Reef | -5.817 |
oranges | -5.717 |
Ib | -5.514 |
Norn | -5.509 |
Token | berry |
Token ID | 8396 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Nept | +0.051 |
Reef | +0.047 |
oranges | +0.046 |
Ib | +0.045 |
Mercury | +0.044 |
Neg logit contributions | |
avage | -0.093 |
leck | -0.083 |
ghai | -0.081 |
anski | -0.079 |
Gat | -0.078 |
Token | orange |
Token ID | 10912 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
avage | +3.875 |
leck | +3.401 |
ghai | +3.274 |
Gat | +3.208 |
anski | +3.198 |
Neg logit contributions | |
Nept | -2.689 |
Reef | -2.530 |
Ib | -2.423 |
oranges | -2.402 |
Mercury | -2.346 |
Token | muff |
Token ID | 27563 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
avage | +4.500 |
leck | +3.933 |
ghai | +3.782 |
Gat | +3.701 |
anski | +3.667 |
Neg logit contributions | |
Nept | -3.268 |
Reef | -3.072 |
Ib | -2.948 |
oranges | -2.902 |
Mercury | -2.865 |
Token | ins |
Token ID | 1040 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
avage | +1.583 |
leck | +1.353 |
ghai | +1.298 |
anski | +1.259 |
Gat | +1.254 |
Neg logit contributions | |
Nept | -1.586 |
Reef | -1.510 |
oranges | -1.466 |
Ib | -1.460 |
Mercury | -1.422 |
Token | and |
Token ID | 290 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
Nept | +0.933 |
Reef | +0.881 |
oranges | +0.864 |
Ib | +0.845 |
adul | +0.827 |
Neg logit contributions | |
avage | -1.221 |
leck | -1.069 |
ghai | -1.028 |
anski | -1.001 |
Gat | -0.997 |
Token | the |
Token ID | 262 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
avage | +6.504 |
leck | +5.725 |
ghai | +5.569 |
Gat | +5.535 |
anski | +5.404 |
Neg logit contributions | |
Nept | -4.494 |
Reef | -4.266 |
Ib | -4.062 |
oranges | -3.950 |
Mercury | -3.932 |
Token | like |
Token ID | 588 |
Feature activation | -6.71e-03 |
Pos logit contributions | |
avage | +0.817 |
leck | +0.717 |
ghai | +0.695 |
anski | +0.677 |
Gat | +0.672 |
Neg logit contributions | |
Nept | -0.572 |
Reef | -0.538 |
oranges | -0.522 |
Ib | -0.517 |
Mercury | -0.500 |
Token | , |
Token ID | 11 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
avage | +0.089 |
leck | +0.078 |
ghai | +0.075 |
anski | +0.073 |
Gat | +0.072 |
Neg logit contributions | |
Nept | -0.073 |
Reef | -0.069 |
oranges | -0.067 |
Ib | -0.066 |
Mercury | -0.064 |
Token | you |
Token ID | 345 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
avage | +2.380 |
leck | +2.066 |
ghai | +1.986 |
anski | +1.939 |
Gat | +1.935 |
Neg logit contributions | |
Nept | -2.037 |
Reef | -1.929 |
oranges | -1.870 |
Ib | -1.862 |
Mercury | -1.806 |
Token | � |
Token ID | 447 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
avage | +1.800 |
leck | +1.561 |
ghai | +1.506 |
anski | +1.465 |
Gat | +1.461 |
Neg logit contributions | |
Nept | -1.511 |
Reef | -1.430 |
oranges | -1.385 |
Ib | -1.379 |
Mercury | -1.337 |
Token | � |
Token ID | 247 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Nept | +0.771 |
Reef | +0.746 |
Ib | +0.728 |
oranges | +0.724 |
Mercury | +0.707 |
Neg logit contributions | |
avage | -0.532 |
leck | -0.444 |
ghai | -0.422 |
anski | -0.409 |
Gat | -0.402 |
Token | G |
Token ID | 38 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
avage | +5.772 |
leck | +4.752 |
Gat | +4.737 |
GBT | +4.703 |
ghai | +4.512 |
Neg logit contributions | |
Nept | -8.603 |
oranges | -8.275 |
Reef | -8.065 |
sax | -7.885 |
adul | -7.876 |
Token | ED |
Token ID | 1961 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
avage | +1.947 |
leck | +1.687 |
ghai | +1.617 |
Gat | +1.588 |
anski | +1.577 |
Neg logit contributions | |
Nept | -1.600 |
Reef | -1.502 |
oranges | -1.477 |
Ib | -1.451 |
adul | -1.419 |
Token | NET |
Token ID | 30502 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
avage | +8.991 |
leck | +7.470 |
Gat | +7.376 |
Discover | +7.203 |
GBT | +7.066 |
Neg logit contributions | |
Nept | -8.376 |
oranges | -8.106 |
Reef | -7.928 |
adul | -7.729 |
Ib | -7.608 |
Token | CALL |
Token ID | 42815 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
avage | +5.101 |
Gat | +4.090 |
Discover | +4.055 |
leck | +3.977 |
TE | +3.810 |
Neg logit contributions | |
Nept | -8.247 |
oranges | -8.229 |
Reef | -7.735 |
adul | -7.706 |
sax | -7.672 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
avage | +2.677 |
leck | +2.138 |
ghai | +2.008 |
Gat | +1.951 |
anski | +1.920 |
Neg logit contributions | |
Nept | -4.538 |
Reef | -4.339 |
oranges | -4.285 |
Ib | -4.224 |
Mercury | -4.154 |
Token | : |
Token ID | 25 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Nept | +1.354 |
Reef | +1.280 |
Ib | +1.233 |
oranges | +1.215 |
Mercury | +1.197 |
Neg logit contributions | |
avage | -1.842 |
leck | -1.620 |
ghai | -1.566 |
anski | -1.525 |
Gat | -1.494 |
Token | 0 |
Token ID | 657 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
avage | +14.214 |
Gat | +12.465 |
Discover | +12.011 |
leck | +11.740 |
GBT | +11.585 |
Neg logit contributions | |
Nept | -15.791 |
oranges | -15.470 |
sax | -15.032 |
Reef | -14.862 |
adul | -14.659 |
Token | 551 |
Token ID | 43697 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
avage | +2.853 |
leck | +2.449 |
ghai | +2.359 |
Gat | +2.297 |
anski | +2.288 |
Neg logit contributions | |
Nept | -2.687 |
Reef | -2.559 |
oranges | -2.497 |
Ib | -2.461 |
adul | -2.410 |
Token | z |
Token ID | 89 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Nept | +2.958 |
Reef | +2.794 |
oranges | +2.741 |
Ib | +2.733 |
Mercury | +2.651 |
Neg logit contributions | |
avage | -2.815 |
leck | -2.391 |
ghai | -2.309 |
anski | -2.197 |
Gat | -2.186 |
Token | VOL |
Token ID | 38570 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
avage | +2.553 |
leck | +2.202 |
ghai | +2.115 |
Gat | +2.080 |
anski | +2.062 |
Neg logit contributions | |
Nept | -2.204 |
Reef | -2.087 |
oranges | -2.042 |
Ib | -2.008 |
adul | -1.957 |
Token | UN |
Token ID | 4944 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
avage | +2.686 |
leck | +2.349 |
ghai | +2.274 |
Gat | +2.229 |
anski | +2.213 |
Neg logit contributions | |
Nept | -1.912 |
Reef | -1.780 |
oranges | -1.748 |
Ib | -1.716 |
adul | -1.671 |
Token | ness |
Token ID | 1108 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
avage | +2.451 |
leck | +2.095 |
ghai | +2.009 |
Gat | +1.950 |
anski | +1.946 |
Neg logit contributions | |
Nept | -2.439 |
Reef | -2.327 |
oranges | -2.263 |
Ib | -2.241 |
Mercury | -2.183 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
avage | +0.343 |
leck | +0.295 |
ghai | +0.283 |
anski | +0.275 |
Gat | +0.272 |
Neg logit contributions | |
Nept | -0.344 |
Reef | -0.327 |
oranges | -0.318 |
Ib | -0.318 |
Mercury | -0.308 |
Token | � |
Token ID | 447 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
Nept | +0.317 |
Reef | +0.299 |
Ib | +0.292 |
oranges | +0.287 |
Mercury | +0.282 |
Neg logit contributions | |
avage | -0.363 |
leck | -0.316 |
ghai | -0.305 |
anski | -0.296 |
Gat | -0.289 |
Token | � |
Token ID | 251 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
Nept | +0.184 |
Reef | +0.177 |
Ib | +0.173 |
oranges | +0.172 |
Mercury | +0.167 |
Neg logit contributions | |
avage | -0.167 |
leck | -0.143 |
ghai | -0.136 |
anski | -0.134 |
Gat | -0.131 |
Token | ( |
Token ID | 357 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Nept | +0.977 |
Reef | +0.912 |
Ib | +0.896 |
oranges | +0.879 |
Mercury | +0.858 |
Neg logit contributions | |
avage | -1.375 |
leck | -1.210 |
ghai | -1.176 |
anski | -1.146 |
Gat | -1.118 |
Token | At |
Token ID | 2953 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
avage | +3.740 |
leck | +3.230 |
ghai | +3.080 |
Gat | +3.032 |
anski | +2.998 |
Neg logit contributions | |
Nept | -3.272 |
Reef | -3.112 |
oranges | -3.035 |
Ib | -2.967 |
adul | -2.931 |
Token | las |
Token ID | 21921 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
avage | +9.664 |
leck | +7.831 |
ghai | +6.889 |
Gat | +6.738 |
anski | +6.700 |
Neg logit contributions | |
Nept | -16.945 |
Reef | -16.589 |
defic | -16.214 |
Skydragon | -16.151 |
oranges | -15.994 |
Token | ) |
Token ID | 8 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Nept | +3.333 |
Reef | +3.102 |
Ib | +3.047 |
oranges | +3.026 |
Mercury | +2.962 |
Neg logit contributions | |
avage | -4.583 |
leck | -4.021 |
ghai | -3.957 |
anski | -3.839 |
Gat | -3.751 |
Token |
|
Token ID | 198 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
avage | +1.752 |
leck | +1.503 |
ghai | +1.441 |
Gat | +1.414 |
anski | +1.400 |
Neg logit contributions | |
Nept | -1.633 |
Reef | -1.545 |
oranges | -1.520 |
Ib | -1.489 |
adul | -1.454 |
Token |
|
Token ID | 198 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Nept | +1.084 |
Reef | +1.031 |
Ib | +0.996 |
oranges | +0.990 |
Mercury | +0.968 |
Neg logit contributions | |
avage | -1.303 |
leck | -1.137 |
ghai | -1.095 |
anski | -1.066 |
Gat | -1.053 |
Token | � |
Token ID | 447 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
avage | +5.518 |
leck | +4.720 |
ghai | +4.484 |
Gat | +4.437 |
sth | +4.428 |
Neg logit contributions | |
Nept | -5.062 |
Reef | -4.831 |
oranges | -4.729 |
Ib | -4.564 |
adul | -4.546 |
Token | for |
Token ID | 329 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
avage | +5.905 |
leck | +5.047 |
ghai | +4.864 |
Gat | +4.842 |
anski | +4.751 |
Neg logit contributions | |
Nept | -5.275 |
Reef | -5.071 |
oranges | -4.866 |
Ib | -4.803 |
Norn | -4.740 |
Token | Slovakia |
Token ID | 36839 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
avage | +12.596 |
Gat | +10.896 |
leck | +10.798 |
anski | +10.344 |
ghai | +10.208 |
Neg logit contributions | |
Nept | -10.235 |
Reef | -9.360 |
oranges | -9.352 |
adul | -9.270 |
sax | -8.967 |
Token | in |
Token ID | 287 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
avage | +7.952 |
leck | +6.798 |
Gat | +6.648 |
ghai | +6.595 |
anski | +6.477 |
Neg logit contributions | |
Nept | -7.289 |
Reef | -6.969 |
oranges | -6.781 |
Ib | -6.564 |
adul | -6.541 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
avage | +8.148 |
leck | +6.937 |
Gat | +6.719 |
ghai | +6.608 |
anski | +6.522 |
Neg logit contributions | |
Nept | -7.327 |
Reef | -6.970 |
oranges | -6.689 |
Norn | -6.548 |
adul | -6.471 |
Token | 13 |
Token ID | 1511 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
avage | +12.946 |
leck | +11.265 |
Gat | +11.009 |
Discover | +10.783 |
ghai | +10.706 |
Neg logit contributions | |
Nept | -8.918 |
Reef | -8.313 |
oranges | -8.162 |
adul | -7.877 |
Norn | -7.834 |
Token | th |
Token ID | 400 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
avage | +8.644 |
leck | +7.385 |
sth | +6.919 |
ghai | +6.912 |
Gat | +6.869 |
Neg logit contributions | |
Nept | -8.887 |
Reef | -8.318 |
adul | -8.003 |
oranges | -7.925 |
Ib | -7.895 |
Token | minute |
Token ID | 5664 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
avage | +12.907 |
leck | +10.582 |
Gat | +10.170 |
ghai | +10.058 |
Discover | +9.580 |
Neg logit contributions | |
Nept | -15.766 |
Reef | -14.609 |
oranges | -14.595 |
adul | -14.163 |
sax | -13.735 |
Token | when |
Token ID | 618 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
avage | +9.041 |
leck | +7.578 |
Gat | +7.362 |
ghai | +7.291 |
Discover | +6.986 |
Neg logit contributions | |
Nept | -9.670 |
Reef | -9.267 |
oranges | -8.989 |
Norn | -8.834 |
Ib | -8.658 |
Token | his |
Token ID | 465 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
avage | +3.776 |
leck | +3.263 |
ghai | +3.142 |
Gat | +3.094 |
anski | +3.077 |
Neg logit contributions | |
Nept | -3.223 |
Reef | -3.046 |
oranges | -2.963 |
Ib | -2.901 |
adul | -2.845 |
Token | effort |
Token ID | 3626 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
avage | +5.810 |
leck | +4.986 |
ghai | +4.847 |
Gat | +4.823 |
anski | +4.749 |
Neg logit contributions | |
Nept | -4.593 |
Reef | -4.327 |
oranges | -4.164 |
Norn | -4.076 |
Ib | -4.043 |
Token | hit |
Token ID | 2277 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
avage | +5.816 |
leck | +5.061 |
ghai | +4.900 |
Gat | +4.860 |
anski | +4.755 |
Neg logit contributions | |
Nept | -4.439 |
Reef | -4.206 |
oranges | -4.025 |
Norn | -3.919 |
Ib | -3.912 |
Token | all |
Token ID | 477 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
avage | +2.224 |
leck | +1.941 |
ghai | +1.876 |
Gat | +1.825 |
anski | +1.822 |
Neg logit contributions | |
Nept | -1.713 |
Reef | -1.617 |
oranges | -1.568 |
Ib | -1.556 |
Mercury | -1.507 |
Token | this |
Token ID | 428 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
avage | +1.403 |
leck | +1.227 |
ghai | +1.185 |
anski | +1.154 |
Gat | +1.149 |
Neg logit contributions | |
Nept | -1.063 |
Reef | -1.003 |
oranges | -0.971 |
Ib | -0.965 |
Mercury | -0.936 |
Token | wonderful |
Token ID | 7932 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
avage | +4.595 |
leck | +3.975 |
ghai | +3.861 |
Gat | +3.805 |
anski | +3.718 |
Neg logit contributions | |
Nept | -3.792 |
Reef | -3.593 |
oranges | -3.482 |
Ib | -3.441 |
Norn | -3.342 |
Token | choice |
Token ID | 3572 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
avage | +3.698 |
leck | +3.184 |
ghai | +3.092 |
Gat | +3.040 |
anski | +2.975 |
Neg logit contributions | |
Nept | -3.159 |
Reef | -2.991 |
oranges | -2.923 |
Ib | -2.886 |
adul | -2.792 |
Token | you |
Token ID | 345 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
avage | +3.551 |
leck | +3.062 |
ghai | +2.968 |
Gat | +2.887 |
anski | +2.857 |
Neg logit contributions | |
Nept | -3.070 |
Reef | -2.906 |
oranges | -2.824 |
Ib | -2.795 |
adul | -2.711 |
Token | now |
Token ID | 783 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
avage | +4.862 |
leck | +4.106 |
ghai | +3.996 |
Gat | +3.933 |
anski | +3.881 |
Neg logit contributions | |
Nept | -4.584 |
Reef | -4.365 |
oranges | -4.199 |
Ib | -4.160 |
Norn | -4.070 |
Token | have |
Token ID | 423 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
avage | +10.641 |
Discover | +8.691 |
ghai | +8.507 |
leck | +8.369 |
Gat | +8.231 |
Neg logit contributions | |
Nept | -13.073 |
Reef | -12.703 |
Norn | -11.910 |
oranges | -11.792 |
Skydragon | -11.781 |
Token | . |
Token ID | 13 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
avage | +6.045 |
leck | +5.251 |
ghai | +5.051 |
Gat | +4.972 |
anski | +4.858 |
Neg logit contributions | |
Nept | -5.277 |
Reef | -4.986 |
oranges | -4.831 |
Ib | -4.781 |
Norn | -4.653 |
Token | The |
Token ID | 383 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Nept | +0.064 |
Reef | +0.060 |
Ib | +0.058 |
oranges | +0.058 |
Mercury | +0.057 |
Neg logit contributions | |
avage | -0.079 |
leck | -0.069 |
ghai | -0.066 |
anski | -0.065 |
Gat | -0.063 |
Token | schedule |
Token ID | 7269 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
avage | +5.226 |
leck | +4.571 |
ghai | +4.400 |
Gat | +4.388 |
anski | +4.292 |
Neg logit contributions | |
Nept | -3.868 |
Reef | -3.647 |
oranges | -3.562 |
Ib | -3.502 |
adul | -3.400 |
Token | is |
Token ID | 318 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
avage | +5.402 |
leck | +4.698 |
ghai | +4.519 |
Gat | +4.446 |
anski | +4.392 |
Neg logit contributions | |
Nept | -4.316 |
Reef | -4.070 |
oranges | -3.929 |
Ib | -3.912 |
Norn | -3.796 |
Token | men |
Token ID | 1450 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
avage | +4.027 |
leck | +3.498 |
ghai | +3.378 |
Gat | +3.366 |
anski | +3.321 |
Neg logit contributions | |
Nept | -2.889 |
Reef | -2.728 |
oranges | -2.637 |
Ib | -2.631 |
Norn | -2.555 |
Token | ( |
Token ID | 357 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
Nept | +2.143 |
Reef | +2.025 |
oranges | +1.950 |
Ib | +1.937 |
Mercury | +1.893 |
Neg logit contributions | |
avage | -3.104 |
leck | -2.775 |
ghai | -2.641 |
anski | -2.593 |
Gat | -2.549 |
Token | 56 |
Token ID | 3980 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
avage | +5.490 |
leck | +4.713 |
ghai | +4.531 |
anski | +4.404 |
Gat | +4.389 |
Neg logit contributions | |
Nept | -4.795 |
Reef | -4.514 |
oranges | -4.399 |
Ib | -4.348 |
adul | -4.245 |
Token | % |
Token ID | 4 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
avage | +3.658 |
leck | +2.860 |
ghai | +2.675 |
anski | +2.594 |
Gat | +2.592 |
Neg logit contributions | |
Nept | -6.288 |
Reef | -6.077 |
oranges | -5.880 |
Ib | -5.861 |
adul | -5.782 |
Token | support |
Token ID | 1104 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
avage | +8.599 |
leck | +7.169 |
ghai | +6.903 |
Gat | +6.810 |
anski | +6.771 |
Neg logit contributions | |
Nept | -7.574 |
Reef | -7.078 |
oranges | -7.007 |
Ib | -6.880 |
Norn | -6.768 |
Token | to |
Token ID | 284 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
avage | +12.709 |
leck | +10.539 |
Gat | +10.163 |
sth | +10.097 |
anski | +9.981 |
Neg logit contributions | |
Nept | -11.850 |
Reef | -10.866 |
oranges | -10.805 |
Ib | -10.602 |
Norn | -10.586 |
Token | 41 |
Token ID | 6073 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
avage | +14.105 |
Gat | +12.708 |
leck | +12.570 |
Discover | +12.015 |
anski | +11.796 |
Neg logit contributions | |
Nept | -8.517 |
Reef | -7.694 |
oranges | -7.669 |
Û | -7.396 |
Skydragon | -7.342 |
Token | % |
Token ID | 4 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
avage | +6.977 |
leck | +4.521 |
Gat | +4.292 |
Discover | +4.212 |
anski | +4.207 |
Neg logit contributions | |
Nept | -17.002 |
Reef | -16.480 |
oranges | -15.814 |
sax | -15.663 |
Ib | -15.650 |
Token | opposed |
Token ID | 6886 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
avage | +8.311 |
leck | +7.063 |
ghai | +6.754 |
anski | +6.648 |
Gat | +6.605 |
Neg logit contributions | |
Nept | -6.468 |
Reef | -6.032 |
oranges | -5.947 |
Ib | -5.849 |
Norn | -5.739 |
Token | ), |
Token ID | 828 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
avage | +7.756 |
leck | +6.508 |
Gat | +5.986 |
anski | +5.984 |
ghai | +5.956 |
Neg logit contributions | |
Nept | -8.865 |
Reef | -8.352 |
oranges | -8.160 |
Ib | -8.096 |
Norn | -7.957 |
Token | but |
Token ID | 475 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
avage | +6.785 |
leck | +5.853 |
Gat | +5.617 |
ghai | +5.593 |
anski | +5.498 |
Neg logit contributions | |
Nept | -5.439 |
Reef | -5.165 |
Ib | -4.981 |
oranges | -4.938 |
Norn | -4.864 |