Token | 2008 |
Token ID | 3648 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
gypt | +4.648 |
Bees | +3.387 |
bee | +3.320 |
wana | +3.229 |
gar | +3.224 |
Neg logit contributions | |
Vi | -6.163 |
MMA | -6.140 |
Priv | -6.076 |
LX | -5.898 |
MV | -5.786 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
gypt | +0.776 |
bee | +0.627 |
Bees | +0.616 |
gar | +0.612 |
wana | +0.604 |
Neg logit contributions | |
MMA | -0.533 |
Vi | -0.530 |
Priv | -0.519 |
LX | -0.497 |
MV | -0.482 |
Token | 4 |
Token ID | 604 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
MMA | +1.092 |
Vi | +1.083 |
Priv | +1.037 |
LX | +1.012 |
MV | +0.980 |
Neg logit contributions | |
gypt | -1.771 |
bee | -1.426 |
Bees | -1.403 |
gar | -1.400 |
wana | -1.396 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
gypt | +5.673 |
Bees | +4.103 |
bee | +4.036 |
wana | +3.836 |
gar | +3.791 |
Neg logit contributions | |
MMA | -8.603 |
Vi | -8.566 |
Priv | -8.543 |
LX | -8.302 |
Orn | -8.109 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
gypt | +3.141 |
bee | +2.553 |
Bees | +2.496 |
gar | +2.478 |
wana | +2.406 |
Neg logit contributions | |
MMA | -2.423 |
Priv | -2.416 |
Vi | -2.410 |
LX | -2.274 |
シャ | -2.246 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
MMA | +1.747 |
Vi | +1.730 |
Priv | +1.638 |
LX | +1.615 |
MV | +1.565 |
Neg logit contributions | |
gypt | -2.981 |
bee | -2.404 |
Bees | -2.361 |
wana | -2.359 |
gar | -2.358 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +9.65e-02 |
Pos logit contributions | |
gypt | +8.007 |
Bees | +6.059 |
wana | +5.870 |
bee | +5.802 |
gar | +5.595 |
Neg logit contributions | |
Priv | -9.963 |
Vi | -9.869 |
MMA | -9.772 |
LX | -9.649 |
シャ | -9.379 |
Token | 12 |
Token ID | 1105 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
gypt | +0.927 |
bee | +0.745 |
Bees | +0.732 |
gar | +0.729 |
wana | +0.717 |
Neg logit contributions | |
MMA | -0.678 |
Vi | -0.674 |
Priv | -0.660 |
LX | -0.634 |
MV | -0.616 |
Token | 2 |
Token ID | 362 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
MMA | +1.888 |
Vi | +1.868 |
Priv | +1.758 |
LX | +1.743 |
MV | +1.689 |
Neg logit contributions | |
gypt | -3.346 |
bee | -2.703 |
wana | -2.662 |
Bees | -2.656 |
gar | -2.652 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
gypt | +2.287 |
bee | +1.766 |
Bees | +1.746 |
wana | +1.731 |
gar | +1.710 |
Neg logit contributions | |
MMA | -2.130 |
Vi | -2.120 |
Priv | -2.090 |
LX | -2.031 |
MV | -1.970 |
Token | 6 |
Token ID | 718 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
gypt | +0.981 |
bee | +0.793 |
Bees | +0.779 |
gar | +0.776 |
wana | +0.764 |
Neg logit contributions | |
MMA | -0.674 |
Vi | -0.671 |
Priv | -0.657 |
LX | -0.630 |
MV | -0.611 |
Token | oub |
Token ID | 12944 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
gypt | +4.402 |
bee | +3.493 |
gar | +3.411 |
wana | +3.380 |
Bees | +3.345 |
Neg logit contributions | |
Vi | -3.576 |
MMA | -3.537 |
Priv | -3.391 |
LX | -3.384 |
MV | -3.279 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
gypt | +7.492 |
bee | +5.940 |
wana | +5.841 |
Bees | +5.831 |
gar | +5.808 |
Neg logit contributions | |
MMA | -6.497 |
Vi | -6.467 |
Priv | -6.453 |
LX | -6.234 |
MV | -6.021 |
Token |
|
Token ID | 198 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
gypt | +1.536 |
bee | +1.229 |
gar | +1.204 |
Bees | +1.193 |
wana | +1.183 |
Neg logit contributions | |
MMA | -1.217 |
Vi | -1.216 |
Priv | -1.173 |
LX | -1.156 |
MV | -1.115 |
Token | 2009 |
Token ID | 10531 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
gypt | +3.470 |
bee | +2.453 |
gar | +2.346 |
wana | +2.344 |
Bees | +2.318 |
Neg logit contributions | |
MMA | -5.310 |
Vi | -5.295 |
LX | -5.120 |
Priv | -5.076 |
MV | -4.963 |
Token | Charlie |
Token ID | 11526 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
gypt | +2.726 |
bee | +2.176 |
Bees | +2.157 |
gar | +2.113 |
wana | +2.100 |
Neg logit contributions | |
MMA | -2.192 |
Vi | -2.161 |
Priv | -2.138 |
LX | -2.063 |
MV | -2.000 |
Token | Sheen |
Token ID | 50189 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
gypt | +2.937 |
bee | +2.281 |
Bees | +2.272 |
wana | +2.219 |
gar | +2.211 |
Neg logit contributions | |
MMA | -2.860 |
Vi | -2.815 |
Priv | -2.787 |
LX | -2.701 |
MV | -2.632 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
gypt | +8.409 |
bee | +6.439 |
wana | +6.418 |
Bees | +6.381 |
gar | +6.328 |
Neg logit contributions | |
Priv | -9.138 |
MMA | -9.020 |
Vi | -8.956 |
LX | -8.747 |
ネ | -8.591 |
Token | Jim |
Token ID | 5395 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
MMA | +1.403 |
Vi | +1.395 |
Priv | +1.329 |
LX | +1.308 |
MV | +1.277 |
Neg logit contributions | |
gypt | -1.785 |
bee | -1.388 |
gar | -1.364 |
wana | -1.361 |
Bees | -1.356 |
Token | Parsons |
Token ID | 35925 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
gypt | +2.276 |
bee | +1.854 |
Bees | +1.829 |
gar | +1.825 |
wana | +1.793 |
Neg logit contributions | |
MMA | -1.613 |
Vi | -1.569 |
Priv | -1.567 |
LX | -1.502 |
MV | -1.468 |
Token |
|
Token ID | 198 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
gypt | +4.937 |
bee | +4.020 |
gar | +3.934 |
Bees | +3.821 |
wana | +3.767 |
Neg logit contributions | |
Vi | -4.698 |
MMA | -4.617 |
Priv | -4.556 |
LX | -4.505 |
emort | -4.398 |
Token |
|
Token ID | 198 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
gypt | +1.948 |
bee | +1.562 |
gar | +1.530 |
Bees | +1.510 |
wana | +1.499 |
Neg logit contributions | |
Vi | -1.568 |
MMA | -1.566 |
Priv | -1.510 |
LX | -1.493 |
MV | -1.439 |
Token | Fight |
Token ID | 10480 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
gypt | +2.800 |
bee | +2.239 |
Bees | +2.208 |
gar | +2.190 |
wana | +2.152 |
Neg logit contributions | |
MMA | -2.155 |
Vi | -2.130 |
Priv | -2.083 |
LX | -2.016 |
MV | -1.963 |
Token | With |
Token ID | 2080 |
Feature activation | -4.53e-03 |
Pos logit contributions | |
MMA | +0.246 |
Vi | +0.244 |
Priv | +0.235 |
LX | +0.231 |
MV | +0.224 |
Neg logit contributions | |
gypt | -0.305 |
bee | -0.238 |
Bees | -0.234 |
gar | -0.233 |
wana | -0.233 |
Token | Each |
Token ID | 5501 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
MMA | +0.033 |
Vi | +0.033 |
Priv | +0.032 |
LX | +0.031 |
MV | +0.030 |
Neg logit contributions | |
gypt | -0.043 |
bee | -0.034 |
Bees | -0.033 |
gar | -0.033 |
wana | -0.033 |
Token | other |
Token ID | 847 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
MMA | +1.126 |
Vi | +1.111 |
Priv | +1.067 |
LX | +1.048 |
MV | +1.028 |
Neg logit contributions | |
gypt | -1.290 |
bee | -0.991 |
wana | -0.977 |
Bees | -0.968 |
gar | -0.967 |
Token | 200 |
Token ID | 939 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
gypt | +2.899 |
bee | +2.269 |
Bees | +2.234 |
gar | +2.221 |
wana | +2.199 |
Neg logit contributions | |
MMA | -2.494 |
Vi | -2.482 |
Priv | -2.403 |
LX | -2.354 |
MV | -2.283 |
Token | 80 |
Token ID | 1795 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
gypt | +1.175 |
bee | +0.934 |
Bees | +0.914 |
gar | +0.913 |
wana | +0.910 |
Neg logit contributions | |
MMA | -0.829 |
Vi | -0.825 |
Priv | -0.788 |
LX | -0.774 |
MV | -0.751 |
Token | 205 |
Token ID | 21261 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
gypt | +6.286 |
bee | +4.999 |
gar | +4.777 |
Bees | +4.430 |
gee | +4.370 |
Neg logit contributions | |
MMA | -11.127 |
Vi | -11.036 |
LX | -10.800 |
emort | -10.730 |
arij | -10.656 |
Token | O |
Token ID | 440 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
MMA | +0.611 |
Vi | +0.608 |
Priv | +0.581 |
LX | +0.559 |
MV | +0.536 |
Neg logit contributions | |
gypt | -1.304 |
bee | -1.079 |
Bees | -1.066 |
gar | -1.059 |
wana | -1.055 |
Token | & |
Token ID | 5 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
gypt | +0.192 |
bee | +0.152 |
gar | +0.149 |
Bees | +0.149 |
wana | +0.148 |
Neg logit contributions | |
MMA | -0.140 |
Vi | -0.139 |
Priv | -0.133 |
LX | -0.131 |
MV | -0.127 |
Token | A |
Token ID | 32 |
Feature activation | -8.10e-03 |
Pos logit contributions | |
gypt | +1.961 |
bee | +1.503 |
gar | +1.467 |
Bees | +1.462 |
wana | +1.445 |
Neg logit contributions | |
MMA | -2.030 |
Vi | -2.029 |
Priv | -1.947 |
LX | -1.933 |
MV | -1.878 |
Token | - |
Token ID | 12 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
MMA | +0.060 |
Vi | +0.059 |
Priv | +0.057 |
LX | +0.056 |
MV | +0.054 |
Neg logit contributions | |
gypt | -0.077 |
bee | -0.061 |
Bees | -0.059 |
gar | -0.059 |
wana | -0.059 |
Token | practice |
Token ID | 3357 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
gypt | +2.265 |
bee | +1.803 |
gar | +1.769 |
Bees | +1.766 |
gars | +1.723 |
Neg logit contributions | |
MMA | -1.798 |
Vi | -1.781 |
Priv | -1.750 |
LX | -1.720 |
MV | -1.648 |
Token | when |
Token ID | 618 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
gypt | +1.550 |
bee | +1.246 |
gar | +1.220 |
Bees | +1.215 |
wana | +1.214 |
Neg logit contributions | |
MMA | -1.036 |
Vi | -1.036 |
Priv | -1.005 |
LX | -0.981 |
MV | -0.941 |
Token | cornerback |
Token ID | 26683 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
gypt | +1.235 |
bee | +0.978 |
Bees | +0.963 |
gar | +0.955 |
wana | +0.941 |
Neg logit contributions | |
MMA | -0.951 |
Vi | -0.937 |
Priv | -0.923 |
LX | -0.898 |
MV | -0.865 |
Token | A |
Token ID | 317 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
MMA | +1.014 |
Vi | +1.010 |
Priv | +0.962 |
LX | +0.947 |
MV | +0.923 |
Neg logit contributions | |
gypt | -1.282 |
bee | -0.998 |
gar | -0.981 |
wana | -0.981 |
Bees | -0.979 |
Token | q |
Token ID | 80 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
gypt | +0.180 |
bee | +0.146 |
gar | +0.143 |
Bees | +0.142 |
wana | +0.142 |
Neg logit contributions | |
MMA | -0.113 |
Vi | -0.111 |
Priv | -0.107 |
LX | -0.104 |
MV | -0.101 |
Token | ib |
Token ID | 571 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
gypt | +2.496 |
bee | +1.755 |
gar | +1.711 |
wana | +1.663 |
gars | +1.652 |
Neg logit contributions | |
MMA | -3.957 |
Vi | -3.948 |
LX | -3.829 |
Priv | -3.828 |
MV | -3.727 |
Token | Tal |
Token ID | 7193 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
gypt | +7.342 |
bee | +5.961 |
Bib | +5.897 |
Bees | +5.691 |
gar | +5.575 |
Neg logit contributions | |
Priv | -10.312 |
LX | -9.929 |
MMA | -9.760 |
シャ | -9.733 |
ゼ | -9.719 |
Token | ib |
Token ID | 571 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
gypt | +1.266 |
gar | +0.886 |
bee | +0.879 |
wana | +0.868 |
Bees | +0.852 |
Neg logit contributions | |
MMA | -2.137 |
Priv | -2.128 |
Vi | -2.117 |
LX | -2.087 |
MV | -2.030 |
Token | jumped |
Token ID | 11687 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
gypt | +3.221 |
bee | +2.566 |
gar | +2.513 |
wana | +2.490 |
Bees | +2.477 |
Neg logit contributions | |
Vi | -2.440 |
MMA | -2.435 |
Priv | -2.414 |
LX | -2.350 |
MV | -2.249 |
Token | an |
Token ID | 281 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
gypt | +1.901 |
bee | +1.514 |
Bees | +1.488 |
gar | +1.482 |
wana | +1.451 |
Neg logit contributions | |
MMA | -1.468 |
Vi | -1.445 |
Priv | -1.430 |
LX | -1.397 |
MV | -1.343 |
Token | out |
Token ID | 503 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
MMA | +2.141 |
Vi | +2.114 |
Priv | +2.025 |
LX | +1.990 |
MV | +1.943 |
Neg logit contributions | |
gypt | -2.809 |
bee | -2.210 |
Bees | -2.171 |
wana | -2.164 |
gar | -2.164 |
Token | of |
Token ID | 286 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
gypt | +4.201 |
bee | +3.341 |
wana | +3.276 |
Bees | +3.265 |
gar | +3.260 |
Neg logit contributions | |
MMA | -3.101 |
Vi | -3.070 |
Priv | -3.022 |
LX | -2.905 |
MV | -2.810 |
Token | collagen |
Token ID | 45452 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
gypt | +2.831 |
bee | +2.221 |
Bees | +2.201 |
gar | +2.177 |
wana | +2.177 |
Neg logit contributions | |
Vi | -2.180 |
MMA | -2.176 |
Priv | -2.164 |
LX | -2.058 |
MV | -1.985 |
Token | and |
Token ID | 290 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
gypt | +0.347 |
bee | +0.271 |
Bees | +0.266 |
gar | +0.265 |
wana | +0.264 |
Neg logit contributions | |
MMA | -0.285 |
Vi | -0.283 |
Priv | -0.275 |
LX | -0.268 |
MV | -0.260 |
Token | bio |
Token ID | 13401 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
gypt | +0.480 |
bee | +0.377 |
Bees | +0.372 |
gar | +0.370 |
wana | +0.368 |
Neg logit contributions | |
MMA | -0.370 |
Vi | -0.368 |
Priv | -0.357 |
LX | -0.347 |
MV | -0.337 |
Token | ap |
Token ID | 499 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
MMA | +1.024 |
Vi | +1.017 |
Priv | +0.981 |
LX | +0.962 |
MV | +0.939 |
Neg logit contributions | |
gypt | -1.140 |
bee | -0.878 |
Bees | -0.862 |
gar | -0.858 |
wana | -0.856 |
Token | at |
Token ID | 265 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
MMA | +1.919 |
Vi | +1.910 |
Priv | +1.853 |
LX | +1.826 |
MV | +1.789 |
Neg logit contributions | |
gypt | -1.416 |
bee | -1.016 |
Bees | -0.992 |
gar | -0.979 |
wana | -0.978 |
Token | ite |
Token ID | 578 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
gypt | +7.347 |
Bees | +5.241 |
bee | +5.215 |
gar | +5.198 |
wana | +5.070 |
Neg logit contributions | |
Priv | -10.219 |
MMA | -10.146 |
Vi | -10.061 |
LX | -9.890 |
MV | -9.575 |
Token | ( |
Token ID | 357 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
gypt | +3.102 |
bee | +2.437 |
Bees | +2.409 |
gar | +2.399 |
wana | +2.389 |
Neg logit contributions | |
MMA | -2.261 |
Vi | -2.245 |
Priv | -2.211 |
LX | -2.118 |
MV | -2.047 |
Token | hard |
Token ID | 10424 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
gypt | +0.866 |
bee | +0.678 |
gar | +0.664 |
Bees | +0.659 |
wana | +0.658 |
Neg logit contributions | |
MMA | -0.730 |
Vi | -0.726 |
Priv | -0.699 |
LX | -0.688 |
MV | -0.668 |
Token | carbon |
Token ID | 6588 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
gypt | +0.266 |
bee | +0.212 |
gar | +0.209 |
Bees | +0.208 |
wana | +0.207 |
Neg logit contributions | |
MMA | -0.188 |
Vi | -0.187 |
Priv | -0.181 |
LX | -0.176 |
MV | -0.170 |
Token | ate |
Token ID | 378 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
MMA | +2.473 |
Vi | +2.414 |
LX | +2.284 |
Priv | +2.279 |
MV | +2.228 |
Neg logit contributions | |
gypt | -3.409 |
bee | -2.672 |
wana | -2.635 |
gar | -2.620 |
Bees | -2.619 |
Token | Cons |
Token ID | 9444 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
gypt | +0.636 |
bee | +0.493 |
gar | +0.482 |
Bees | +0.481 |
wana | +0.475 |
Neg logit contributions | |
MMA | -0.585 |
Vi | -0.583 |
Priv | -0.557 |
LX | -0.555 |
MV | -0.538 |
Token | piracy |
Token ID | 8703 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
MMA | +1.906 |
Vi | +1.894 |
Priv | +1.827 |
LX | +1.790 |
MV | +1.744 |
Neg logit contributions | |
gypt | -2.302 |
bee | -1.796 |
Bees | -1.762 |
gar | -1.758 |
wana | -1.751 |
Token | The |
Token ID | 383 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
gypt | +0.335 |
bee | +0.263 |
Bees | +0.260 |
gar | +0.258 |
wana | +0.255 |
Neg logit contributions | |
MMA | -0.268 |
Vi | -0.266 |
Priv | -0.260 |
LX | -0.252 |
MV | -0.244 |
Token | ories |
Token ID | 1749 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
MMA | +0.950 |
Vi | +0.942 |
Priv | +0.897 |
LX | +0.873 |
MV | +0.842 |
Neg logit contributions | |
gypt | -1.806 |
bee | -1.474 |
Bees | -1.451 |
gar | -1.448 |
wana | -1.444 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
gypt | +3.540 |
bee | +2.736 |
Bees | +2.714 |
gar | +2.666 |
wana | +2.652 |
Neg logit contributions | |
MMA | -3.269 |
Vi | -3.247 |
Priv | -3.167 |
LX | -3.098 |
MV | -3.005 |
Token | 01 |
Token ID | 486 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
MMA | +0.963 |
Vi | +0.957 |
Priv | +0.922 |
LX | +0.904 |
MV | +0.880 |
Neg logit contributions | |
gypt | -1.160 |
bee | -0.904 |
Bees | -0.887 |
gar | -0.885 |
wana | -0.882 |
Token | 30 |
Token ID | 1270 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
gypt | +8.690 |
bee | +6.943 |
gar | +6.622 |
gee | +6.558 |
Bees | +6.444 |
Neg logit contributions | |
Vi | -8.588 |
MMA | -8.283 |
LX | -8.122 |
MV | -7.941 |
Priv | -7.852 |
Token | O |
Token ID | 440 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
MMA | +0.971 |
Vi | +0.961 |
Priv | +0.909 |
LX | +0.884 |
MV | +0.849 |
Neg logit contributions | |
gypt | -2.156 |
bee | -1.778 |
Bees | -1.751 |
gar | -1.749 |
wana | -1.745 |
Token | & |
Token ID | 5 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
MMA | +0.099 |
Vi | +0.099 |
Priv | +0.095 |
LX | +0.093 |
MV | +0.090 |
Neg logit contributions | |
gypt | -0.138 |
bee | -0.109 |
Bees | -0.107 |
gar | -0.107 |
wana | -0.107 |
Token | A |
Token ID | 32 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
gypt | +1.958 |
bee | +1.503 |
gar | +1.466 |
Bees | +1.461 |
wana | +1.442 |
Neg logit contributions | |
MMA | -2.039 |
Vi | -2.038 |
Priv | -1.955 |
LX | -1.943 |
MV | -1.886 |
Token | - |
Token ID | 12 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
gypt | +0.270 |
bee | +0.213 |
Bees | +0.209 |
gar | +0.209 |
wana | +0.207 |
Neg logit contributions | |
MMA | -0.212 |
Vi | -0.211 |
Priv | -0.203 |
LX | -0.199 |
MV | -0.193 |
Token | emin |
Token ID | 14857 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
gypt | +1.637 |
bee | +1.281 |
gar | +1.265 |
Bees | +1.250 |
wana | +1.249 |
Neg logit contributions | |
MMA | -1.360 |
Vi | -1.350 |
Priv | -1.303 |
LX | -1.290 |
MV | -1.245 |
Token | ism |
Token ID | 1042 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
gypt | +1.146 |
bee | +0.930 |
gar | +0.919 |
Bees | +0.917 |
wana | +0.903 |
Neg logit contributions | |
MMA | -0.693 |
Vi | -0.690 |
Priv | -0.664 |
LX | -0.651 |
MV | -0.631 |
Token | In |
Token ID | 554 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
gypt | +2.281 |
bee | +1.802 |
Bees | +1.783 |
gar | +1.771 |
wana | +1.752 |
Neg logit contributions | |
MMA | -1.801 |
Vi | -1.785 |
Priv | -1.741 |
LX | -1.694 |
MV | -1.645 |
Token | 08 |
Token ID | 8487 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
MMA | +0.798 |
Vi | +0.792 |
Priv | +0.762 |
LX | +0.746 |
MV | +0.725 |
Neg logit contributions | |
gypt | -1.066 |
bee | -0.841 |
Bees | -0.826 |
gar | -0.824 |
wana | -0.821 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
gypt | +0.839 |
bee | +0.659 |
Bees | +0.646 |
gar | +0.645 |
wana | +0.644 |
Neg logit contributions | |
MMA | -0.653 |
Vi | -0.648 |
Priv | -0.623 |
LX | -0.610 |
MV | -0.594 |
Token | 01 |
Token ID | 486 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
MMA | +0.931 |
Vi | +0.925 |
Priv | +0.892 |
LX | +0.874 |
MV | +0.849 |
Neg logit contributions | |
gypt | -1.139 |
bee | -0.887 |
Bees | -0.873 |
gar | -0.869 |
wana | -0.868 |
Token | 29 |
Token ID | 1959 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
gypt | +7.670 |
bee | +6.029 |
Bees | +5.717 |
gar | +5.666 |
gars | +5.555 |
Neg logit contributions | |
Vi | -9.001 |
MMA | -8.783 |
LX | -8.589 |
Priv | -8.422 |
Orn | -8.357 |
Token | O |
Token ID | 440 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
MMA | +0.096 |
Vi | +0.096 |
Priv | +0.093 |
LX | +0.088 |
MV | +0.085 |
Neg logit contributions | |
gypt | -0.200 |
bee | -0.166 |
Bees | -0.164 |
gar | -0.162 |
wana | -0.161 |
Token | & |
Token ID | 5 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
gypt | +0.360 |
bee | +0.286 |
gar | +0.280 |
Bees | +0.280 |
wana | +0.278 |
Neg logit contributions | |
MMA | -0.265 |
Vi | -0.264 |
Priv | -0.253 |
LX | -0.248 |
MV | -0.241 |
Token | A |
Token ID | 32 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
gypt | +2.623 |
bee | +2.024 |
gar | +1.973 |
Bees | +1.957 |
wana | +1.922 |
Neg logit contributions | |
Vi | -2.865 |
MMA | -2.854 |
LX | -2.736 |
Priv | -2.733 |
MV | -2.648 |
Token | - |
Token ID | 12 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
gypt | +0.713 |
bee | +0.564 |
Bees | +0.552 |
gar | +0.551 |
wana | +0.545 |
Neg logit contributions | |
MMA | -0.570 |
Vi | -0.568 |
Priv | -0.548 |
LX | -0.537 |
MV | -0.521 |
Token | of |
Token ID | 286 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
MMA | +0.267 |
Vi | +0.264 |
Priv | +0.253 |
LX | +0.245 |
MV | +0.239 |
Neg logit contributions | |
gypt | -0.459 |
bee | -0.371 |
Bees | -0.365 |
wana | -0.364 |
gar | -0.363 |
Token | " |
Token ID | 366 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
gypt | +0.864 |
bee | +0.674 |
Bees | +0.661 |
gar | +0.659 |
wana | +0.657 |
Neg logit contributions | |
MMA | -0.716 |
Vi | -0.712 |
Priv | -0.687 |
LX | -0.673 |
MV | -0.655 |
Token | off |
Token ID | 2364 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
MMA | +1.424 |
Vi | +1.414 |
Priv | +1.376 |
LX | +1.332 |
MV | +1.306 |
Neg logit contributions | |
gypt | -1.620 |
bee | -1.242 |
Bees | -1.230 |
wana | -1.212 |
gar | -1.210 |
Token | - |
Token ID | 12 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
gypt | +3.721 |
bee | +2.912 |
gar | +2.869 |
Bees | +2.850 |
wana | +2.810 |
Neg logit contributions | |
MMA | -3.126 |
Vi | -3.107 |
Priv | -3.016 |
LX | -2.959 |
MV | -2.870 |
Token | the |
Token ID | 1169 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
gypt | +3.093 |
bee | +2.470 |
gar | +2.437 |
Bees | +2.401 |
wana | +2.395 |
Neg logit contributions | |
MMA | -2.244 |
Vi | -2.232 |
Priv | -2.126 |
LX | -2.107 |
MV | -2.038 |
Token | - |
Token ID | 12 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
gypt | +5.167 |
bee | +4.092 |
gar | +3.994 |
Bees | +3.882 |
wana | +3.817 |
Neg logit contributions | |
Vi | -4.938 |
MMA | -4.899 |
Priv | -4.852 |
LX | -4.703 |
MV | -4.538 |
Token | record |
Token ID | 22105 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
gypt | +6.773 |
bee | +5.271 |
gar | +5.238 |
hops | +4.805 |
gee | +4.721 |
Neg logit contributions | |
Vi | -9.809 |
MMA | -9.702 |
LX | -9.490 |
Priv | -9.356 |
Rudolph | -9.167 |
Token | " |
Token ID | 1 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
gypt | +1.950 |
bee | +1.579 |
gar | +1.548 |
Bees | +1.548 |
wana | +1.529 |
Neg logit contributions | |
MMA | -1.275 |
Vi | -1.267 |
Priv | -1.218 |
LX | -1.196 |
MV | -1.148 |
Token | information |
Token ID | 1321 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
gypt | +1.593 |
bee | +1.264 |
Bees | +1.238 |
gar | +1.234 |
wana | +1.224 |
Neg logit contributions | |
MMA | -1.237 |
Vi | -1.229 |
Priv | -1.186 |
LX | -1.168 |
MV | -1.126 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
gypt | +0.452 |
bee | +0.363 |
Bees | +0.356 |
gar | +0.356 |
wana | +0.355 |
Neg logit contributions | |
MMA | -0.294 |
Vi | -0.292 |
Priv | -0.280 |
LX | -0.273 |
MV | -0.265 |
Token | noting |
Token ID | 10820 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
gypt | +2.067 |
bee | +1.642 |
Bees | +1.610 |
gar | +1.607 |
wana | +1.594 |
Neg logit contributions | |
MMA | -1.570 |
Vi | -1.563 |
Priv | -1.514 |
LX | -1.475 |
MV | -1.433 |
Token | x |
Token ID | 87 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
gypt | +3.853 |
bee | +3.001 |
gar | +2.963 |
Bees | +2.939 |
wana | +2.898 |
Neg logit contributions | |
MMA | -3.216 |
Vi | -3.162 |
Priv | -3.144 |
LX | -2.999 |
MV | -2.951 |
Token | ic |
Token ID | 291 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
gypt | +2.796 |
bee | +2.170 |
Bees | +2.155 |
gar | +2.144 |
gars | +2.094 |
Neg logit contributions | |
MMA | -2.374 |
Vi | -2.332 |
Priv | -2.326 |
LX | -2.239 |
シャ | -2.187 |
Token | Karen |
Token ID | 18678 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
gypt | +0.521 |
bee | +0.416 |
Bees | +0.411 |
gar | +0.408 |
wana | +0.404 |
Neg logit contributions | |
MMA | -0.366 |
Vi | -0.363 |
Priv | -0.351 |
LX | -0.343 |
MV | -0.331 |
Token | Carpenter |
Token ID | 32659 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
gypt | +2.431 |
bee | +1.929 |
Bees | +1.906 |
gar | +1.884 |
wana | +1.863 |
Neg logit contributions | |
MMA | -1.990 |
Vi | -1.973 |
Priv | -1.922 |
LX | -1.874 |
MV | -1.814 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
gypt | +5.561 |
bee | +4.407 |
Bees | +4.399 |
gar | +4.289 |
wana | +4.207 |
Neg logit contributions | |
MMA | -4.951 |
Vi | -4.922 |
Priv | -4.852 |
LX | -4.711 |
シャ | -4.540 |
Token | 01 |
Token ID | 486 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
gypt | +0.569 |
bee | +0.445 |
gar | +0.432 |
Bees | +0.431 |
wana | +0.427 |
Neg logit contributions | |
MMA | -0.508 |
Vi | -0.506 |
Priv | -0.487 |
LX | -0.478 |
MV | -0.469 |
Token | 15 |
Token ID | 1314 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
gypt | +7.525 |
bee | +6.131 |
gar | +5.955 |
gars | +5.758 |
Bees | +5.700 |
Neg logit contributions | |
Vi | -8.422 |
MMA | -8.253 |
LX | -8.078 |
Priv | -7.896 |
Orn | -7.774 |
Token | O |
Token ID | 440 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
MMA | +0.638 |
Vi | +0.633 |
Priv | +0.602 |
LX | +0.582 |
MV | +0.559 |
Neg logit contributions | |
gypt | -1.386 |
bee | -1.145 |
Bees | -1.130 |
gar | -1.125 |
wana | -1.121 |
Token | & |
Token ID | 5 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
gypt | +0.633 |
bee | +0.504 |
gar | +0.494 |
Bees | +0.492 |
wana | +0.489 |
Neg logit contributions | |
MMA | -0.473 |
Vi | -0.472 |
Priv | -0.452 |
LX | -0.444 |
MV | -0.431 |
Token | A |
Token ID | 32 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
gypt | +1.296 |
bee | +0.990 |
Bees | +0.966 |
gar | +0.965 |
wana | +0.958 |
Neg logit contributions | |
MMA | -1.292 |
Vi | -1.287 |
Priv | -1.241 |
LX | -1.223 |
MV | -1.192 |
Token | - |
Token ID | 12 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
gypt | +0.181 |
bee | +0.143 |
Bees | +0.140 |
gar | +0.140 |
wana | +0.139 |
Neg logit contributions | |
MMA | -0.142 |
Vi | -0.141 |
Priv | -0.136 |
LX | -0.133 |
MV | -0.129 |
Token |
|
Token ID | 198 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
gypt | +3.176 |
bee | +2.554 |
gar | +2.506 |
Bees | +2.481 |
wana | +2.467 |
Neg logit contributions | |
Vi | -2.635 |
MMA | -2.631 |
Priv | -2.578 |
LX | -2.501 |
MV | -2.414 |
Token |
|
Token ID | 198 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
gypt | +0.688 |
bee | +0.547 |
gar | +0.536 |
Bees | +0.535 |
wana | +0.532 |
Neg logit contributions | |
MMA | -0.515 |
Vi | -0.513 |
Priv | -0.493 |
LX | -0.484 |
MV | -0.469 |
Token | 2005 |
Token ID | 14315 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
gypt | +5.005 |
bee | +3.701 |
gar | +3.690 |
wana | +3.510 |
gars | +3.435 |
Neg logit contributions | |
MMA | -7.621 |
Vi | -7.562 |
LX | -7.366 |
Rudolph | -7.172 |
Orn | -7.142 |
Token | Jason |
Token ID | 8982 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
MMA | +2.412 |
Vi | +2.388 |
Priv | +2.269 |
LX | +2.243 |
MV | +2.199 |
Neg logit contributions | |
gypt | -2.874 |
bee | -2.209 |
wana | -2.187 |
gar | -2.165 |
gars | -2.162 |
Token | Bat |
Token ID | 6577 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
gypt | +1.588 |
bee | +1.279 |
Bees | +1.271 |
gar | +1.248 |
wana | +1.237 |
Neg logit contributions | |
MMA | -1.209 |
Priv | -1.179 |
Vi | -1.170 |
LX | -1.127 |
MV | -1.088 |
Token | eman |
Token ID | 8463 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Vi | +0.094 |
MMA | +0.094 |
Priv | +0.092 |
LX | +0.089 |
MV | +0.087 |
Neg logit contributions | |
gypt | -0.092 |
bee | -0.073 |
gar | -0.070 |
wana | -0.070 |
Bees | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
gypt | +8.448 |
bee | +6.882 |
Bees | +6.685 |
gar | +6.561 |
wana | +6.549 |
Neg logit contributions | |
MMA | -7.504 |
Priv | -7.483 |
Vi | -7.470 |
LX | -7.176 |
MV | -7.051 |
Token |
|
Token ID | 198 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
gypt | +0.751 |
bee | +0.598 |
gar | +0.586 |
Bees | +0.584 |
wana | +0.580 |
Neg logit contributions | |
MMA | -0.568 |
Vi | -0.566 |
Priv | -0.544 |
LX | -0.535 |
MV | -0.518 |
Token | 2005 |
Token ID | 14315 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
gypt | +4.446 |
bee | +3.289 |
gar | +3.220 |
wana | +3.146 |
gars | +3.091 |
Neg logit contributions | |
MMA | -5.959 |
Vi | -5.936 |
LX | -5.718 |
Priv | -5.645 |
MV | -5.569 |
Token | Zach |
Token ID | 18825 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
MMA | +0.234 |
Vi | +0.233 |
Priv | +0.225 |
LX | +0.220 |
MV | +0.214 |
Neg logit contributions | |
gypt | -0.288 |
bee | -0.226 |
Bees | -0.222 |
gar | -0.221 |
wana | -0.220 |
Token | Bra |
Token ID | 9718 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
gypt | +1.852 |
bee | +1.518 |
Bees | +1.497 |
gar | +1.490 |
wana | +1.450 |
Neg logit contributions | |
MMA | -1.467 |
Priv | -1.448 |
Vi | -1.408 |
LX | -1.368 |
シャ | -1.339 |
Token | that |
Token ID | 326 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
MMA | +1.478 |
Vi | +1.467 |
Priv | +1.404 |
LX | +1.371 |
MV | +1.333 |
Neg logit contributions | |
gypt | -2.197 |
bee | -1.748 |
Bees | -1.722 |
gar | -1.717 |
wana | -1.713 |
Token | he |
Token ID | 339 |
Feature activation | +1.93e-03 |
Pos logit contributions | |
MMA | +0.762 |
Vi | +0.756 |
Priv | +0.725 |
LX | +0.708 |
MV | +0.686 |
Neg logit contributions | |
gypt | -1.168 |
bee | -0.936 |
Bees | -0.920 |
gar | -0.918 |
wana | -0.915 |
Token | has |
Token ID | 468 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
gypt | +0.019 |
bee | +0.016 |
Bees | +0.015 |
gar | +0.015 |
wana | +0.015 |
Neg logit contributions | |
MMA | -0.013 |
Vi | -0.013 |
Priv | -0.012 |
LX | -0.012 |
MV | -0.012 |
Token | accepted |
Token ID | 6292 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
gypt | +0.670 |
bee | +0.527 |
Bees | +0.517 |
gar | +0.515 |
wana | +0.512 |
Neg logit contributions | |
MMA | -0.533 |
Vi | -0.530 |
Priv | -0.514 |
LX | -0.502 |
MV | -0.489 |
Token | Tal |
Token ID | 7193 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
MMA | +0.484 |
Vi | +0.480 |
Priv | +0.463 |
LX | +0.453 |
MV | +0.440 |
Neg logit contributions | |
gypt | -0.666 |
bee | -0.529 |
Bees | -0.519 |
gar | -0.518 |
wana | -0.516 |
Token | ul |
Token ID | 377 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
gypt | +1.192 |
bee | +0.940 |
gar | +0.927 |
wana | +0.919 |
gars | +0.908 |
Neg logit contributions | |
MMA | -0.905 |
Vi | -0.904 |
Priv | -0.862 |
LX | -0.858 |
MV | -0.826 |
Token | ah |
Token ID | 993 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
gypt | +4.604 |
bee | +3.056 |
gar | +2.888 |
aga | +2.757 |
wana | +2.686 |
Neg logit contributions | |
Vi | -11.387 |
MMA | -11.329 |
LX | -11.183 |
Priv | -11.126 |
Orn | -10.942 |
Token | back |
Token ID | 736 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
gypt | +1.220 |
bee | +0.964 |
Bees | +0.945 |
gar | +0.942 |
wana | +0.937 |
Neg logit contributions | |
MMA | -0.943 |
Vi | -0.937 |
Priv | -0.906 |
LX | -0.887 |
MV | -0.863 |
Token | into |
Token ID | 656 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
MMA | +0.815 |
Vi | +0.810 |
Priv | +0.777 |
LX | +0.759 |
MV | +0.736 |
Neg logit contributions | |
gypt | -1.291 |
bee | -1.042 |
gar | -1.021 |
Bees | -1.021 |
wana | -1.015 |
Token | his |
Token ID | 465 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
gypt | +1.028 |
bee | +0.811 |
Bees | +0.798 |
gar | +0.795 |
wana | +0.786 |
Neg logit contributions | |
MMA | -0.783 |
Vi | -0.780 |
Priv | -0.756 |
LX | -0.734 |
MV | -0.716 |
Token | life |
Token ID | 1204 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
gypt | +1.880 |
bee | +1.474 |
Bees | +1.453 |
gar | +1.447 |
wana | +1.427 |
Neg logit contributions | |
MMA | -1.593 |
Vi | -1.592 |
Priv | -1.559 |
LX | -1.508 |
MV | -1.466 |
Token | with |
Token ID | 351 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
gypt | +0.504 |
bee | +0.398 |
gar | +0.392 |
wana | +0.389 |
Bees | +0.389 |
Neg logit contributions | |
MMA | -0.387 |
Vi | -0.386 |
Priv | -0.375 |
LX | -0.365 |
MV | -0.355 |
Token | AA |
Token ID | 15923 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
gypt | +2.956 |
bee | +2.214 |
Bees | +2.166 |
gar | +2.106 |
wana | +2.078 |
Neg logit contributions | |
MMA | -3.898 |
Vi | -3.897 |
Priv | -3.891 |
LX | -3.746 |
シャ | -3.689 |
Token | on |
Token ID | 319 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
gypt | +0.227 |
bee | +0.184 |
gar | +0.181 |
Bees | +0.180 |
wana | +0.179 |
Neg logit contributions | |
MMA | -0.139 |
Vi | -0.138 |
Priv | -0.133 |
LX | -0.130 |
MV | -0.125 |
Token | ( |
Token ID | 357 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
MMA | +1.906 |
Vi | +1.891 |
Priv | +1.802 |
LX | +1.759 |
MV | +1.709 |
Neg logit contributions | |
gypt | -3.168 |
bee | -2.550 |
Bees | -2.508 |
gar | -2.503 |
wana | -2.501 |
Token | Anti |
Token ID | 28795 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
MMA | +0.014 |
Vi | +0.014 |
Priv | +0.013 |
LX | +0.013 |
MV | +0.013 |
Neg logit contributions | |
gypt | -0.016 |
bee | -0.013 |
Bees | -0.012 |
gar | -0.012 |
wana | -0.012 |
Token | Ali |
Token ID | 37893 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
gypt | +5.230 |
bee | +3.681 |
gar | +3.398 |
Bees | +3.368 |
aga | +3.323 |
Neg logit contributions | |
Vi | -9.807 |
MMA | -9.750 |
LX | -9.717 |
Priv | -9.552 |
Rudolph | -9.431 |
Token | asing |
Token ID | 2313 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
gypt | +5.514 |
bee | +3.756 |
gar | +3.657 |
aga | +3.485 |
wana | +3.426 |
Neg logit contributions | |
Vi | -10.549 |
MMA | -10.386 |
LX | -10.257 |
Priv | -10.226 |
MV | -10.099 |
Token | is |
Token ID | 318 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
gypt | +2.088 |
bee | +1.678 |
gar | +1.649 |
Bees | +1.635 |
wana | +1.620 |
Neg logit contributions | |
MMA | -1.460 |
Vi | -1.456 |
Priv | -1.416 |
LX | -1.374 |
MV | -1.328 |
Token | a |
Token ID | 257 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
gypt | +4.236 |
bee | +3.293 |
gar | +3.187 |
Bees | +3.168 |
wana | +3.158 |
Neg logit contributions | |
Vi | -3.979 |
MMA | -3.976 |
Priv | -3.909 |
LX | -3.836 |
MV | -3.677 |
Token | technique |
Token ID | 8173 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
gypt | +2.796 |
bee | +1.847 |
gar | +1.769 |
Bees | +1.739 |
wana | +1.734 |
Neg logit contributions | |
MMA | -4.929 |
Vi | -4.903 |
Priv | -4.864 |
LX | -4.798 |
Orn | -4.646 |
Token | used |
Token ID | 973 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
gypt | +2.955 |
bee | +2.327 |
wana | +2.275 |
Bees | +2.272 |
gar | +2.267 |
Neg logit contributions | |
MMA | -2.326 |
Vi | -2.303 |
Priv | -2.266 |
LX | -2.211 |
MV | -2.120 |
Token | ussian |
Token ID | 31562 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
gypt | +3.736 |
gar | +2.787 |
bee | +2.776 |
wana | +2.758 |
gars | +2.694 |
Neg logit contributions | |
MMA | -4.185 |
Vi | -4.170 |
LX | -4.065 |
Priv | -4.064 |
Orn | -3.887 |
Token | , |
Token ID | 11 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
MMA | +1.346 |
Vi | +1.325 |
Priv | +1.259 |
LX | +1.231 |
MV | +1.197 |
Neg logit contributions | |
gypt | -2.439 |
bee | -1.974 |
Bees | -1.944 |
gar | -1.939 |
wana | -1.936 |
Token | then |
Token ID | 788 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
MMA | +0.355 |
Vi | +0.352 |
Priv | +0.337 |
LX | +0.329 |
MV | +0.320 |
Neg logit contributions | |
gypt | -0.555 |
bee | -0.445 |
Bees | -0.438 |
gar | -0.436 |
wana | -0.436 |
Token | apply |
Token ID | 4174 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
MMA | +2.066 |
Vi | +2.022 |
Priv | +1.895 |
LX | +1.894 |
MV | +1.840 |
Neg logit contributions | |
gypt | -3.791 |
bee | -3.077 |
Bees | -3.040 |
gar | -3.034 |
wana | -3.028 |
Token | the |
Token ID | 262 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
gypt | +4.282 |
bee | +3.352 |
gar | +3.300 |
wana | +3.242 |
Bees | +3.242 |
Neg logit contributions | |
Vi | -3.634 |
MMA | -3.612 |
Priv | -3.568 |
LX | -3.480 |
シャ | -3.323 |
Token | black |
Token ID | 2042 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
gypt | +3.344 |
bee | +1.909 |
gar | +1.832 |
Bees | +1.775 |
wana | +1.763 |
Neg logit contributions | |
Priv | -8.959 |
Vi | -8.899 |
MMA | -8.869 |
LX | -8.669 |
士 | -8.595 |
Token | hat |
Token ID | 5183 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
gypt | +5.726 |
bee | +4.111 |
gar | +4.012 |
hops | +3.766 |
wana | +3.647 |
Neg logit contributions | |
Vi | -10.224 |
MMA | -10.076 |
Priv | -9.955 |
LX | -9.812 |
Rudolph | -9.722 |
Token | # |
Token ID | 1303 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
gypt | +0.339 |
bee | +0.261 |
Bees | +0.256 |
gar | +0.255 |
wana | +0.254 |
Neg logit contributions | |
MMA | -0.302 |
Vi | -0.300 |
Priv | -0.287 |
LX | -0.284 |
MV | -0.278 |
Token | morph |
Token ID | 17488 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
gypt | +2.327 |
bee | +1.812 |
wana | +1.776 |
Bees | +1.768 |
gar | +1.760 |
Neg logit contributions | |
Priv | -1.821 |
Vi | -1.816 |
MMA | -1.814 |
LX | -1.714 |
シャ | -1.694 |
Token | ological |
Token ID | 2770 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
gypt | +2.720 |
bee | +2.197 |
wana | +2.138 |
gar | +2.136 |
gars | +2.100 |
Neg logit contributions | |
Vi | -1.881 |
MMA | -1.855 |
Priv | -1.799 |
LX | -1.746 |
MV | -1.676 |
Token | operator |
Token ID | 10088 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Vi | +0.096 |
MMA | +0.095 |
Priv | +0.090 |
LX | +0.085 |
MV | +0.078 |
Neg logit contributions | |
gypt | -0.333 |
bee | -0.284 |
gar | -0.279 |
Bees | -0.278 |
wana | -0.276 |
Token | ch |
Token ID | 354 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
MMA | +0.519 |
Vi | +0.516 |
Priv | +0.497 |
LX | +0.487 |
MV | +0.475 |
Neg logit contributions | |
gypt | -0.588 |
bee | -0.455 |
Bees | -0.446 |
gar | -0.444 |
wana | -0.443 |
Token | tein |
Token ID | 22006 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
gypt | +3.473 |
bee | +2.840 |
gar | +2.837 |
wana | +2.816 |
gars | +2.766 |
Neg logit contributions | |
MMA | -1.880 |
Vi | -1.865 |
Priv | -1.807 |
LX | -1.743 |
MV | -1.682 |
Token | Pt |
Token ID | 34352 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
gypt | +1.442 |
bee | +1.145 |
Bees | +1.128 |
gar | +1.123 |
wana | +1.113 |
Neg logit contributions | |
MMA | -1.073 |
Vi | -1.064 |
Priv | -1.030 |
LX | -1.003 |
MV | -0.975 |
Token | 2 |
Token ID | 362 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
gypt | +1.998 |
bee | +1.618 |
Bees | +1.599 |
gar | +1.592 |
wana | +1.579 |
Neg logit contributions | |
MMA | -1.233 |
Vi | -1.220 |
Priv | -1.184 |
LX | -1.139 |
MV | -1.098 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
gypt | +4.835 |
bee | +3.802 |
Bees | +3.764 |
gar | +3.703 |
wana | +3.650 |
Neg logit contributions | |
MMA | -4.204 |
Vi | -4.196 |
Priv | -4.079 |
LX | -3.983 |
MV | -3.852 |
Token | 01 |
Token ID | 486 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
MMA | +1.712 |
Vi | +1.698 |
Priv | +1.642 |
LX | +1.598 |
MV | +1.547 |
Neg logit contributions | |
gypt | -2.190 |
bee | -1.700 |
Bees | -1.687 |
wana | -1.682 |
gar | -1.675 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
gypt | +7.871 |
bee | +6.309 |
gar | +6.240 |
Bees | +6.027 |
wana | +5.927 |
Neg logit contributions | |
Vi | -7.632 |
MMA | -7.475 |
LX | -7.323 |
MV | -7.207 |
Orn | -7.077 |
Token | O |
Token ID | 440 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
MMA | +0.580 |
Vi | +0.575 |
Priv | +0.547 |
LX | +0.529 |
MV | +0.508 |
Neg logit contributions | |
gypt | -1.259 |
bee | -1.040 |
Bees | -1.027 |
gar | -1.022 |
wana | -1.018 |
Token | & |
Token ID | 5 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
gypt | +0.666 |
bee | +0.529 |
gar | +0.519 |
Bees | +0.516 |
wana | +0.514 |
Neg logit contributions | |
MMA | -0.498 |
Vi | -0.498 |
Priv | -0.476 |
LX | -0.468 |
MV | -0.453 |
Token | A |
Token ID | 32 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
gypt | +1.607 |
bee | +1.230 |
gar | +1.200 |
Bees | +1.199 |
wana | +1.186 |
Neg logit contributions | |
MMA | -1.634 |
Vi | -1.631 |
Priv | -1.569 |
LX | -1.552 |
MV | -1.509 |
Token | - |
Token ID | 12 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
gypt | +0.488 |
bee | +0.385 |
Bees | +0.377 |
gar | +0.377 |
wana | +0.373 |
Neg logit contributions | |
MMA | -0.387 |
Vi | -0.385 |
Priv | -0.371 |
LX | -0.364 |
MV | -0.353 |
Token | x |
Token ID | 2124 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
MMA | +1.269 |
Vi | +1.253 |
Priv | +1.174 |
LX | +1.147 |
MV | +1.094 |
Neg logit contributions | |
gypt | -3.107 |
bee | -2.570 |
Bees | -2.536 |
wana | -2.533 |
gar | -2.530 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
gypt | +1.204 |
bee | +0.990 |
gar | +0.977 |
Bees | +0.962 |
wana | +0.955 |
Neg logit contributions | |
Vi | -0.692 |
MMA | -0.690 |
Priv | -0.657 |
LX | -0.648 |
MV | -0.622 |
Token | x |
Token ID | 87 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
gypt | +1.103 |
bee | +0.898 |
gar | +0.887 |
wana | +0.870 |
Bees | +0.867 |
Neg logit contributions | |
Vi | -0.705 |
MMA | -0.704 |
Priv | -0.668 |
LX | -0.657 |
MV | -0.638 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
gypt | +3.722 |
bee | +3.087 |
gar | +3.049 |
Bees | +2.957 |
wana | +2.931 |
Neg logit contributions | |
Vi | -2.393 |
MMA | -2.363 |
Priv | -2.274 |
LX | -2.249 |
シャ | -2.165 |
Token | x |
Token ID | 87 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
gypt | +3.061 |
bee | +2.514 |
gar | +2.499 |
wana | +2.405 |
gars | +2.379 |
Neg logit contributions | |
Vi | -2.200 |
MMA | -2.181 |
Priv | -2.073 |
LX | -2.050 |
MV | -2.008 |
Token | . |
Token ID | 13 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
gypt | +8.235 |
bee | +6.832 |
gar | +6.786 |
gee | +6.385 |
Bees | +6.362 |
Neg logit contributions | |
Vi | -6.639 |
redes | -6.572 |
MMA | -6.447 |
emort | -6.322 |
Orn | -6.238 |
Token | 150 |
Token ID | 8628 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
gypt | +6.192 |
bee | +4.434 |
gar | +4.375 |
wana | +4.250 |
gars | +4.006 |
Neg logit contributions | |
Vi | -9.933 |
MMA | -9.762 |
LX | -9.438 |
Orn | -9.312 |
Priv | -9.173 |
Token | 110 |
Token ID | 9796 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
MMA | +0.556 |
Vi | +0.551 |
Priv | +0.532 |
LX | +0.515 |
MV | +0.499 |
Neg logit contributions | |
gypt | -0.849 |
bee | -0.683 |
Bees | -0.672 |
gar | -0.669 |
wana | -0.665 |
Token | 81 |
Token ID | 6659 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
gypt | +3.481 |
bee | +2.790 |
gar | +2.696 |
Bees | +2.644 |
wana | +2.572 |
Neg logit contributions | |
Vi | -3.496 |
MMA | -3.458 |
Priv | -3.288 |
LX | -3.260 |
Orn | -3.195 |
Token | 12 |
Token ID | 1065 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
MMA | +0.901 |
Vi | +0.895 |
Priv | +0.862 |
LX | +0.845 |
MV | +0.826 |
Neg logit contributions | |
gypt | -1.052 |
bee | -0.824 |
gar | -0.805 |
Bees | -0.805 |
wana | -0.796 |
Token | x |
Token ID | 2124 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
MMA | +0.091 |
Vi | +0.091 |
Priv | +0.086 |
LX | +0.083 |
MV | +0.080 |
Neg logit contributions | |
gypt | -0.204 |
bee | -0.169 |
Bees | -0.167 |
gar | -0.167 |
wana | -0.165 |
Token | # |
Token ID | 1303 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
gypt | +2.123 |
bee | +1.674 |
Bees | +1.656 |
gar | +1.638 |
wana | +1.628 |
Neg logit contributions | |
MMA | -1.695 |
Vi | -1.674 |
Priv | -1.627 |
LX | -1.584 |
MV | -1.546 |
Token | Close |
Token ID | 13872 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
gypt | +0.442 |
bee | +0.353 |
Bees | +0.348 |
gar | +0.347 |
wana | +0.346 |
Neg logit contributions | |
MMA | -0.297 |
Vi | -0.294 |
Priv | -0.283 |
LX | -0.276 |
MV | -0.268 |
Token | Graphics |
Token ID | 19840 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
gypt | +2.026 |
bee | +1.600 |
gar | +1.579 |
Bees | +1.574 |
wana | +1.557 |
Neg logit contributions | |
MMA | -1.635 |
Vi | -1.600 |
Priv | -1.561 |
LX | -1.517 |
MV | -1.480 |
Token | $ |
Token ID | 720 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
gypt | +1.117 |
bee | +0.893 |
Bees | +0.877 |
gar | +0.876 |
wana | +0.868 |
Neg logit contributions | |
MMA | -0.816 |
Vi | -0.797 |
Priv | -0.768 |
LX | -0.755 |
MV | -0.739 |
Token | image |
Token ID | 9060 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
gypt | +1.632 |
bee | +1.288 |
gar | +1.272 |
wana | +1.247 |
Bees | +1.244 |
Neg logit contributions | |
MMA | -1.336 |
Vi | -1.321 |
Priv | -1.257 |
LX | -1.247 |
MV | -1.217 |
Token | . |
Token ID | 13 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
gypt | +4.662 |
bee | +3.709 |
gar | +3.606 |
Bees | +3.572 |
wana | +3.540 |
Neg logit contributions | |
MMA | -4.012 |
Vi | -3.937 |
Priv | -3.712 |
LX | -3.710 |
MV | -3.659 |
Token | Dis |
Token ID | 7279 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
gypt | +6.854 |
bee | +5.357 |
gar | +5.343 |
gee | +5.015 |
gars | +5.007 |
Neg logit contributions | |
MMA | -8.390 |
Vi | -8.118 |
LX | -7.760 |
MV | -7.726 |
Orn | -7.653 |
Token | pose |
Token ID | 3455 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
gypt | +4.324 |
bee | +3.438 |
gar | +3.401 |
aga | +3.271 |
wana | +3.260 |
Neg logit contributions | |
MMA | -3.777 |
Vi | -3.610 |
LX | -3.492 |
シャ | -3.413 |
Orn | -3.408 |
Token | (); |
Token ID | 9783 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
gypt | +2.160 |
bee | +1.693 |
Bees | +1.671 |
gar | +1.663 |
wana | +1.641 |
Neg logit contributions | |
MMA | -1.744 |
Vi | -1.716 |
Priv | -1.631 |
LX | -1.627 |
MV | -1.585 |
Token | # |
Token ID | 1303 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
gypt | +4.426 |
bee | +3.462 |
Bees | +3.438 |
gar | +3.397 |
wana | +3.352 |
Neg logit contributions | |
MMA | -3.836 |
Vi | -3.778 |
Priv | -3.689 |
LX | -3.578 |
MV | -3.543 |
Token | Save |
Token ID | 12793 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
gypt | +1.776 |
bee | +1.400 |
gar | +1.382 |
Bees | +1.381 |
wana | +1.365 |
Neg logit contributions | |
MMA | -1.382 |
Vi | -1.358 |
Priv | -1.318 |
LX | -1.283 |
MV | -1.253 |
Token | games |
Token ID | 1830 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
gypt | +5.117 |
bee | +4.180 |
gar | +4.139 |
Bees | +4.112 |
gars | +4.053 |
Neg logit contributions | |
Vi | -3.125 |
Priv | -3.125 |
MMA | -3.057 |
LX | -2.956 |
シャ | -2.918 |
Token | with |
Token ID | 351 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
gypt | +0.504 |
bee | +0.398 |
gar | +0.392 |
wana | +0.389 |
Bees | +0.389 |
Neg logit contributions | |
MMA | -0.387 |
Vi | -0.386 |
Priv | -0.375 |
LX | -0.365 |
MV | -0.355 |
Token | AA |
Token ID | 15923 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
gypt | +2.956 |
bee | +2.214 |
Bees | +2.166 |
gar | +2.106 |
wana | +2.078 |
Neg logit contributions | |
MMA | -3.898 |
Vi | -3.897 |
Priv | -3.891 |
LX | -3.746 |
シャ | -3.689 |
Token | on |
Token ID | 319 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
gypt | +0.227 |
bee | +0.184 |
gar | +0.181 |
Bees | +0.180 |
wana | +0.179 |
Neg logit contributions | |
MMA | -0.139 |
Vi | -0.138 |
Priv | -0.133 |
LX | -0.130 |
MV | -0.125 |
Token | ( |
Token ID | 357 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
MMA | +1.906 |
Vi | +1.891 |
Priv | +1.802 |
LX | +1.759 |
MV | +1.709 |
Neg logit contributions | |
gypt | -3.168 |
bee | -2.550 |
Bees | -2.508 |
gar | -2.503 |
wana | -2.501 |
Token | Anti |
Token ID | 28795 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
MMA | +0.014 |
Vi | +0.014 |
Priv | +0.013 |
LX | +0.013 |
MV | +0.013 |
Neg logit contributions | |
gypt | -0.016 |
bee | -0.013 |
Bees | -0.012 |
gar | -0.012 |
wana | -0.012 |
Token | Ali |
Token ID | 37893 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
gypt | +5.230 |
bee | +3.681 |
gar | +3.398 |
Bees | +3.368 |
aga | +3.323 |
Neg logit contributions | |
Vi | -9.807 |
MMA | -9.750 |
LX | -9.717 |
Priv | -9.552 |
Rudolph | -9.431 |
Token | asing |
Token ID | 2313 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
gypt | +5.514 |
bee | +3.756 |
gar | +3.657 |
aga | +3.485 |
wana | +3.426 |
Neg logit contributions | |
Vi | -10.549 |
MMA | -10.386 |
LX | -10.257 |
Priv | -10.226 |
MV | -10.099 |
Token | is |
Token ID | 318 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
gypt | +2.088 |
bee | +1.678 |
gar | +1.649 |
Bees | +1.635 |
wana | +1.620 |
Neg logit contributions | |
MMA | -1.460 |
Vi | -1.456 |
Priv | -1.416 |
LX | -1.374 |
MV | -1.328 |
Token | a |
Token ID | 257 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
gypt | +4.236 |
bee | +3.293 |
gar | +3.187 |
Bees | +3.168 |
wana | +3.158 |
Neg logit contributions | |
Vi | -3.979 |
MMA | -3.976 |
Priv | -3.909 |
LX | -3.836 |
MV | -3.677 |
Token | technique |
Token ID | 8173 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
gypt | +2.796 |
bee | +1.847 |
gar | +1.769 |
Bees | +1.739 |
wana | +1.734 |
Neg logit contributions | |
MMA | -4.929 |
Vi | -4.903 |
Priv | -4.864 |
LX | -4.798 |
Orn | -4.646 |
Token | t |
Token ID | 83 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
MMA | +0.688 |
Vi | +0.682 |
Priv | +0.655 |
LX | +0.640 |
MV | +0.624 |
Neg logit contributions | |
gypt | -0.919 |
bee | -0.721 |
Bees | -0.714 |
wana | -0.708 |
gar | -0.705 |
Token | � |
Token ID | 447 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
gypt | +1.946 |
bee | +1.563 |
gar | +1.532 |
Bees | +1.529 |
wana | +1.520 |
Neg logit contributions | |
MMA | -1.312 |
Vi | -1.309 |
Priv | -1.256 |
LX | -1.225 |
MV | -1.188 |
Token | � |
Token ID | 247 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
gypt | +2.448 |
bee | +1.889 |
gar | +1.874 |
Bees | +1.847 |
gars | +1.818 |
Neg logit contributions | |
Vi | -2.177 |
MMA | -2.168 |
Priv | -2.097 |
LX | -2.034 |
MV | -1.986 |
Token | ) |
Token ID | 8 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
gypt | +1.350 |
bee | +1.088 |
gar | +1.068 |
Bees | +1.060 |
wana | +1.054 |
Neg logit contributions | |
MMA | -0.895 |
Vi | -0.889 |
Priv | -0.859 |
LX | -0.836 |
MV | -0.809 |
Token | + |
Token ID | 1343 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
gypt | +1.675 |
bee | +1.337 |
gar | +1.314 |
Bees | +1.307 |
wana | +1.302 |
Neg logit contributions | |
MMA | -1.199 |
Vi | -1.194 |
Priv | -1.157 |
LX | -1.122 |
MV | -1.086 |
Token | f |
Token ID | 277 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
gypt | +1.344 |
bee | +1.101 |
gar | +1.083 |
Bees | +1.079 |
wana | +1.075 |
Neg logit contributions | |
MMA | -0.703 |
Vi | -0.697 |
Priv | -0.672 |
LX | -0.646 |
MV | -0.623 |
Token | anthrop |
Token ID | 17911 |
Feature activation | -7.90e-05 |
Pos logit contributions | |
gypt | +7.158 |
gar | +5.451 |
bee | +5.436 |
acca | +5.249 |
gars | +5.220 |
Neg logit contributions | |
Priv | -7.979 |
Vi | -7.962 |
MMA | -7.871 |
LX | -7.633 |
MV | -7.367 |
Token | ic |
Token ID | 291 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
MMA | +0.001 |
Vi | +0.001 |
Priv | +0.001 |
LX | +0.001 |
MV | +0.001 |
Neg logit contributions | |
gypt | -0.001 |
bee | -0.001 |
gar | -0.001 |
wana | -0.001 |
Bees | -0.001 |
Token | ( |
Token ID | 357 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
MMA | +3.051 |
Vi | +2.996 |
Priv | +2.836 |
LX | +2.751 |
MV | +2.712 |
Neg logit contributions | |
gypt | -5.769 |
bee | -4.689 |
Bees | -4.682 |
wana | -4.639 |
gars | -4.585 |
Token | t |
Token ID | 83 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
MMA | +1.890 |
Vi | +1.869 |
Priv | +1.795 |
LX | +1.749 |
MV | +1.702 |
Neg logit contributions | |
gypt | -2.606 |
bee | -2.056 |
Bees | -2.054 |
wana | -2.027 |
gar | -2.003 |
Token | � |
Token ID | 447 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
gypt | +0.602 |
bee | +0.474 |
Bees | +0.464 |
gar | +0.464 |
wana | +0.462 |
Neg logit contributions | |
MMA | -0.466 |
Vi | -0.464 |
Priv | -0.446 |
LX | -0.437 |
MV | -0.425 |
Token | 26 |
Token ID | 2075 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
MMA | +0.023 |
Vi | +0.023 |
Priv | +0.022 |
LX | +0.022 |
MV | +0.021 |
Neg logit contributions | |
gypt | -0.027 |
bee | -0.021 |
gar | -0.021 |
Bees | -0.021 |
wana | -0.021 |
Token | x |
Token ID | 2124 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
MMA | +1.269 |
Vi | +1.253 |
Priv | +1.174 |
LX | +1.147 |
MV | +1.094 |
Neg logit contributions | |
gypt | -3.107 |
bee | -2.570 |
Bees | -2.536 |
wana | -2.533 |
gar | -2.530 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
gypt | +1.204 |
bee | +0.990 |
gar | +0.977 |
Bees | +0.962 |
wana | +0.955 |
Neg logit contributions | |
Vi | -0.692 |
MMA | -0.690 |
Priv | -0.657 |
LX | -0.648 |
MV | -0.622 |
Token | x |
Token ID | 87 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
gypt | +1.103 |
bee | +0.898 |
gar | +0.887 |
wana | +0.870 |
Bees | +0.867 |
Neg logit contributions | |
Vi | -0.705 |
MMA | -0.704 |
Priv | -0.668 |
LX | -0.657 |
MV | -0.638 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
gypt | +3.722 |
bee | +3.087 |
gar | +3.049 |
Bees | +2.957 |
wana | +2.931 |
Neg logit contributions | |
Vi | -2.393 |
MMA | -2.363 |
Priv | -2.274 |
LX | -2.249 |
シャ | -2.165 |
Token | x |
Token ID | 87 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
gypt | +3.061 |
bee | +2.514 |
gar | +2.499 |
wana | +2.405 |
gars | +2.379 |
Neg logit contributions | |
Vi | -2.200 |
MMA | -2.181 |
Priv | -2.073 |
LX | -2.050 |
MV | -2.008 |
Token | . |
Token ID | 13 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
gypt | +8.235 |
bee | +6.832 |
gar | +6.786 |
gee | +6.385 |
Bees | +6.362 |
Neg logit contributions | |
Vi | -6.639 |
redes | -6.572 |
MMA | -6.447 |
emort | -6.322 |
Orn | -6.238 |
Token | 150 |
Token ID | 8628 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
gypt | +6.192 |
bee | +4.434 |
gar | +4.375 |
wana | +4.250 |
gars | +4.006 |
Neg logit contributions | |
Vi | -9.933 |
MMA | -9.762 |
LX | -9.438 |
Orn | -9.312 |
Priv | -9.173 |
Token | 110 |
Token ID | 9796 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
MMA | +0.556 |
Vi | +0.551 |
Priv | +0.532 |
LX | +0.515 |
MV | +0.499 |
Neg logit contributions | |
gypt | -0.849 |
bee | -0.683 |
Bees | -0.672 |
gar | -0.669 |
wana | -0.665 |
Token | 81 |
Token ID | 6659 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
gypt | +3.481 |
bee | +2.790 |
gar | +2.696 |
Bees | +2.644 |
wana | +2.572 |
Neg logit contributions | |
Vi | -3.496 |
MMA | -3.458 |
Priv | -3.288 |
LX | -3.260 |
Orn | -3.195 |
Token | 12 |
Token ID | 1065 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
MMA | +0.901 |
Vi | +0.895 |
Priv | +0.862 |
LX | +0.845 |
MV | +0.826 |
Neg logit contributions | |
gypt | -1.052 |
bee | -0.824 |
gar | -0.805 |
Bees | -0.805 |
wana | -0.796 |
Token | 225 |
Token ID | 18182 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
gypt | +3.060 |
bee | +2.410 |
gar | +2.350 |
Bees | +2.319 |
acca | +2.283 |
Neg logit contributions | |
MMA | -2.784 |
Vi | -2.776 |
Priv | -2.657 |
LX | -2.617 |
MV | -2.557 |
Token | x |
Token ID | 2124 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
MMA | +0.663 |
Vi | +0.657 |
Priv | +0.623 |
LX | +0.601 |
MV | +0.578 |
Neg logit contributions | |
gypt | -1.534 |
bee | -1.272 |
Bees | -1.253 |
gar | -1.251 |
wana | -1.246 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
gypt | +1.402 |
bee | +1.154 |
gar | +1.138 |
Bees | +1.119 |
wana | +1.111 |
Neg logit contributions | |
Vi | -0.811 |
MMA | -0.809 |
Priv | -0.770 |
LX | -0.760 |
MV | -0.730 |
Token | x |
Token ID | 87 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
gypt | +1.561 |
bee | +1.273 |
gar | +1.259 |
wana | +1.231 |
Bees | +1.223 |
Neg logit contributions | |
Vi | -1.018 |
MMA | -1.016 |
Priv | -0.964 |
LX | -0.949 |
MV | -0.923 |
Token | . |
Token ID | 13 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
gypt | +4.066 |
bee | +3.385 |
gar | +3.346 |
Bees | +3.224 |
wana | +3.202 |
Neg logit contributions | |
Vi | -2.660 |
MMA | -2.624 |
Priv | -2.523 |
LX | -2.500 |
シャ | -2.410 |
Token | x |
Token ID | 87 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
gypt | +5.274 |
gar | +4.381 |
bee | +4.366 |
wana | +4.143 |
gars | +4.113 |
Neg logit contributions | |
Vi | -4.127 |
MMA | -4.082 |
Priv | -3.856 |
LX | -3.832 |
Mort | -3.792 |
Token | . |
Token ID | 13 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
gypt | +8.070 |
gar | +6.690 |
bee | +6.599 |
gars | +6.253 |
wana | +6.155 |
Neg logit contributions | |
Vi | -6.800 |
MMA | -6.658 |
Orn | -6.276 |
LX | -6.275 |
シャ | -6.188 |
Token | 148 |
Token ID | 18294 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
gypt | +4.811 |
bee | +3.711 |
gar | +3.656 |
wana | +3.560 |
Bees | +3.559 |
Neg logit contributions | |
Vi | -4.886 |
MMA | -4.884 |
LX | -4.585 |
Priv | -4.583 |
Orn | -4.453 |
Token | 10 |
Token ID | 838 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
MMA | +0.729 |
Vi | +0.721 |
Priv | +0.697 |
LX | +0.674 |
MV | +0.653 |
Neg logit contributions | |
gypt | -1.145 |
bee | -0.925 |
Bees | -0.910 |
gar | -0.907 |
wana | -0.899 |
Token | 42 |
Token ID | 3682 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
gypt | +3.047 |
bee | +2.419 |
gar | +2.347 |
Bees | +2.302 |
acca | +2.251 |
Neg logit contributions | |
Vi | -2.994 |
MMA | -2.982 |
Priv | -2.819 |
LX | -2.793 |
MV | -2.736 |
Token | 170 |
Token ID | 17279 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
gypt | +1.059 |
bee | +0.830 |
gar | +0.812 |
Bees | +0.806 |
wana | +0.795 |
Neg logit contributions | |
MMA | -0.939 |
Vi | -0.934 |
Priv | -0.894 |
LX | -0.879 |
MV | -0.863 |
Token | at |
Token ID | 265 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
gypt | +2.599 |
bee | +1.783 |
gar | +1.732 |
wana | +1.660 |
acca | +1.631 |
Neg logit contributions | |
MMA | -4.758 |
Vi | -4.756 |
Priv | -4.633 |
LX | -4.610 |
MV | -4.498 |
Token | osis |
Token ID | 5958 |
Feature activation | +9.90e-03 |
Pos logit contributions | |
MMA | +1.431 |
Vi | +1.426 |
Priv | +1.381 |
LX | +1.362 |
MV | +1.337 |
Neg logit contributions | |
gypt | -0.881 |
bee | -0.602 |
Bees | -0.594 |
gar | -0.578 |
wana | -0.571 |
Token | of |
Token ID | 286 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
gypt | +0.101 |
bee | +0.081 |
gar | +0.079 |
Bees | +0.079 |
wana | +0.079 |
Neg logit contributions | |
MMA | -0.066 |
Vi | -0.065 |
Priv | -0.063 |
LX | -0.061 |
MV | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
MMA | +0.860 |
Vi | +0.854 |
Priv | +0.820 |
LX | +0.802 |
MV | +0.779 |
Neg logit contributions | |
gypt | -1.220 |
bee | -0.970 |
Bees | -0.952 |
gar | -0.950 |
wana | -0.947 |
Token | palms |
Token ID | 39513 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
gypt | +1.834 |
bee | +1.374 |
Bees | +1.360 |
gar | +1.353 |
gars | +1.345 |
Neg logit contributions | |
Vi | -1.840 |
MMA | -1.840 |
Priv | -1.775 |
LX | -1.749 |
MV | -1.714 |
Token | and |
Token ID | 290 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
MMA | +1.515 |
Vi | +1.499 |
Priv | +1.424 |
LX | +1.395 |
MV | +1.355 |
Neg logit contributions | |
gypt | -2.359 |
bee | -1.880 |
Bees | -1.859 |
wana | -1.856 |
gar | -1.842 |
Token | sol |
Token ID | 1540 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
MMA | +5.797 |
Vi | +5.369 |
LX | +4.575 |
MV | +4.491 |
Mort | +4.292 |
Neg logit contributions | |
gypt | -19.382 |
wana | -16.784 |
bee | -16.745 |
Bees | -16.723 |
ECA | -16.040 |
Token | es |
Token ID | 274 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
MMA | +1.314 |
Vi | +1.295 |
Priv | +1.250 |
LX | +1.222 |
MV | +1.186 |
Neg logit contributions | |
gypt | -1.746 |
bee | -1.368 |
Bees | -1.347 |
wana | -1.347 |
gar | -1.335 |
Token | ") |
Token ID | 4943 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
MMA | +2.284 |
Vi | +2.276 |
Priv | +2.075 |
LX | +2.002 |
MV | +1.938 |
Neg logit contributions | |
gypt | -6.479 |
wana | -5.391 |
Bees | -5.366 |
bee | -5.358 |
gar | -5.279 |
Token | is |
Token ID | 318 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
MMA | +3.216 |
Vi | +3.178 |
Priv | +2.940 |
LX | +2.907 |
MV | +2.817 |
Neg logit contributions | |
gypt | -5.911 |
wana | -4.795 |
bee | -4.746 |
Bees | -4.736 |
gars | -4.664 |
Token | an |
Token ID | 281 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
MMA | +0.385 |
Vi | +0.382 |
Priv | +0.370 |
LX | +0.361 |
MV | +0.349 |
Neg logit contributions | |
gypt | -0.559 |
bee | -0.446 |
gar | -0.438 |
Bees | -0.436 |
wana | -0.433 |
Token | noted |
Token ID | 4367 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
MMA | +0.534 |
Vi | +0.530 |
Priv | +0.507 |
LX | +0.497 |
MV | +0.485 |
Neg logit contributions | |
gypt | -0.748 |
bee | -0.593 |
Bees | -0.582 |
gar | -0.581 |
wana | -0.579 |
Token | Kap |
Token ID | 27344 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
MMA | +0.167 |
Vi | +0.166 |
Priv | +0.160 |
LX | +0.156 |
MV | +0.152 |
Neg logit contributions | |
gypt | -0.217 |
bee | -0.170 |
Bees | -0.167 |
gar | -0.167 |
wana | -0.166 |
Token | ur |
Token ID | 333 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
MMA | +1.919 |
Vi | +1.905 |
Priv | +1.825 |
LX | +1.777 |
MV | +1.748 |
Neg logit contributions | |
gypt | -2.599 |
bee | -2.049 |
Bees | -2.039 |
wana | -1.990 |
gar | -1.983 |
Token | and |
Token ID | 290 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
MMA | +0.139 |
Vi | +0.138 |
Priv | +0.131 |
LX | +0.128 |
MV | +0.124 |
Neg logit contributions | |
gypt | -0.246 |
bee | -0.200 |
Bees | -0.196 |
gar | -0.196 |
wana | -0.195 |
Token | Va |
Token ID | 17668 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Vi | +1.320 |
MMA | +1.311 |
Priv | +1.235 |
LX | +1.209 |
MV | +1.177 |
Neg logit contributions | |
gypt | -2.437 |
bee | -1.973 |
Bees | -1.940 |
gar | -1.940 |
wana | -1.931 |
Token | ish |
Token ID | 680 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
MMA | +0.921 |
Vi | +0.915 |
Priv | +0.880 |
LX | +0.856 |
MV | +0.837 |
Neg logit contributions | |
gypt | -1.232 |
bee | -0.969 |
Bees | -0.965 |
wana | -0.945 |
gar | -0.941 |
Token | nav |
Token ID | 28341 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
MMA | +5.493 |
Vi | +5.341 |
Priv | +5.095 |
MV | +4.879 |
yne | +4.840 |
Neg logit contributions | |
gypt | -15.637 |
Bees | -13.812 |
bee | -13.236 |
ECA | -13.001 |
wana | -12.840 |
Token | . |
Token ID | 13 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
MMA | +0.413 |
Vi | +0.409 |
Priv | +0.390 |
LX | +0.379 |
MV | +0.366 |
Neg logit contributions | |
gypt | -0.779 |
bee | -0.635 |
Bees | -0.626 |
gar | -0.624 |
wana | -0.622 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
MMA | +1.210 |
Vi | +1.202 |
Priv | +1.156 |
LX | +1.132 |
MV | +1.101 |
Neg logit contributions | |
gypt | -1.605 |
bee | -1.266 |
Bees | -1.242 |
gar | -1.240 |
wana | -1.236 |
Token |
|
Token ID | 198 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
MMA | +1.413 |
Vi | +1.396 |
Priv | +1.343 |
LX | +1.302 |
MV | +1.273 |
Neg logit contributions | |
gypt | -2.089 |
bee | -1.646 |
Bees | -1.628 |
wana | -1.626 |
gar | -1.615 |
Token | Thus |
Token ID | 19093 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
MMA | +0.616 |
Vi | +0.612 |
Priv | +0.588 |
LX | +0.580 |
MV | +0.565 |
Neg logit contributions | |
gypt | -0.676 |
bee | -0.523 |
gar | -0.511 |
Bees | -0.510 |
wana | -0.507 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
gypt | +2.504 |
bee | +1.981 |
Bees | +1.949 |
gar | +1.946 |
wana | +1.931 |
Neg logit contributions | |
MMA | -1.860 |
Vi | -1.845 |
Priv | -1.777 |
LX | -1.738 |
MV | -1.691 |
Token |
|
Token ID | 198 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
gypt | +1.324 |
bee | +1.057 |
gar | +1.037 |
Bees | +1.028 |
wana | +1.021 |
Neg logit contributions | |
MMA | -1.040 |
Vi | -1.038 |
Priv | -1.000 |
LX | -0.985 |
MV | -0.951 |
Token | Google |
Token ID | 11708 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
MMA | +0.555 |
Vi | +0.551 |
Priv | +0.532 |
LX | +0.523 |
MV | +0.510 |
Neg logit contributions | |
gypt | -0.572 |
bee | -0.437 |
Bees | -0.427 |
gar | -0.427 |
wana | -0.424 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
gypt | +0.275 |
bee | +0.219 |
Bees | +0.215 |
gar | +0.215 |
wana | +0.213 |
Neg logit contributions | |
MMA | -0.191 |
Vi | -0.189 |
Priv | -0.183 |
LX | -0.178 |
MV | -0.173 |
Token |
|
Token ID | 198 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
MMA | +1.607 |
Vi | +1.597 |
Priv | +1.529 |
LX | +1.493 |
MV | +1.437 |
Neg logit contributions | |
gypt | -2.662 |
bee | -2.158 |
wana | -2.115 |
Bees | -2.109 |
gar | -2.094 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
MMA | +4.864 |
Vi | +4.759 |
Priv | +4.497 |
LX | +4.284 |
MV | +4.274 |
Neg logit contributions | |
gypt | -9.035 |
wana | -7.134 |
gars | -7.068 |
Bees | -7.065 |
bee | -7.063 |
Token | Ol |
Token ID | 30098 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Priv | +8.980 |
MMA | +8.514 |
Vi | +8.495 |
LX | +7.714 |
MV | +7.704 |
Neg logit contributions | |
gypt | -12.636 |
Bees | -10.055 |
wana | -9.999 |
bee | -9.911 |
gars | -9.816 |
Token | we |
Token ID | 732 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
MMA | +1.419 |
Vi | +1.410 |
Priv | +1.359 |
LX | +1.332 |
MV | +1.296 |
Neg logit contributions | |
gypt | -1.744 |
bee | -1.364 |
Bees | -1.335 |
gar | -1.335 |
wana | -1.330 |
Token | us |
Token ID | 385 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
MMA | +0.120 |
Vi | +0.119 |
Priv | +0.115 |
LX | +0.113 |
MV | +0.110 |
Neg logit contributions | |
gypt | -0.136 |
bee | -0.105 |
Bees | -0.103 |
gar | -0.103 |
wana | -0.102 |
Token | , |
Token ID | 11 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
MMA | +1.032 |
Vi | +1.023 |
Priv | +0.972 |
LX | +0.949 |
MV | +0.920 |
Neg logit contributions | |
gypt | -1.839 |
bee | -1.486 |
Bees | -1.467 |
wana | -1.460 |
gar | -1.460 |
Token | D |
Token ID | 360 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
MMA | +1.997 |
Vi | +1.988 |
Priv | +1.874 |
LX | +1.873 |
MV | +1.825 |
Neg logit contributions | |
gypt | -2.416 |
bee | -1.855 |
wana | -1.836 |
gar | -1.820 |
Bees | -1.812 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
gypt | +0.596 |
bee | +0.473 |
Bees | +0.464 |
wana | +0.463 |
gar | +0.462 |
Neg logit contributions | |
MMA | -0.424 |
Vi | -0.422 |
Priv | -0.404 |
LX | -0.396 |
MV | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
gypt | +1.150 |
bee | +0.917 |
gar | +0.900 |
Bees | +0.893 |
wana | +0.887 |
Neg logit contributions | |
MMA | -0.895 |
Vi | -0.893 |
Priv | -0.860 |
LX | -0.847 |
MV | -0.818 |
Token | Google |
Token ID | 11708 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
MMA | +1.740 |
Vi | +1.729 |
Priv | +1.676 |
LX | +1.621 |
MV | +1.583 |
Neg logit contributions | |
gypt | -2.334 |
bee | -1.836 |
Bees | -1.811 |
wana | -1.803 |
gar | -1.794 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
MMA | +0.533 |
Vi | +0.529 |
Priv | +0.504 |
LX | +0.494 |
MV | +0.480 |
Neg logit contributions | |
gypt | -0.809 |
bee | -0.644 |
Bees | -0.634 |
wana | -0.634 |
gar | -0.631 |
Token |
|
Token ID | 198 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
MMA | +2.026 |
Vi | +2.023 |
Priv | +1.929 |
LX | +1.879 |
MV | +1.810 |
Neg logit contributions | |
gypt | -3.383 |
bee | -2.749 |
Bees | -2.688 |
wana | -2.687 |
gar | -2.665 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
MMA | +4.774 |
Vi | +4.642 |
Priv | +4.371 |
MV | +4.195 |
LX | +4.167 |
Neg logit contributions | |
gypt | -8.860 |
wana | -6.981 |
gars | -6.939 |
Bees | -6.934 |
bee | -6.908 |
Token | Ol |
Token ID | 30098 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Priv | +8.999 |
MMA | +8.764 |
Vi | +8.638 |
MV | +8.034 |
LX | +7.868 |
Neg logit contributions | |
gypt | -11.883 |
Bees | -9.349 |
wana | -9.182 |
gars | -9.152 |
bee | -9.109 |
Token | we |
Token ID | 732 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
MMA | +0.784 |
Vi | +0.781 |
Priv | +0.748 |
LX | +0.728 |
MV | +0.703 |
Neg logit contributions | |
gypt | -1.321 |
bee | -1.071 |
gar | -1.053 |
wana | -1.047 |
Bees | -1.046 |
Token | us |
Token ID | 385 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
gypt | +0.833 |
bee | +0.652 |
gar | +0.640 |
Bees | +0.633 |
wana | +0.631 |
Neg logit contributions | |
MMA | -0.707 |
Vi | -0.702 |
Priv | -0.686 |
LX | -0.666 |
MV | -0.648 |
Token | , |
Token ID | 11 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
MMA | +0.543 |
Vi | +0.539 |
Priv | +0.510 |
LX | +0.500 |
MV | +0.484 |
Neg logit contributions | |
gypt | -0.952 |
bee | -0.768 |
Bees | -0.760 |
gar | -0.754 |
wana | -0.753 |
Token | D |
Token ID | 360 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
MMA | +0.560 |
Vi | +0.556 |
Priv | +0.535 |
LX | +0.523 |
MV | +0.508 |
Neg logit contributions | |
gypt | -0.783 |
bee | -0.622 |
Bees | -0.611 |
gar | -0.609 |
wana | -0.607 |
Token | | |
Token ID | 930 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
MMA | +1.965 |
Vi | +1.933 |
Priv | +1.839 |
LX | +1.800 |
MV | +1.729 |
Neg logit contributions | |
gypt | -3.497 |
bee | -2.826 |
Bees | -2.778 |
wana | -2.778 |
gar | -2.754 |
Token | Medline |
Token ID | 34582 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
gypt | +1.635 |
bee | +1.279 |
Bees | +1.278 |
gar | +1.266 |
gars | +1.235 |
Neg logit contributions | |
MMA | -1.370 |
Vi | -1.360 |
Priv | -1.333 |
LX | -1.299 |
strength | -1.256 |
Token | | |
Token ID | 930 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
gypt | +2.013 |
bee | +1.629 |
Bees | +1.602 |
gar | +1.600 |
wana | +1.593 |
Neg logit contributions | |
MMA | -1.190 |
Vi | -1.182 |
Priv | -1.129 |
LX | -1.101 |
MV | -1.066 |
Token | ISI |
Token ID | 22048 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
MMA | +1.191 |
Vi | +1.182 |
Priv | +1.144 |
LX | +1.124 |
MV | +1.097 |
Neg logit contributions | |
gypt | -1.234 |
bee | -0.944 |
Bees | -0.925 |
gar | -0.921 |
wana | -0.916 |
Token |
|
Token ID | 198 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
MMA | +0.833 |
Vi | +0.823 |
Priv | +0.786 |
LX | +0.769 |
MV | +0.747 |
Neg logit contributions | |
gypt | -1.266 |
bee | -1.014 |
Bees | -0.993 |
wana | -0.991 |
gar | -0.990 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
MMA | +4.607 |
Vi | +4.478 |
Priv | +4.213 |
MV | +4.084 |
LX | +4.052 |
Neg logit contributions | |
gypt | -8.267 |
wana | -6.491 |
gars | -6.465 |
bee | -6.444 |
Bees | -6.423 |
Token | My |
Token ID | 3666 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
Priv | +9.212 |
MMA | +8.972 |
Vi | +8.889 |
MV | +8.316 |
Mort | +8.186 |
Neg logit contributions | |
gypt | -10.854 |
Bees | -8.399 |
wana | -8.320 |
bee | -8.205 |
gars | -8.196 |
Token | ers |
Token ID | 364 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
gypt | +2.969 |
bee | +2.385 |
gar | +2.348 |
wana | +2.309 |
Bees | +2.299 |
Neg logit contributions | |
MMA | -2.083 |
Vi | -2.070 |
Priv | -2.004 |
LX | -1.947 |
MV | -1.898 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
MMA | +2.447 |
Vi | +2.402 |
Priv | +2.226 |
LX | +2.212 |
MV | +2.142 |
Neg logit contributions | |
gypt | -4.728 |
Bees | -3.776 |
wana | -3.775 |
bee | -3.766 |
gars | -3.712 |
Token | D |
Token ID | 360 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
MMA | +1.503 |
Vi | +1.492 |
Priv | +1.407 |
LX | +1.402 |
MV | +1.364 |
Neg logit contributions | |
gypt | -2.161 |
bee | -1.703 |
wana | -1.679 |
gar | -1.675 |
Bees | -1.666 |
Token | . |
Token ID | 13 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Vi | +2.528 |
MMA | +2.518 |
Priv | +2.353 |
LX | +2.288 |
MV | +2.208 |
Neg logit contributions | |
gypt | -5.685 |
bee | -4.690 |
wana | -4.658 |
Bees | -4.629 |
gar | -4.573 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
gypt | +2.236 |
bee | +1.769 |
Bees | +1.739 |
gar | +1.737 |
wana | +1.726 |
Neg logit contributions | |
MMA | -1.664 |
Vi | -1.650 |
Priv | -1.591 |
LX | -1.556 |
MV | -1.513 |
Token |
|
Token ID | 198 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
gypt | +2.011 |
bee | +1.612 |
gar | +1.582 |
Bees | +1.560 |
wana | +1.546 |
Neg logit contributions | |
Vi | -1.640 |
MMA | -1.640 |
Priv | -1.583 |
LX | -1.565 |
MV | -1.506 |
Token | Google |
Token ID | 11708 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
gypt | +0.285 |
bee | +0.218 |
gar | +0.213 |
Bees | +0.210 |
wana | +0.208 |
Neg logit contributions | |
MMA | -0.299 |
Vi | -0.297 |
Priv | -0.285 |
LX | -0.284 |
MV | -0.275 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
gypt | +0.754 |
bee | +0.602 |
gar | +0.591 |
Bees | +0.590 |
wana | +0.583 |
Neg logit contributions | |
MMA | -0.534 |
Vi | -0.531 |
Priv | -0.513 |
LX | -0.500 |
MV | -0.485 |
Token |
|
Token ID | 198 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
MMA | +1.395 |
Vi | +1.387 |
Priv | +1.325 |
LX | +1.299 |
MV | +1.257 |
Neg logit contributions | |
gypt | -2.213 |
bee | -1.783 |
wana | -1.749 |
Bees | -1.746 |
gar | -1.735 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
MMA | +3.995 |
Vi | +3.918 |
Priv | +3.719 |
LX | +3.562 |
MV | +3.535 |
Neg logit contributions | |
gypt | -7.002 |
wana | -5.507 |
bee | -5.484 |
Bees | -5.478 |
gars | -5.452 |
Token | Park |
Token ID | 25478 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
Priv | +8.299 |
Vi | +7.939 |
MMA | +7.924 |
LX | +7.224 |
MV | +7.202 |
Neg logit contributions | |
gypt | -11.739 |
Bees | -9.328 |
wana | -9.270 |
bee | -9.230 |
gars | -9.082 |
Token | er |
Token ID | 263 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
gypt | +0.935 |
bee | +0.757 |
gar | +0.742 |
wana | +0.734 |
Bees | +0.732 |
Neg logit contributions | |
MMA | -0.638 |
Vi | -0.630 |
Priv | -0.616 |
LX | -0.594 |
MV | -0.576 |
Token | , |
Token ID | 11 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
gypt | +0.376 |
bee | +0.303 |
Bees | +0.299 |
wana | +0.298 |
gar | +0.298 |
Neg logit contributions | |
MMA | -0.215 |
Vi | -0.214 |
Priv | -0.203 |
LX | -0.199 |
MV | -0.192 |
Token | A |
Token ID | 317 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
MMA | +1.255 |
Vi | +1.246 |
Priv | +1.178 |
LX | +1.171 |
MV | +1.139 |
Neg logit contributions | |
gypt | -1.802 |
bee | -1.421 |
wana | -1.399 |
gar | -1.398 |
Bees | -1.392 |
Token | . |
Token ID | 13 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
MMA | +1.197 |
Vi | +1.195 |
Priv | +1.126 |
LX | +1.095 |
MV | +1.059 |
Neg logit contributions | |
gypt | -2.436 |
bee | -1.996 |
wana | -1.979 |
Bees | -1.974 |
gar | -1.959 |
Token | x |
Token ID | 2124 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
MMA | +1.405 |
Vi | +1.386 |
Priv | +1.287 |
LX | +1.271 |
MV | +1.207 |
Neg logit contributions | |
gypt | -3.562 |
bee | -2.942 |
Bees | -2.911 |
wana | -2.906 |
gar | -2.899 |
Token | . |
Token ID | 13 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
MMA | +0.185 |
Vi | +0.184 |
Priv | +0.175 |
LX | +0.171 |
MV | +0.165 |
Neg logit contributions | |
gypt | -0.343 |
bee | -0.281 |
gar | -0.277 |
Bees | -0.275 |
wana | -0.274 |
Token | x |
Token ID | 87 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
gypt | +0.483 |
bee | +0.392 |
gar | +0.386 |
wana | +0.381 |
Bees | +0.381 |
Neg logit contributions | |
MMA | -0.300 |
Vi | -0.300 |
Priv | -0.285 |
LX | -0.279 |
MV | -0.271 |
Token | . |
Token ID | 13 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
MMA | +0.455 |
Vi | +0.453 |
Priv | +0.431 |
LX | +0.420 |
MV | +0.405 |
Neg logit contributions | |
gypt | -0.860 |
bee | -0.704 |
gar | -0.693 |
Bees | -0.691 |
wana | -0.688 |
Token | x |
Token ID | 87 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
MMA | +2.115 |
Vi | +2.082 |
Priv | +2.010 |
LX | +1.946 |
MV | +1.864 |
Neg logit contributions | |
gypt | -3.875 |
Bees | -3.129 |
bee | -3.119 |
wana | -3.081 |
gars | -3.055 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
MMA | +3.615 |
Vi | +3.497 |
Priv | +3.397 |
LX | +3.230 |
MV | +3.069 |
Neg logit contributions | |
gypt | -8.292 |
Bees | -6.849 |
wana | -6.745 |
bee | -6.740 |
gars | -6.736 |
Token | 121 |
Token ID | 19244 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
MMA | +4.344 |
Priv | +4.274 |
Vi | +4.080 |
LX | +3.731 |
strength | +3.543 |
Neg logit contributions | |
gypt | -14.887 |
Bees | -12.736 |
gars | -12.489 |
wana | -12.231 |
gar | -12.219 |
Token | 119 |
Token ID | 15136 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
MMA | +0.741 |
Vi | +0.735 |
Priv | +0.710 |
LX | +0.686 |
MV | +0.666 |
Neg logit contributions | |
gypt | -1.138 |
bee | -0.916 |
Bees | -0.901 |
gar | -0.898 |
wana | -0.891 |
Token | 47 |
Token ID | 2857 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
gypt | +2.474 |
bee | +1.952 |
gar | +1.885 |
Bees | +1.874 |
wana | +1.834 |
Neg logit contributions | |
Vi | -2.406 |
MMA | -2.398 |
Priv | -2.297 |
LX | -2.251 |
MV | -2.200 |
Token | 11 |
Token ID | 1157 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
MMA | +0.199 |
Vi | +0.198 |
Priv | +0.191 |
LX | +0.187 |
MV | +0.182 |
Neg logit contributions | |
gypt | -0.235 |
bee | -0.184 |
gar | -0.180 |
Bees | -0.180 |
wana | -0.178 |
Token | x |
Token ID | 2124 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
MMA | +0.525 |
Vi | +0.521 |
Priv | +0.494 |
LX | +0.477 |
MV | +0.458 |
Neg logit contributions | |
gypt | -1.214 |
bee | -1.007 |
Bees | -0.992 |
gar | -0.991 |
wana | -0.987 |
Token | with |
Token ID | 351 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
MMA | +1.169 |
Vi | +1.157 |
Priv | +1.106 |
LX | +1.082 |
MV | +1.053 |
Neg logit contributions | |
gypt | -1.724 |
bee | -1.373 |
Bees | -1.356 |
gar | -1.342 |
wana | -1.341 |
Token | all |
Token ID | 477 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
MMA | +4.789 |
Vi | +4.636 |
LX | +4.277 |
Priv | +4.246 |
MV | +4.238 |
Neg logit contributions | |
gypt | -7.209 |
bee | -5.678 |
wana | -5.671 |
Bees | -5.666 |
gars | -5.562 |
Token | the |
Token ID | 262 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
MMA | +0.649 |
Vi | +0.645 |
Priv | +0.620 |
LX | +0.606 |
MV | +0.588 |
Neg logit contributions | |
gypt | -0.914 |
bee | -0.726 |
Bees | -0.713 |
gar | -0.712 |
wana | -0.709 |
Token | other |
Token ID | 584 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
MMA | +0.047 |
Vi | +0.047 |
Priv | +0.046 |
LX | +0.044 |
MV | +0.043 |
Neg logit contributions | |
gypt | -0.067 |
bee | -0.053 |
gar | -0.052 |
Bees | -0.052 |
wana | -0.052 |
Token | ingredients |
Token ID | 9391 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
gypt | +1.650 |
bee | +1.316 |
gar | +1.299 |
Bees | +1.287 |
gars | +1.282 |
Neg logit contributions | |
MMA | -1.260 |
Vi | -1.259 |
Priv | -1.231 |
LX | -1.195 |
MV | -1.155 |
Token | and |
Token ID | 290 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
MMA | +2.319 |
Vi | +2.296 |
Priv | +2.170 |
LX | +2.117 |
MV | +2.070 |
Neg logit contributions | |
gypt | -3.780 |
bee | -3.020 |
Bees | -3.001 |
wana | -2.982 |
gar | -2.954 |
Token | mix |
Token ID | 5022 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
MMA | +4.342 |
Vi | +4.281 |
MV | +3.554 |
LX | +3.484 |
Priv | +3.419 |
Neg logit contributions | |
gypt | -14.401 |
Bees | -12.322 |
bee | -12.230 |
wana | -12.023 |
pees | -11.752 |
Token | well |
Token ID | 880 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
MMA | +2.862 |
Vi | +2.816 |
Priv | +2.668 |
LX | +2.592 |
MV | +2.562 |
Neg logit contributions | |
gypt | -4.099 |
Bees | -3.236 |
bee | -3.236 |
wana | -3.206 |
gars | -3.185 |
Token | until |
Token ID | 1566 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
MMA | +2.235 |
Vi | +2.217 |
Priv | +2.074 |
LX | +2.019 |
MV | +1.978 |
Neg logit contributions | |
gypt | -4.162 |
bee | -3.391 |
Bees | -3.373 |
wana | -3.322 |
gar | -3.297 |
Token | the |
Token ID | 262 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
MMA | +0.482 |
Vi | +0.478 |
Priv | +0.458 |
LX | +0.448 |
MV | +0.436 |
Neg logit contributions | |
gypt | -0.698 |
bee | -0.555 |
Bees | -0.546 |
wana | -0.544 |
gar | -0.544 |
Token | mixture |
Token ID | 11710 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
MMA | +2.992 |
Vi | +2.972 |
Priv | +2.772 |
LX | +2.720 |
MV | +2.691 |
Neg logit contributions | |
gypt | -5.333 |
bee | -4.319 |
Bees | -4.281 |
gar | -4.239 |
wana | -4.237 |
Token | s |
Token ID | 82 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
gypt | +1.305 |
bee | +1.034 |
Bees | +1.014 |
gar | +1.012 |
wana | +1.004 |
Neg logit contributions | |
MMA | -0.982 |
Vi | -0.974 |
Priv | -0.940 |
LX | -0.920 |
MV | -0.894 |
Token | )} |
Token ID | 38165 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
gypt | +0.739 |
bee | +0.598 |
Bees | +0.585 |
gar | +0.584 |
wana | +0.578 |
Neg logit contributions | |
MMA | -0.491 |
Vi | -0.490 |
Priv | -0.471 |
LX | -0.460 |
MV | -0.445 |
Token | 7 |
Token ID | 767 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
MMA | +0.484 |
Vi | +0.481 |
Priv | +0.462 |
LX | +0.452 |
MV | +0.436 |
Neg logit contributions | |
gypt | -0.761 |
bee | -0.612 |
Bees | -0.603 |
gar | -0.600 |
wana | -0.598 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
gypt | +0.478 |
bee | +0.392 |
gar | +0.385 |
Bees | +0.385 |
wana | +0.380 |
Neg logit contributions | |
MMA | -0.261 |
Vi | -0.259 |
Priv | -0.247 |
LX | -0.243 |
MV | -0.233 |
Token | N |
Token ID | 399 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
MMA | +1.986 |
Vi | +1.979 |
Priv | +1.880 |
LX | +1.849 |
MV | +1.797 |
Neg logit contributions | |
gypt | -2.816 |
bee | -2.224 |
wana | -2.188 |
gar | -2.184 |
Bees | -2.175 |
Token | b |
Token ID | 65 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
MMA | +2.316 |
Vi | +2.298 |
Priv | +2.230 |
LX | +2.150 |
MV | +2.071 |
Neg logit contributions | |
gypt | -3.430 |
Bees | -2.710 |
bee | -2.700 |
wana | -2.687 |
gar | -2.658 |
Token | 3 |
Token ID | 18 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
Vi | +6.256 |
MMA | +6.136 |
Priv | +5.959 |
LX | +5.691 |
Orn | +5.292 |
Neg logit contributions | |
gypt | -11.585 |
Bees | -9.378 |
wana | -9.334 |
gars | -9.297 |
gar | -9.125 |
Token | { |
Token ID | 1391 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
MMA | +3.687 |
Vi | +3.650 |
Priv | +3.370 |
LX | +3.283 |
MV | +3.142 |
Neg logit contributions | |
gypt | -8.290 |
wana | -6.816 |
bee | -6.699 |
gars | -6.681 |
gar | -6.679 |
Token | ( |
Token ID | 7 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
MMA | +0.122 |
Vi | +0.122 |
Priv | +0.116 |
LX | +0.114 |
MV | +0.111 |
Neg logit contributions | |
gypt | -0.169 |
bee | -0.135 |
gar | -0.132 |
Bees | -0.132 |
wana | -0.131 |
Token | 244 |
Token ID | 25707 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
MMA | +0.664 |
Vi | +0.660 |
Priv | +0.635 |
LX | +0.622 |
MV | +0.605 |
Neg logit contributions | |
gypt | -0.840 |
bee | -0.660 |
Bees | -0.646 |
gar | -0.646 |
wana | -0.642 |
Token | s |
Token ID | 82 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
gypt | +2.327 |
bee | +1.863 |
gar | +1.840 |
Bees | +1.794 |
gars | +1.789 |
Neg logit contributions | |
MMA | -1.996 |
Vi | -1.990 |
Priv | -1.948 |
LX | -1.913 |
MV | -1.840 |
Token | Eating |
Token ID | 37537 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
MMA | +1.390 |
Vi | +1.380 |
Priv | +1.323 |
LX | +1.295 |
MV | +1.257 |
Neg logit contributions | |
gypt | -2.049 |
bee | -1.633 |
Bees | -1.604 |
gar | -1.601 |
wana | -1.597 |
Token | a |
Token ID | 257 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
gypt | +1.506 |
bee | +1.185 |
gar | +1.175 |
Bees | +1.165 |
wana | +1.146 |
Neg logit contributions | |
MMA | -1.285 |
Vi | -1.284 |
Priv | -1.252 |
LX | -1.198 |
MV | -1.168 |
Token | L |
Token ID | 406 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
MMA | +0.821 |
Vi | +0.817 |
Priv | +0.790 |
LX | +0.767 |
MV | +0.745 |
Neg logit contributions | |
gypt | -1.086 |
bee | -0.861 |
gar | -0.845 |
Bees | -0.843 |
wana | -0.835 |
Token | CH |
Token ID | 3398 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
gypt | +2.446 |
bee | +1.933 |
gar | +1.887 |
wana | +1.873 |
Bees | +1.857 |
Neg logit contributions | |
Vi | -2.125 |
MMA | -2.095 |
Priv | -2.039 |
LX | -1.998 |
MV | -1.915 |
Token | F |
Token ID | 37 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
MMA | +0.521 |
Vi | +0.518 |
Priv | +0.503 |
LX | +0.489 |
MV | +0.478 |
Neg logit contributions | |
gypt | -0.635 |
bee | -0.498 |
Bees | -0.488 |
gar | -0.486 |
wana | -0.483 |
Token | ( |
Token ID | 357 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
gypt | +0.268 |
bee | +0.215 |
gar | +0.211 |
Bees | +0.210 |
wana | +0.208 |
Neg logit contributions | |
MMA | -0.199 |
Vi | -0.198 |
Priv | -0.192 |
LX | -0.185 |
MV | -0.179 |
Token | Low |
Token ID | 20535 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
MMA | +7.714 |
Vi | +7.402 |
Priv | +7.283 |
LX | +7.139 |
MV | +7.010 |
Neg logit contributions | |
gypt | -10.355 |
Bees | -8.183 |
wana | -8.020 |
gars | -7.835 |
bee | -7.785 |
Token | Carb |
Token ID | 20453 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
MMA | +0.919 |
Vi | +0.915 |
Priv | +0.882 |
LX | +0.860 |
MV | +0.835 |
Neg logit contributions | |
gypt | -1.261 |
bee | -1.001 |
Bees | -0.984 |
gar | -0.982 |
wana | -0.977 |
Token | High |
Token ID | 3334 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
MMA | +1.708 |
Vi | +1.693 |
Priv | +1.617 |
LX | +1.589 |
MV | +1.544 |
Neg logit contributions | |
gypt | -2.435 |
bee | -1.928 |
Bees | -1.894 |
wana | -1.892 |
gar | -1.890 |
Token | Fat |
Token ID | 12301 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
MMA | +0.201 |
Vi | +0.200 |
Priv | +0.194 |
LX | +0.188 |
MV | +0.183 |
Neg logit contributions | |
gypt | -0.272 |
bee | -0.216 |
Bees | -0.213 |
gar | -0.213 |
wana | -0.211 |
Token | ) |
Token ID | 8 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
MMA | +0.318 |
Vi | +0.317 |
Priv | +0.307 |
LX | +0.296 |
MV | +0.286 |
Neg logit contributions | |
gypt | -0.534 |
bee | -0.436 |
gar | -0.430 |
Bees | -0.429 |
wana | -0.425 |
Token | , |
Token ID | 11 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
MMA | +2.783 |
Vi | +2.772 |
Priv | +2.596 |
LX | +2.551 |
MV | +2.492 |
Neg logit contributions | |
gypt | -4.284 |
bee | -3.356 |
Bees | -3.338 |
wana | -3.324 |
gar | -3.305 |
Token | Baltimore |
Token ID | 10346 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
MMA | +0.433 |
Vi | +0.430 |
Priv | +0.413 |
LX | +0.404 |
MV | +0.393 |
Neg logit contributions | |
gypt | -0.601 |
bee | -0.476 |
Bees | -0.468 |
gar | -0.467 |
wana | -0.465 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
MMA | +1.747 |
Vi | +1.739 |
Priv | +1.675 |
LX | +1.649 |
MV | +1.617 |
Neg logit contributions | |
gypt | -1.644 |
bee | -1.222 |
wana | -1.197 |
gar | -1.196 |
Bees | -1.194 |
Token | The |
Token ID | 464 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
MMA | +1.590 |
Vi | +1.577 |
Priv | +1.539 |
LX | +1.492 |
MV | +1.458 |
Neg logit contributions | |
gypt | -1.783 |
bee | -1.367 |
Bees | -1.353 |
wana | -1.341 |
gar | -1.334 |
Token | opinions |
Token ID | 9317 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
gypt | +0.286 |
bee | +0.226 |
Bees | +0.223 |
gar | +0.221 |
wana | +0.220 |
Neg logit contributions | |
MMA | -0.215 |
Vi | -0.213 |
Priv | -0.206 |
LX | -0.201 |
MV | -0.195 |
Token | expressed |
Token ID | 6241 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
MMA | +1.453 |
Vi | +1.442 |
Priv | +1.374 |
LX | +1.339 |
MV | +1.295 |
Neg logit contributions | |
gypt | -2.591 |
bee | -2.104 |
Bees | -2.071 |
gar | -2.065 |
wana | -2.060 |
Token | by |
Token ID | 416 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
MMA | +5.580 |
Vi | +5.425 |
Priv | +5.231 |
MV | +4.950 |
LX | +4.942 |
Neg logit contributions | |
gypt | -11.933 |
Bees | -9.863 |
bee | -9.641 |
pees | -9.554 |
wana | -9.546 |
Token | column |
Token ID | 5721 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
MMA | +3.025 |
Vi | +2.933 |
Priv | +2.713 |
LX | +2.526 |
Orn | +2.511 |
Neg logit contributions | |
gypt | -8.866 |
bee | -7.404 |
wana | -7.388 |
gar | -7.253 |
gars | -7.141 |
Token | ists |
Token ID | 1023 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
MMA | +1.061 |
Vi | +1.052 |
Priv | +0.996 |
LX | +0.973 |
MV | +0.939 |
Neg logit contributions | |
gypt | -1.905 |
bee | -1.546 |
wana | -1.520 |
Bees | -1.516 |
gar | -1.514 |
Token | are |
Token ID | 389 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
MMA | +3.724 |
Vi | +3.510 |
Priv | +3.319 |
LX | +3.214 |
Mort | +3.205 |
Neg logit contributions | |
gypt | -7.726 |
bee | -6.254 |
gars | -6.163 |
Bees | -6.133 |
gar | -6.128 |
Token | their |
Token ID | 511 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
MMA | +3.291 |
Vi | +3.289 |
Priv | +3.091 |
LX | +3.017 |
MV | +2.951 |
Neg logit contributions | |
gypt | -5.781 |
bee | -4.582 |
wana | -4.546 |
Bees | -4.542 |
gar | -4.515 |
Token | house |
Token ID | 2156 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
MMA | +0.198 |
Vi | +0.195 |
Priv | +0.189 |
LX | +0.184 |
MV | +0.178 |
Neg logit contributions | |
gypt | -0.292 |
bee | -0.234 |
Bees | -0.230 |
gar | -0.229 |
wana | -0.228 |
Token | on |
Token ID | 319 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
MMA | +0.390 |
Vi | +0.387 |
Priv | +0.369 |
LX | +0.361 |
MV | +0.350 |
Neg logit contributions | |
gypt | -0.615 |
bee | -0.493 |
Bees | -0.486 |
wana | -0.484 |
gar | -0.484 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Vi | +1.252 |
MMA | +1.252 |
Priv | +1.187 |
LX | +1.168 |
MV | +1.139 |
Neg logit contributions | |
gypt | -1.735 |
bee | -1.371 |
gar | -1.344 |
wana | -1.342 |
Bees | -1.340 |
Token | r |
Token ID | 374 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
MMA | +1.618 |
Vi | +1.616 |
Priv | +1.542 |
LX | +1.518 |
MV | +1.482 |
Neg logit contributions | |
gypt | -2.003 |
bee | -1.563 |
gar | -1.528 |
Bees | -1.526 |
wana | -1.525 |
Token | ue |
Token ID | 518 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
MMA | +1.600 |
Vi | +1.589 |
Priv | +1.533 |
LX | +1.503 |
MV | +1.465 |
Neg logit contributions | |
gypt | -1.865 |
bee | -1.448 |
Bees | -1.419 |
gar | -1.417 |
wana | -1.411 |
Token | du |
Token ID | 7043 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Vi | +2.737 |
MMA | +2.708 |
Priv | +2.539 |
LX | +2.529 |
Mort | +2.465 |
Neg logit contributions | |
gypt | -3.930 |
bee | -3.117 |
wana | -3.091 |
Bees | -3.059 |
gar | -3.041 |
Token | Vie |
Token ID | 47154 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
Vi | +8.050 |
MMA | +7.853 |
Mort | +7.469 |
LX | +7.408 |
Priv | +7.358 |
Neg logit contributions | |
gypt | -9.461 |
bee | -7.466 |
gars | -7.332 |
acca | -7.293 |
wana | -7.268 |
Token | ux |
Token ID | 2821 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
Vi | +4.576 |
MMA | +4.496 |
Priv | +4.242 |
LX | +4.228 |
Mort | +4.140 |
Neg logit contributions | |
gypt | -6.606 |
bee | -5.259 |
Bees | -5.230 |
wana | -5.198 |
acca | -5.124 |
Token | - |
Token ID | 12 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Vi | +4.307 |
MMA | +4.209 |
Priv | +3.988 |
LX | +3.941 |
Mort | +3.881 |
Neg logit contributions | |
gypt | -6.046 |
bee | -4.762 |
wana | -4.741 |
Bees | -4.707 |
gars | -4.658 |
Token | Col |
Token ID | 5216 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Vi | +4.330 |
MMA | +4.258 |
Priv | +4.216 |
LX | +4.012 |
MV | +3.946 |
Neg logit contributions | |
gypt | -4.923 |
Bees | -3.802 |
bee | -3.773 |
wana | -3.762 |
acca | -3.682 |
Token | omb |
Token ID | 2381 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
MMA | +2.999 |
Vi | +2.963 |
Priv | +2.848 |
LX | +2.801 |
MV | +2.726 |
Neg logit contributions | |
gypt | -3.691 |
bee | -2.871 |
Bees | -2.864 |
wana | -2.811 |
gar | -2.790 |
Token | . |
Token ID | 13 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
gypt | +0.222 |
bee | +0.179 |
gar | +0.176 |
Bees | +0.175 |
wana | +0.175 |
Neg logit contributions | |
MMA | -0.135 |
Vi | -0.134 |
Priv | -0.128 |
LX | -0.125 |
MV | -0.121 |
Token | com |
Token ID | 785 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
gypt | +0.781 |
bee | +0.624 |
gar | +0.612 |
Bees | +0.611 |
wana | +0.608 |
Neg logit contributions | |
MMA | -0.558 |
Vi | -0.553 |
Priv | -0.530 |
LX | -0.520 |
MV | -0.505 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
gypt | +1.571 |
bee | +1.257 |
gar | +1.234 |
Bees | +1.233 |
wana | +1.219 |
Neg logit contributions | |
MMA | -1.127 |
Vi | -1.122 |
Priv | -1.088 |
LX | -1.052 |
MV | -1.024 |
Token |
|
Token ID | 198 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
gypt | +1.744 |
bee | +1.398 |
gar | +1.369 |
Bees | +1.354 |
wana | +1.342 |
Neg logit contributions | |
Vi | -1.394 |
MMA | -1.392 |
Priv | -1.340 |
LX | -1.323 |
MV | -1.277 |
Token | All |
Token ID | 3237 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
gypt | +0.694 |
bee | +0.548 |
gar | +0.537 |
Bees | +0.529 |
wana | +0.529 |
Neg logit contributions | |
MMA | -0.580 |
Vi | -0.578 |
Priv | -0.546 |
LX | -0.545 |
MV | -0.531 |
Token | content |
Token ID | 2695 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
MMA | +3.499 |
Vi | +3.456 |
Priv | +3.317 |
LX | +3.251 |
MV | +3.167 |
Neg logit contributions | |
gypt | -4.890 |
bee | -3.837 |
Bees | -3.773 |
gar | -3.764 |
wana | -3.749 |
Token | on |
Token ID | 319 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Vi | +6.541 |
MMA | +6.534 |
LX | +6.104 |
Priv | +6.020 |
MV | +5.905 |
Neg logit contributions | |
gypt | -10.984 |
bee | -8.820 |
gars | -8.685 |
Bees | -8.633 |
gar | -8.519 |
Token | Lac |
Token ID | 23115 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
MMA | +2.862 |
Vi | +2.847 |
Priv | +2.736 |
LX | +2.697 |
MV | +2.626 |
Neg logit contributions | |
gypt | -3.110 |
bee | -2.382 |
gar | -2.330 |
Bees | -2.321 |
wana | -2.318 |
Token | an |
Token ID | 272 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
MMA | +0.475 |
Vi | +0.472 |
Priv | +0.455 |
LX | +0.447 |
MV | +0.436 |
Neg logit contributions | |
gypt | -0.514 |
bee | -0.395 |
Bees | -0.387 |
gar | -0.386 |
wana | -0.385 |
Token | Online |
Token ID | 14439 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
MMA | +1.317 |
Vi | +1.307 |
Priv | +1.257 |
LX | +1.234 |
MV | +1.199 |
Neg logit contributions | |
gypt | -1.701 |
bee | -1.339 |
Bees | -1.314 |
gar | -1.312 |
wana | -1.306 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
MMA | +1.411 |
Vi | +1.394 |
Priv | +1.332 |
LX | +1.288 |
MV | +1.248 |
Neg logit contributions | |
gypt | -2.822 |
bee | -2.311 |
Bees | -2.276 |
wana | -2.269 |
gar | -2.266 |
Token | to |
Token ID | 284 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
gypt | +1.253 |
bee | +1.000 |
gar | +0.982 |
Bees | +0.974 |
wana | +0.969 |
Neg logit contributions | |
MMA | -0.905 |
Vi | -0.892 |
Priv | -0.862 |
LX | -0.837 |
MV | -0.817 |
Token | the |
Token ID | 262 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
gypt | +0.804 |
bee | +0.650 |
gar | +0.642 |
Bees | +0.639 |
wana | +0.635 |
Neg logit contributions | |
MMA | -0.478 |
Vi | -0.473 |
Priv | -0.455 |
LX | -0.439 |
MV | -0.427 |
Token | 19 |
Token ID | 678 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
MMA | +0.038 |
Vi | +0.037 |
Priv | +0.036 |
LX | +0.035 |
MV | +0.034 |
Neg logit contributions | |
gypt | -0.053 |
bee | -0.042 |
Bees | -0.041 |
gar | -0.041 |
wana | -0.041 |
Token | th |
Token ID | 400 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
MMA | +1.408 |
Vi | +1.400 |
Priv | +1.351 |
LX | +1.324 |
MV | +1.291 |
Neg logit contributions | |
gypt | -1.604 |
bee | -1.241 |
Bees | -1.216 |
gar | -1.212 |
wana | -1.209 |
Token | partition |
Token ID | 18398 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
MMA | +1.123 |
Vi | +1.117 |
Priv | +1.065 |
LX | +1.037 |
MV | +1.000 |
Neg logit contributions | |
gypt | -2.071 |
bee | -1.681 |
Bees | -1.656 |
wana | -1.651 |
gar | -1.645 |
Token | (/ |
Token ID | 50247 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
MMA | +2.202 |
Vi | +2.185 |
Priv | +2.021 |
LX | +1.983 |
MV | +1.848 |
Neg logit contributions | |
gypt | -7.010 |
bee | -5.844 |
wana | -5.769 |
Bees | -5.766 |
gars | -5.720 |
Token | dev |
Token ID | 7959 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Vi | +5.268 |
MMA | +5.183 |
Priv | +5.076 |
LX | +4.826 |
MV | +4.470 |
Neg logit contributions | |
gypt | -11.628 |
wana | -9.551 |
Bees | -9.508 |
bee | -9.270 |
gars | -9.212 |
Token | / |
Token ID | 14 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
MMA | +0.768 |
Vi | +0.760 |
Priv | +0.721 |
LX | +0.700 |
MV | +0.674 |
Neg logit contributions | |
gypt | -1.617 |
bee | -1.328 |
Bees | -1.310 |
gar | -1.306 |
wana | -1.304 |
Token | block |
Token ID | 9967 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
MMA | +2.220 |
Vi | +2.189 |
Priv | +2.110 |
LX | +2.044 |
MV | +1.963 |
Neg logit contributions | |
gypt | -4.653 |
bee | -3.774 |
Bees | -3.771 |
wana | -3.757 |
gars | -3.700 |
Token | / |
Token ID | 14 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
gypt | +0.250 |
bee | +0.203 |
gar | +0.200 |
Bees | +0.197 |
wana | +0.195 |
Neg logit contributions | |
MMA | -0.176 |
Vi | -0.175 |
Priv | -0.168 |
LX | -0.164 |
MV | -0.159 |
Token | mm |
Token ID | 3020 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
gypt | +0.279 |
bee | +0.226 |
gar | +0.223 |
Bees | +0.219 |
wana | +0.219 |
Neg logit contributions | |
Vi | -0.185 |
MMA | -0.185 |
Priv | -0.175 |
LX | -0.172 |
MV | -0.166 |
Token | successful |
Token ID | 4388 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
MMA | +1.287 |
Vi | +1.279 |
Priv | +1.232 |
LX | +1.208 |
MV | +1.177 |
Neg logit contributions | |
gypt | -1.553 |
bee | -1.211 |
Bees | -1.188 |
gar | -1.185 |
wana | -1.181 |
Token | performance |
Token ID | 2854 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
MMA | +1.515 |
Vi | +1.504 |
Priv | +1.443 |
LX | +1.412 |
MV | +1.372 |
Neg logit contributions | |
gypt | -2.158 |
bee | -1.715 |
Bees | -1.685 |
gar | -1.681 |
wana | -1.676 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
MMA | +1.010 |
Vi | +1.003 |
Priv | +0.961 |
LX | +0.939 |
MV | +0.911 |
Neg logit contributions | |
gypt | -1.530 |
bee | -1.225 |
Bees | -1.204 |
gar | -1.201 |
wana | -1.197 |
Token | while |
Token ID | 981 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
gypt | +1.687 |
bee | +1.345 |
Bees | +1.322 |
gar | +1.318 |
wana | +1.306 |
Neg logit contributions | |
MMA | -1.245 |
Vi | -1.240 |
Priv | -1.201 |
LX | -1.165 |
MV | -1.131 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
MMA | +1.053 |
Vi | +1.046 |
Priv | +1.004 |
LX | +0.982 |
MV | +0.954 |
Neg logit contributions | |
gypt | -1.482 |
bee | -1.177 |
Bees | -1.156 |
gar | -1.154 |
wana | -1.150 |
Token | sax |
Token ID | 46909 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
MMA | +0.837 |
Vi | +0.831 |
Priv | +0.797 |
LX | +0.780 |
MV | +0.757 |
Neg logit contributions | |
gypt | -1.185 |
bee | -0.941 |
Bees | -0.924 |
gar | -0.922 |
wana | -0.920 |
Token | ophon |
Token ID | 48982 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
Vi | +4.883 |
MMA | +4.865 |
Priv | +4.512 |
LX | +4.392 |
MV | +4.189 |
Neg logit contributions | |
gypt | -11.931 |
Bees | -9.775 |
bee | -9.655 |
gars | -9.594 |
wana | -9.565 |
Token | ist |
Token ID | 396 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
MMA | +2.386 |
Vi | +2.359 |
Priv | +2.175 |
LX | +2.122 |
MV | +2.053 |
Neg logit contributions | |
gypt | -6.642 |
bee | -5.509 |
Bees | -5.496 |
gars | -5.423 |
wana | -5.423 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
MMA | +2.314 |
Vi | +2.295 |
Priv | +2.173 |
LX | +2.148 |
MV | +2.077 |
Neg logit contributions | |
gypt | -3.485 |
bee | -2.766 |
wana | -2.730 |
Bees | -2.727 |
gar | -2.700 |
Token | this |
Token ID | 428 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
MMA | +1.288 |
Vi | +1.278 |
Priv | +1.229 |
LX | +1.203 |
MV | +1.170 |
Neg logit contributions | |
gypt | -1.723 |
bee | -1.360 |
Bees | -1.334 |
gar | -1.332 |
wana | -1.328 |
Token | performance |
Token ID | 2854 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
gypt | +0.843 |
bee | +0.665 |
Bees | +0.654 |
gar | +0.651 |
wana | +0.642 |
Neg logit contributions | |
MMA | -0.664 |
Vi | -0.661 |
Priv | -0.640 |
LX | -0.624 |
MV | -0.604 |
Token | - |
Token ID | 532 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
MMA | +1.766 |
Vi | +1.742 |
Priv | +1.698 |
LX | +1.670 |
MV | +1.634 |
Neg logit contributions | |
gypt | -1.840 |
bee | -1.378 |
wana | -1.376 |
Bees | -1.362 |
gar | -1.353 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
MMA | +2.846 |
Vi | +2.777 |
LX | +2.612 |
MV | +2.554 |
Priv | +2.532 |
Neg logit contributions | |
gypt | -5.108 |
bee | -4.093 |
wana | -4.052 |
Bees | -4.036 |
gars | -3.998 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
MMA | +3.818 |
Vi | +3.738 |
MV | +3.478 |
LX | +3.470 |
Priv | +3.323 |
Neg logit contributions | |
gypt | -6.792 |
bee | -5.405 |
wana | -5.396 |
Bees | -5.387 |
gar | -5.358 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
MMA | +3.864 |
Vi | +3.790 |
MV | +3.531 |
LX | +3.518 |
Priv | +3.359 |
Neg logit contributions | |
gypt | -6.847 |
bee | -5.441 |
wana | -5.433 |
Bees | -5.420 |
gar | -5.396 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
MMA | +3.969 |
Vi | +3.909 |
MV | +3.668 |
LX | +3.634 |
Priv | +3.502 |
Neg logit contributions | |
gypt | -6.862 |
bee | -5.431 |
wana | -5.379 |
Bees | -5.378 |
gar | -5.366 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
MMA | +5.079 |
Vi | +4.991 |
MV | +4.736 |
LX | +4.648 |
Priv | +4.545 |
Neg logit contributions | |
gypt | -7.775 |
wana | -6.046 |
bee | -6.014 |
gar | -6.004 |
Bees | -5.970 |
Token | - |
Token ID | 532 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
MMA | +6.966 |
Vi | +6.809 |
MV | +6.440 |
LX | +6.373 |
Priv | +6.338 |
Neg logit contributions | |
gypt | -9.439 |
wana | -7.299 |
gar | -7.236 |
bee | -7.122 |
gars | -7.082 |
Token | February |
Token ID | 3945 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
MMA | +3.121 |
Vi | +3.083 |
LX | +2.866 |
Priv | +2.820 |
MV | +2.791 |
Neg logit contributions | |
gypt | -4.986 |
bee | -3.941 |
wana | -3.907 |
gars | -3.850 |
pees | -3.839 |
Token | 9 |
Token ID | 860 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
gypt | +1.226 |
bee | +0.990 |
Bees | +0.969 |
gar | +0.963 |
wana | +0.949 |
Neg logit contributions | |
MMA | -0.887 |
Vi | -0.883 |
Priv | -0.868 |
LX | -0.829 |
MV | -0.806 |
Token | , |
Token ID | 11 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
MMA | +1.032 |
Vi | +1.015 |
Priv | +0.970 |
LX | +0.938 |
MV | +0.913 |
Neg logit contributions | |
gypt | -1.923 |
bee | -1.547 |
Bees | -1.534 |
wana | -1.533 |
gar | -1.520 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
MMA | +3.208 |
Vi | +3.197 |
Priv | +3.068 |
LX | +3.027 |
MV | +2.967 |
Neg logit contributions | |
gypt | -3.882 |
bee | -2.956 |
wana | -2.946 |
acca | -2.923 |
gars | -2.851 |
Token | s |
Token ID | 82 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
gypt | +1.614 |
bee | +1.283 |
gar | +1.266 |
Bees | +1.241 |
gars | +1.237 |
Neg logit contributions | |
MMA | -1.346 |
Vi | -1.334 |
Priv | -1.303 |
LX | -1.279 |
MV | -1.234 |
Token | )} |
Token ID | 38165 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
gypt | +0.942 |
bee | +0.763 |
Bees | +0.744 |
gar | +0.744 |
wana | +0.735 |
Neg logit contributions | |
MMA | -0.638 |
Vi | -0.638 |
Priv | -0.612 |
LX | -0.599 |
MV | -0.579 |
Token | 18 |
Token ID | 1248 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
gypt | +2.183 |
bee | +1.646 |
Bees | +1.627 |
gar | +1.595 |
wana | +1.577 |
Neg logit contributions | |
MMA | -2.453 |
Vi | -2.433 |
Priv | -2.386 |
LX | -2.339 |
MV | -2.271 |
Token | . |
Token ID | 13 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
gypt | +0.425 |
bee | +0.348 |
gar | +0.342 |
Bees | +0.342 |
wana | +0.338 |
Neg logit contributions | |
MMA | -0.231 |
Vi | -0.229 |
Priv | -0.219 |
LX | -0.214 |
MV | -0.206 |
Token | N |
Token ID | 399 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
MMA | +2.370 |
Vi | +2.370 |
Priv | +2.235 |
LX | +2.203 |
MV | +2.145 |
Neg logit contributions | |
gypt | -3.479 |
bee | -2.750 |
wana | -2.715 |
gar | -2.704 |
Bees | -2.687 |
Token | b |
Token ID | 65 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
MMA | +2.628 |
Vi | +2.608 |
Priv | +2.546 |
LX | +2.442 |
MV | +2.359 |
Neg logit contributions | |
gypt | -3.676 |
Bees | -2.894 |
bee | -2.864 |
wana | -2.860 |
gar | -2.820 |
Token | 5 |
Token ID | 20 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
Vi | +5.827 |
MMA | +5.785 |
Priv | +5.636 |
LX | +5.296 |
strength | +5.054 |
Neg logit contributions | |
gypt | -10.553 |
Bees | -8.521 |
wana | -8.429 |
gars | -8.339 |
bee | -8.286 |
Token | { |
Token ID | 1391 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
MMA | +3.469 |
Vi | +3.441 |
Priv | +3.169 |
LX | +3.068 |
MV | +2.964 |
Neg logit contributions | |
gypt | -8.194 |
wana | -6.749 |
bee | -6.660 |
gar | -6.620 |
pees | -6.610 |
Token | ( |
Token ID | 7 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
gypt | +0.147 |
bee | +0.117 |
gar | +0.115 |
Bees | +0.114 |
wana | +0.114 |
Neg logit contributions | |
MMA | -0.106 |
Vi | -0.106 |
Priv | -0.101 |
LX | -0.100 |
MV | -0.096 |
Token | 536 |
Token ID | 44468 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
MMA | +0.862 |
Vi | +0.857 |
Priv | +0.826 |
LX | +0.810 |
MV | +0.788 |
Neg logit contributions | |
gypt | -1.032 |
bee | -0.805 |
Bees | -0.789 |
gar | -0.787 |
wana | -0.784 |
Token | s |
Token ID | 82 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
gypt | +0.646 |
bee | +0.515 |
gar | +0.507 |
Bees | +0.502 |
wana | +0.496 |
Neg logit contributions | |
MMA | -0.518 |
Vi | -0.516 |
Priv | -0.500 |
LX | -0.491 |
MV | -0.475 |
Token | � |
Token ID | 247 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
gypt | +0.003 |
bee | +0.002 |
gar | +0.002 |
Bees | +0.002 |
wana | +0.002 |
Neg logit contributions | |
MMA | -0.003 |
Vi | -0.003 |
Priv | -0.003 |
LX | -0.003 |
MV | -0.002 |
Token | s |
Token ID | 82 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
MMA | +1.350 |
Vi | +1.336 |
Priv | +1.285 |
LX | +1.252 |
MV | +1.214 |
Neg logit contributions | |
gypt | -1.983 |
bee | -1.568 |
Bees | -1.557 |
wana | -1.547 |
gar | -1.523 |
Token | bonus |
Token ID | 7202 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
gypt | +2.129 |
bee | +1.653 |
gar | +1.611 |
Bees | +1.595 |
acca | +1.588 |
Neg logit contributions | |
Vi | -2.107 |
MMA | -2.081 |
Priv | -2.076 |
LX | -2.011 |
シャ | -1.943 |
Token | , |
Token ID | 11 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
MMA | +1.476 |
Vi | +1.452 |
Priv | +1.387 |
LX | +1.343 |
MV | +1.307 |
Neg logit contributions | |
gypt | -2.731 |
bee | -2.200 |
Bees | -2.178 |
wana | -2.174 |
gar | -2.161 |
Token | but |
Token ID | 475 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
MMA | +2.510 |
Vi | +2.482 |
Priv | +2.353 |
LX | +2.307 |
MV | +2.266 |
Neg logit contributions | |
gypt | -3.568 |
bee | -2.803 |
Bees | -2.768 |
wana | -2.762 |
gar | -2.739 |
Token | now |
Token ID | 783 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
MMA | +1.840 |
Vi | +1.825 |
Priv | +1.726 |
LX | +1.698 |
MV | +1.642 |
Neg logit contributions | |
gypt | -3.158 |
bee | -2.547 |
Bees | -2.518 |
wana | -2.497 |
gar | -2.487 |
Token | rather |
Token ID | 2138 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
Vi | +5.164 |
MMA | +5.028 |
Priv | +4.622 |
LX | +4.570 |
MV | +4.490 |
Neg logit contributions | |
gypt | -11.215 |
acca | -9.356 |
bee | -9.333 |
Bees | -9.329 |
wana | -9.279 |
Token | than |
Token ID | 621 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
MMA | +0.725 |
Vi | +0.720 |
Priv | +0.693 |
LX | +0.678 |
MV | +0.660 |
Neg logit contributions | |
gypt | -0.939 |
bee | -0.739 |
Bees | -0.725 |
gar | -0.724 |
wana | -0.721 |
Token | having |
Token ID | 1719 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
MMA | +2.485 |
Vi | +2.453 |
Priv | +2.250 |
LX | +2.231 |
MV | +2.177 |
Neg logit contributions | |
gypt | -4.472 |
bee | -3.632 |
Bees | -3.597 |
wana | -3.581 |
gars | -3.565 |
Token | the |
Token ID | 262 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
gypt | +1.625 |
bee | +1.292 |
gar | +1.272 |
Bees | +1.257 |
wana | +1.237 |
Neg logit contributions | |
MMA | -1.270 |
Vi | -1.268 |
Priv | -1.237 |
LX | -1.206 |
MV | -1.167 |
Token | sign |
Token ID | 1051 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
gypt | +1.016 |
bee | +0.849 |
gar | +0.840 |
Bees | +0.834 |
wana | +0.826 |
Neg logit contributions | |
MMA | -0.385 |
Vi | -0.382 |
Priv | -0.366 |
LX | -0.352 |
MV | -0.334 |
Token | the |
Token ID | 262 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
MMA | +0.602 |
Vi | +0.597 |
Priv | +0.574 |
LX | +0.563 |
MV | +0.548 |
Neg logit contributions | |
gypt | -0.776 |
bee | -0.610 |
Bees | -0.599 |
gar | -0.598 |
wana | -0.596 |
Token | North |
Token ID | 2258 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
MMA | +0.752 |
Vi | +0.747 |
Priv | +0.717 |
LX | +0.709 |
MV | +0.693 |
Neg logit contributions | |
gypt | -0.773 |
bee | -0.589 |
gar | -0.575 |
Bees | -0.574 |
wana | -0.573 |
Token | Atlantic |
Token ID | 10596 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
gypt | +2.508 |
bee | +1.964 |
Bees | +1.929 |
gar | +1.925 |
wana | +1.911 |
Neg logit contributions | |
MMA | -2.109 |
Vi | -2.092 |
Priv | -2.036 |
LX | -1.989 |
MV | -1.928 |
Token | and |
Token ID | 290 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
MMA | +1.468 |
Vi | +1.453 |
Priv | +1.383 |
LX | +1.368 |
MV | +1.323 |
Neg logit contributions | |
gypt | -2.362 |
bee | -1.894 |
gar | -1.861 |
Bees | -1.858 |
wana | -1.851 |
Token | North |
Token ID | 2258 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
MMA | +1.410 |
Vi | +1.399 |
Priv | +1.335 |
LX | +1.321 |
MV | +1.285 |
Neg logit contributions | |
gypt | -1.831 |
bee | -1.443 |
gar | -1.413 |
Bees | -1.409 |
wana | -1.406 |
Token | Pacific |
Token ID | 8211 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
gypt | +2.148 |
bee | +1.715 |
gar | +1.698 |
Bees | +1.695 |
wana | +1.682 |
Neg logit contributions | |
MMA | -1.499 |
Vi | -1.482 |
Priv | -1.471 |
LX | -1.408 |
MV | -1.359 |
Token | O |
Token ID | 440 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
MMA | +5.160 |
Vi | +5.068 |
LX | +4.927 |
Orn | +4.616 |
MV | +4.615 |
Neg logit contributions | |
gypt | -11.244 |
bee | -9.104 |
gars | -8.992 |
gar | -8.940 |
pees | -8.915 |
Token | ceans |
Token ID | 19961 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
gypt | +1.211 |
bee | +0.843 |
gar | +0.820 |
Bees | +0.810 |
wana | +0.806 |
Neg logit contributions | |
MMA | -1.891 |
Vi | -1.885 |
Priv | -1.829 |
LX | -1.805 |
MV | -1.769 |
Token | , |
Token ID | 11 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
MMA | +0.686 |
Vi | +0.680 |
Priv | +0.650 |
LX | +0.636 |
MV | +0.616 |
Neg logit contributions | |
gypt | -1.126 |
bee | -0.908 |
Bees | -0.893 |
gar | -0.891 |
wana | -0.887 |
Token | � |
Token ID | 447 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
MMA | +2.815 |
Vi | +2.791 |
Priv | +2.676 |
LX | +2.655 |
MV | +2.586 |
Neg logit contributions | |
gypt | -2.975 |
bee | -2.293 |
Bees | -2.243 |
gar | -2.221 |
wana | -2.217 |
Token | � |
Token ID | 251 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
MMA | +1.130 |
Vi | +1.121 |
Priv | +1.077 |
LX | +1.061 |
MV | +1.024 |
Neg logit contributions | |
gypt | -1.458 |
bee | -1.148 |
Bees | -1.126 |
wana | -1.126 |
gar | -1.119 |
Token | or |
Token ID | 393 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
MMA | +0.595 |
Vi | +0.591 |
Priv | +0.566 |
LX | +0.553 |
MV | +0.535 |
Neg logit contributions | |
gypt | -0.938 |
bee | -0.753 |
Bees | -0.741 |
gar | -0.739 |
wana | -0.737 |
Token | accepted |
Token ID | 6292 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
MMA | +0.790 |
Vi | +0.785 |
Priv | +0.753 |
LX | +0.738 |
MV | +0.719 |
Neg logit contributions | |
gypt | -1.027 |
bee | -0.807 |
Bees | -0.793 |
gar | -0.790 |
wana | -0.789 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
MMA | +3.465 |
Vi | +3.463 |
Priv | +3.270 |
LX | +3.180 |
MV | +3.121 |
Neg logit contributions | |
gypt | -6.462 |
bee | -5.166 |
Bees | -5.153 |
gar | -5.117 |
wana | -5.092 |
Token | The |
Token ID | 383 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
MMA | +2.241 |
Vi | +2.227 |
Priv | +2.131 |
LX | +2.091 |
MV | +2.041 |
Neg logit contributions | |
gypt | -2.946 |
bee | -2.305 |
wana | -2.254 |
gar | -2.251 |
Bees | -2.243 |
Token | opinions |
Token ID | 9317 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
MMA | +1.317 |
Vi | +1.307 |
Priv | +1.251 |
LX | +1.223 |
MV | +1.187 |
Neg logit contributions | |
gypt | -1.992 |
bee | -1.593 |
Bees | -1.563 |
gar | -1.561 |
wana | -1.558 |
Token | expressed |
Token ID | 6241 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
MMA | +2.192 |
Vi | +2.171 |
Priv | +2.067 |
LX | +2.011 |
MV | +1.959 |
Neg logit contributions | |
gypt | -3.909 |
bee | -3.170 |
Bees | -3.123 |
gar | -3.114 |
wana | -3.109 |
Token | in |
Token ID | 287 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
MMA | +5.587 |
Vi | +5.454 |
Priv | +5.198 |
LX | +5.041 |
MV | +4.993 |
Neg logit contributions | |
gypt | -10.356 |
Bees | -8.428 |
bee | -8.368 |
wana | -8.307 |
gars | -8.217 |
Token | these |
Token ID | 777 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
MMA | +4.045 |
Vi | +3.985 |
Priv | +3.780 |
LX | +3.751 |
MV | +3.652 |
Neg logit contributions | |
gypt | -5.453 |
bee | -4.256 |
wana | -4.184 |
gar | -4.157 |
Bees | -4.140 |
Token | rep |
Token ID | 1128 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
MMA | +2.137 |
Vi | +2.112 |
Priv | +2.005 |
LX | +1.946 |
MV | +1.873 |
Neg logit contributions | |
gypt | -4.597 |
bee | -3.775 |
wana | -3.712 |
gar | -3.712 |
Bees | -3.706 |
Token | ost |
Token ID | 455 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
MMA | +2.711 |
Vi | +2.663 |
Priv | +2.578 |
LX | +2.502 |
MV | +2.435 |
Neg logit contributions | |
gypt | -4.514 |
bee | -3.622 |
Bees | -3.561 |
gar | -3.533 |
wana | -3.533 |
Token | s |
Token ID | 82 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
MMA | +0.931 |
Vi | +0.926 |
Priv | +0.888 |
LX | +0.870 |
MV | +0.846 |
Neg logit contributions | |
gypt | -1.241 |
bee | -0.980 |
gar | -0.963 |
Bees | -0.962 |
wana | -0.957 |
Token | input |
Token ID | 5128 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
gypt | +1.057 |
bee | +0.835 |
gar | +0.821 |
Bees | +0.817 |
wana | +0.813 |
Neg logit contributions | |
MMA | -0.819 |
Vi | -0.813 |
Priv | -0.799 |
LX | -0.759 |
MV | -0.743 |
Token | image |
Token ID | 2939 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
MMA | +0.723 |
Vi | +0.717 |
Priv | +0.696 |
LX | +0.673 |
MV | +0.656 |
Neg logit contributions | |
gypt | -1.011 |
bee | -0.804 |
gar | -0.792 |
Bees | -0.787 |
wana | -0.784 |
Token | paths |
Token ID | 13532 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
gypt | +0.484 |
bee | +0.386 |
gar | +0.381 |
Bees | +0.379 |
wana | +0.376 |
Neg logit contributions | |
MMA | -0.347 |
Vi | -0.343 |
Priv | -0.334 |
LX | -0.322 |
MV | -0.314 |
Token | for |
Token ID | 329 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
MMA | +0.171 |
Vi | +0.169 |
Priv | +0.163 |
LX | +0.159 |
MV | +0.155 |
Neg logit contributions | |
gypt | -0.218 |
bee | -0.172 |
gar | -0.169 |
Bees | -0.169 |
wana | -0.168 |
Token | image |
Token ID | 2939 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
gypt | +1.008 |
bee | +0.816 |
gar | +0.803 |
Bees | +0.795 |
wana | +0.792 |
Neg logit contributions | |
MMA | -0.657 |
Vi | -0.650 |
Priv | -0.638 |
LX | -0.605 |
Mort | -0.588 |
Token | Path |
Token ID | 15235 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
gypt | +2.631 |
bee | +2.075 |
gar | +2.037 |
Bees | +2.018 |
wana | +2.010 |
Neg logit contributions | |
MMA | -2.117 |
Vi | -2.086 |
Priv | -2.008 |
LX | -1.964 |
MV | -1.914 |
Token | in |
Token ID | 287 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
gypt | +5.690 |
bee | +4.502 |
gar | +4.398 |
Bees | +4.361 |
wana | +4.246 |
Neg logit contributions | |
MMA | -5.028 |
Vi | -4.895 |
Priv | -4.740 |
LX | -4.648 |
シャ | -4.627 |
Token | paths |
Token ID | 13532 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
gypt | +4.565 |
bee | +3.680 |
gar | +3.680 |
Bees | +3.591 |
gars | +3.587 |
Neg logit contributions | |
Priv | -3.009 |
MMA | -2.987 |
Vi | -2.914 |
シャ | -2.798 |
ネ | -2.741 |
Token | . |
Token ID | 13 |
Feature activation | +9.91e-03 |
Pos logit contributions | |
gypt | +4.381 |
bee | +3.492 |
Bees | +3.376 |
gar | +3.360 |
gars | +3.308 |
Neg logit contributions | |
MMA | -3.806 |
Vi | -3.738 |
Priv | -3.659 |
LX | -3.557 |
シャ | -3.543 |
Token | list |
Token ID | 4868 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
gypt | +0.099 |
bee | +0.080 |
gar | +0.079 |
wana | +0.078 |
Bees | +0.078 |
Neg logit contributions | |
MMA | -0.067 |
Vi | -0.067 |
Priv | -0.064 |
LX | -0.063 |
MV | -0.061 |
Token | _ |
Token ID | 62 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
gypt | +1.468 |
bee | +1.170 |
Bees | +1.145 |
gar | +1.142 |
wana | +1.134 |
Neg logit contributions | |
MMA | -1.115 |
Vi | -1.099 |
Priv | -1.057 |
LX | -1.044 |
MV | -1.011 |
Token | ing |
Token ID | 278 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
gypt | +2.071 |
bee | +1.677 |
gar | +1.659 |
wana | +1.627 |
Bees | +1.615 |
Neg logit contributions | |
MMA | -1.315 |
Vi | -1.315 |
Priv | -1.252 |
LX | -1.243 |
MV | -1.198 |
Token | . |
Token ID | 13 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
gypt | +2.751 |
bee | +2.263 |
gar | +2.235 |
Bees | +2.199 |
wana | +2.184 |
Neg logit contributions | |
MMA | -1.633 |
Vi | -1.627 |
Priv | -1.544 |
LX | -1.525 |
MV | -1.474 |
Token | bit |
Token ID | 2545 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
gypt | +6.257 |
bee | +4.979 |
gar | +4.966 |
wana | +4.789 |
gars | +4.681 |
Neg logit contributions | |
MMA | -6.076 |
Vi | -6.009 |
LX | -5.712 |
Priv | -5.673 |
Mort | -5.566 |
Token | map |
Token ID | 8899 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
gypt | +2.620 |
bee | +1.914 |
gar | +1.842 |
wana | +1.815 |
gars | +1.723 |
Neg logit contributions | |
Vi | -3.610 |
MMA | -3.593 |
Priv | -3.513 |
LX | -3.472 |
Orn | -3.382 |
Token | ($ |
Token ID | 16763 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
gypt | +1.469 |
bee | +1.111 |
Bees | +1.089 |
gar | +1.084 |
wana | +1.079 |
Neg logit contributions | |
MMA | -1.550 |
Vi | -1.534 |
Priv | -1.489 |
LX | -1.456 |
MV | -1.429 |
Token | SR |
Token ID | 12562 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
gypt | +0.494 |
bee | +0.380 |
Bees | +0.372 |
gar | +0.371 |
wana | +0.370 |
Neg logit contributions | |
MMA | -0.456 |
Vi | -0.453 |
Priv | -0.438 |
LX | -0.430 |
MV | -0.419 |
Token | . |
Token ID | 13 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
gypt | +4.941 |
bee | +4.001 |
gar | +3.939 |
Bees | +3.938 |
wana | +3.893 |
Neg logit contributions | |
MMA | -3.070 |
Vi | -3.054 |
Priv | -2.892 |
LX | -2.863 |
MV | -2.784 |
Token | Width |
Token ID | 30916 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
gypt | +2.655 |
bee | +2.055 |
gar | +2.029 |
wana | +1.994 |
Bees | +1.990 |
Neg logit contributions | |
MMA | -2.710 |
Vi | -2.673 |
Priv | -2.546 |
LX | -2.545 |
MV | -2.482 |
Token | , |
Token ID | 11 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
gypt | +2.032 |
bee | +1.643 |
Bees | +1.614 |
gar | +1.611 |
wana | +1.592 |
Neg logit contributions | |
MMA | -1.338 |
Vi | -1.335 |
Priv | -1.277 |
LX | -1.247 |
MV | -1.215 |
Token | $ |
Token ID | 3 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
gypt | +0.491 |
bee | +0.372 |
Bees | +0.363 |
gar | +0.363 |
wana | +0.361 |
Neg logit contributions | |
MMA | -0.506 |
Vi | -0.503 |
Priv | -0.486 |
LX | -0.478 |
MV | -0.467 |
Token | SR |
Token ID | 12562 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
MMA | +0.627 |
Vi | +0.624 |
Priv | +0.610 |
LX | +0.597 |
MV | +0.586 |
Neg logit contributions | |
gypt | -0.485 |
bee | -0.346 |
Bees | -0.341 |
wana | -0.337 |
gar | -0.334 |
Token | outfield |
Token ID | 28307 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
gypt | +1.778 |
bee | +1.413 |
Bees | +1.393 |
gar | +1.384 |
wana | +1.352 |
Neg logit contributions | |
Vi | -1.447 |
MMA | -1.443 |
Priv | -1.411 |
LX | -1.360 |
MV | -1.318 |
Token | prospect |
Token ID | 6034 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
MMA | +3.333 |
Vi | +3.321 |
Priv | +3.142 |
LX | +3.126 |
MV | +3.033 |
Neg logit contributions | |
gypt | -4.453 |
bee | -3.479 |
wana | -3.451 |
Bees | -3.441 |
gars | -3.398 |
Token | in |
Token ID | 287 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
MMA | +1.943 |
Vi | +1.925 |
Priv | +1.818 |
LX | +1.796 |
MV | +1.751 |
Neg logit contributions | |
gypt | -3.059 |
bee | -2.437 |
gar | -2.398 |
Bees | -2.396 |
wana | -2.389 |
Token | Jordan |
Token ID | 8078 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
MMA | +0.290 |
Vi | +0.288 |
Priv | +0.277 |
LX | +0.271 |
MV | +0.264 |
Neg logit contributions | |
gypt | -0.372 |
bee | -0.293 |
Bees | -0.287 |
gar | -0.287 |
wana | -0.285 |
Token | Par |
Token ID | 2547 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
gypt | +1.991 |
Bees | +1.598 |
bee | +1.596 |
gar | +1.570 |
wana | +1.534 |
Neg logit contributions | |
MMA | -1.503 |
Priv | -1.498 |
Vi | -1.462 |
LX | -1.411 |
シャ | -1.387 |
Token | ou |
Token ID | 280 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
MMA | +1.223 |
Vi | +1.215 |
Priv | +1.172 |
LX | +1.151 |
MV | +1.122 |
Neg logit contributions | |
gypt | -1.401 |
bee | -1.092 |
gar | -1.067 |
Bees | -1.065 |
wana | -1.058 |
Token | beck |
Token ID | 27343 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
gypt | +5.109 |
gar | +4.172 |
bee | +4.159 |
wana | +4.027 |
gars | +3.990 |
Neg logit contributions | |
MMA | -3.314 |
Vi | -3.286 |
Priv | -3.248 |
LX | -3.140 |
MV | -3.023 |
Token | ( |
Token ID | 357 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
gypt | +2.389 |
bee | +1.944 |
gar | +1.910 |
wana | +1.898 |
Bees | +1.894 |
Neg logit contributions | |
MMA | -1.412 |
Vi | -1.408 |
Priv | -1.356 |
LX | -1.318 |
MV | -1.268 |
Token | the |
Token ID | 1169 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
gypt | +1.469 |
bee | +1.160 |
gar | +1.143 |
wana | +1.120 |
Bees | +1.116 |
Neg logit contributions | |
MMA | -1.233 |
Vi | -1.231 |
Priv | -1.172 |
LX | -1.165 |
MV | -1.126 |
Token | team |
Token ID | 1074 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
gypt | +0.337 |
bee | +0.262 |
Bees | +0.258 |
gar | +0.257 |
wana | +0.255 |
Neg logit contributions | |
MMA | -0.287 |
Vi | -0.286 |
Priv | -0.276 |
LX | -0.270 |
MV | -0.263 |
Token | � |
Token ID | 447 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
MMA | +0.499 |
Vi | +0.495 |
Priv | +0.477 |
LX | +0.466 |
MV | +0.452 |
Neg logit contributions | |
gypt | -0.710 |
bee | -0.566 |
Bees | -0.555 |
gar | -0.554 |
wana | -0.552 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
gypt | +2.109 |
bee | +1.174 |
gar | +1.077 |
Bees | +1.056 |
wana | +1.013 |
Neg logit contributions | |
Vi | -6.096 |
MMA | -6.073 |
LX | -5.896 |
Priv | -5.867 |
MV | -5.777 |
Token | --+ |
Token ID | 44785 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
gypt | +4.688 |
bee | +3.648 |
gar | +3.569 |
Bees | +3.507 |
gars | +3.480 |
Neg logit contributions | |
Vi | -4.477 |
MMA | -4.452 |
Priv | -4.307 |
LX | -4.231 |
MV | -4.133 |
Token | | |
Token ID | 930 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
MMA | +1.979 |
Vi | +1.959 |
Priv | +1.822 |
LX | +1.798 |
MV | +1.713 |
Neg logit contributions | |
gypt | -4.290 |
bee | -3.499 |
wana | -3.491 |
gars | -3.462 |
gar | -3.460 |
Token | ... |
Token ID | 2644 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
Vi | +4.180 |
MMA | +4.154 |
Priv | +3.940 |
LX | +3.898 |
MV | +3.792 |
Neg logit contributions | |
gypt | -6.115 |
bee | -4.842 |
wana | -4.829 |
gars | -4.822 |
gar | -4.793 |
Token | | |
Token ID | 930 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
MMA | +2.511 |
Vi | +2.467 |
Priv | +2.289 |
LX | +2.236 |
MV | +2.155 |
Neg logit contributions | |
gypt | -5.646 |
bee | -4.589 |
wana | -4.586 |
gars | -4.548 |
Bees | -4.527 |
Token | + |
Token ID | 1343 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
gypt | +1.463 |
bee | +1.130 |
Bees | +1.114 |
gar | +1.112 |
wana | +1.092 |
Neg logit contributions | |
MMA | -1.365 |
Vi | -1.358 |
Priv | -1.323 |
LX | -1.290 |
MV | -1.256 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
gypt | +2.379 |
bee | +1.300 |
gar | +1.187 |
Bees | +1.145 |
wana | +1.092 |
Neg logit contributions | |
Vi | -7.207 |
MMA | -7.190 |
LX | -6.990 |
Priv | -6.921 |
MV | -6.838 |
Token | --+ |
Token ID | 44785 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
gypt | +5.308 |
bee | +4.105 |
gar | +4.038 |
gars | +3.932 |
Bees | +3.931 |
Neg logit contributions | |
Vi | -5.232 |
MMA | -5.205 |
Priv | -5.034 |
LX | -4.947 |
MV | -4.834 |
Token |
|
Token ID | 198 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
gypt | +0.945 |
bee | +0.749 |
Bees | +0.734 |
wana | +0.733 |
gar | +0.732 |
Neg logit contributions | |
MMA | -0.669 |
Vi | -0.665 |
Priv | -0.637 |
LX | -0.624 |
MV | -0.605 |
Token |
|
Token ID | 198 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
MMA | +0.336 |
Vi | +0.333 |
Priv | +0.320 |
LX | +0.312 |
MV | +0.304 |
Neg logit contributions | |
gypt | -0.476 |
bee | -0.377 |
Bees | -0.371 |
wana | -0.370 |
gar | -0.369 |
Token | After |
Token ID | 3260 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
gypt | +0.697 |
bee | +0.533 |
gar | +0.522 |
Bees | +0.518 |
wana | +0.516 |
Neg logit contributions | |
MMA | -0.692 |
Vi | -0.688 |
Priv | -0.660 |
LX | -0.652 |
MV | -0.637 |
Token | . |
Token ID | 13 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
gypt | +3.345 |
bee | +2.724 |
gar | +2.670 |
wana | +2.650 |
Bees | +2.647 |
Neg logit contributions | |
MMA | -2.163 |
Vi | -2.158 |
Priv | -2.099 |
LX | -2.023 |
MV | -1.934 |
Token | Includes |
Token ID | 29581 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
gypt | +4.847 |
Bees | +3.837 |
bee | +3.813 |
gar | +3.804 |
wana | +3.656 |
Neg logit contributions | |
MMA | -4.010 |
Vi | -3.975 |
Priv | -3.868 |
LX | -3.746 |
MV | -3.715 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
gypt | +0.895 |
bee | +0.701 |
Bees | +0.683 |
gar | +0.681 |
wana | +0.676 |
Neg logit contributions | |
MMA | -0.736 |
Vi | -0.736 |
Priv | -0.721 |
LX | -0.708 |
MV | -0.678 |
Token | Catholic |
Token ID | 7835 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
gypt | +1.216 |
bee | +0.957 |
Bees | +0.938 |
gar | +0.935 |
wana | +0.934 |
Neg logit contributions | |
MMA | -0.934 |
Vi | -0.929 |
Priv | -0.892 |
LX | -0.873 |
MV | -0.850 |
Token | Encyclopedia |
Token ID | 36732 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
gypt | +0.759 |
bee | +0.605 |
Bees | +0.597 |
gar | +0.597 |
wana | +0.589 |
Neg logit contributions | |
MMA | -0.501 |
Vi | -0.494 |
Priv | -0.479 |
LX | -0.466 |
MV | -0.453 |
Token | , |
Token ID | 11 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
gypt | +1.861 |
bee | +1.511 |
gar | +1.475 |
Bees | +1.468 |
wana | +1.462 |
Neg logit contributions | |
MMA | -1.247 |
Vi | -1.240 |
Priv | -1.215 |
LX | -1.176 |
MV | -1.136 |
Token | Church |
Token ID | 4564 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
gypt | +4.195 |
gar | +3.159 |
bee | +3.155 |
Bees | +3.068 |
gars | +3.019 |
Neg logit contributions | |
Priv | -4.651 |
MMA | -4.623 |
Vi | -4.545 |
MV | -4.402 |
LX | -4.398 |
Token | Fathers |
Token ID | 30969 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
gypt | +0.604 |
bee | +0.498 |
Bees | +0.497 |
gar | +0.495 |
wana | +0.490 |
Neg logit contributions | |
MMA | -0.273 |
Vi | -0.269 |
Priv | -0.258 |
LX | -0.249 |
MV | -0.243 |
Token | , |
Token ID | 11 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
gypt | +1.922 |
bee | +1.557 |
gar | +1.535 |
Bees | +1.534 |
gars | +1.480 |
Neg logit contributions | |
MMA | -1.380 |
Priv | -1.344 |
Vi | -1.341 |
LX | -1.284 |
ゼ | -1.276 |
Token | Sum |
Token ID | 5060 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
gypt | +0.508 |
bee | +0.401 |
wana | +0.391 |
acca | +0.389 |
Bees | +0.387 |
Neg logit contributions | |
Vi | -0.466 |
MMA | -0.465 |
LX | -0.442 |
Priv | -0.435 |
Mort | -0.425 |
Token | ma |
Token ID | 2611 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
MMA | +1.817 |
Vi | +1.805 |
Priv | +1.745 |
LX | +1.711 |
MV | +1.667 |
Neg logit contributions | |
gypt | -2.020 |
bee | -1.560 |
gar | -1.526 |
Bees | -1.525 |
wana | -1.516 |
Token | stadium |
Token ID | 10308 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
MMA | +0.570 |
Vi | +0.567 |
Priv | +0.546 |
LX | +0.535 |
MV | +0.521 |
Neg logit contributions | |
gypt | -0.700 |
bee | -0.547 |
Bees | -0.537 |
gar | -0.535 |
wana | -0.533 |
Token | extra |
Token ID | 3131 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
gypt | +0.229 |
bee | +0.179 |
Bees | +0.175 |
gar | +0.175 |
wana | +0.173 |
Neg logit contributions | |
MMA | -0.198 |
Vi | -0.197 |
Priv | -0.191 |
LX | -0.186 |
MV | -0.182 |
Token | v |
Token ID | 85 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
MMA | +0.465 |
Vi | +0.459 |
Priv | +0.430 |
LX | +0.416 |
MV | +0.396 |
Neg logit contributions | |
gypt | -1.292 |
bee | -1.082 |
gar | -1.066 |
Bees | -1.065 |
wana | -1.058 |
Token | agan |
Token ID | 7329 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
gypt | +2.005 |
bee | +1.428 |
gar | +1.405 |
acca | +1.397 |
Bees | +1.387 |
Neg logit contributions | |
Vi | -2.883 |
MMA | -2.835 |
Priv | -2.788 |
LX | -2.729 |
MV | -2.699 |
Token | z |
Token ID | 89 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
gypt | +3.667 |
bee | +2.915 |
gar | +2.890 |
Bees | +2.839 |
gars | +2.834 |
Neg logit contributions | |
MMA | -2.842 |
Vi | -2.830 |
Priv | -2.745 |
LX | -2.668 |
MV | -2.617 |
Token | as |
Token ID | 292 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
MMA | +0.652 |
Vi | +0.647 |
Priv | +0.629 |
LX | +0.618 |
MV | +0.604 |
Neg logit contributions | |
gypt | -0.562 |
bee | -0.412 |
Bees | -0.405 |
wana | -0.402 |
gar | -0.402 |
Token | for |
Token ID | 329 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
gypt | +0.524 |
bee | +0.420 |
Bees | +0.413 |
gar | +0.412 |
wana | +0.410 |
Neg logit contributions | |
MMA | -0.342 |
Vi | -0.339 |
Priv | -0.326 |
LX | -0.318 |
MV | -0.308 |
Token | 15 |
Token ID | 1315 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
gypt | +1.142 |
bee | +0.907 |
Bees | +0.894 |
gar | +0.884 |
wana | +0.877 |
Neg logit contributions | |
MMA | -0.883 |
Vi | -0.880 |
Priv | -0.858 |
LX | -0.833 |
MV | -0.808 |
Token | years |
Token ID | 812 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
MMA | +0.329 |
Vi | +0.328 |
Priv | +0.316 |
LX | +0.309 |
MV | +0.301 |
Neg logit contributions | |
gypt | -0.400 |
bee | -0.312 |
Bees | -0.307 |
gar | -0.306 |
wana | -0.305 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
MMA | +0.694 |
Vi | +0.688 |
Priv | +0.654 |
LX | +0.638 |
MV | +0.617 |
Neg logit contributions | |
gypt | -1.258 |
bee | -1.019 |
Bees | -1.006 |
gar | -1.003 |
wana | -1.000 |
Token | The |
Token ID | 383 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
MMA | +0.914 |
Vi | +0.908 |
Priv | +0.875 |
LX | +0.857 |
MV | +0.834 |
Neg logit contributions | |
gypt | -1.142 |
bee | -0.897 |
Bees | -0.882 |
gar | -0.878 |
wana | -0.874 |
Token | . |
Token ID | 13 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
gypt | +0.914 |
bee | +0.749 |
gar | +0.736 |
wana | +0.725 |
Bees | +0.723 |
Neg logit contributions | |
Vi | -0.520 |
MMA | -0.519 |
Priv | -0.493 |
LX | -0.486 |
MV | -0.467 |
Token | org |
Token ID | 2398 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
gypt | +0.084 |
bee | +0.069 |
gar | +0.068 |
wana | +0.067 |
Bees | +0.067 |
Neg logit contributions | |
MMA | -0.042 |
Vi | -0.042 |
Priv | -0.040 |
LX | -0.039 |
MV | -0.037 |
Token | / |
Token ID | 14 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
MMA | +1.368 |
Vi | +1.342 |
Priv | +1.276 |
LX | +1.228 |
MV | +1.185 |
Neg logit contributions | |
gypt | -3.062 |
bee | -2.505 |
Bees | -2.491 |
wana | -2.484 |
gar | -2.466 |
Token | d |
Token ID | 67 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
MMA | +0.137 |
Vi | +0.136 |
Priv | +0.131 |
LX | +0.128 |
MV | +0.125 |
Neg logit contributions | |
gypt | -0.185 |
bee | -0.147 |
gar | -0.144 |
Bees | -0.144 |
wana | -0.143 |
Token | ee |
Token ID | 1453 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
gypt | +2.405 |
bee | +1.533 |
gar | +1.419 |
wana | +1.361 |
Bees | +1.327 |
Neg logit contributions | |
MMA | -5.562 |
Vi | -5.539 |
LX | -5.403 |
Priv | -5.362 |
MV | -5.264 |
Token | pl |
Token ID | 489 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
MMA | +2.004 |
Vi | +1.970 |
Priv | +1.873 |
LX | +1.785 |
MV | +1.718 |
Neg logit contributions | |
gypt | -5.329 |
Bees | -4.446 |
bee | -4.432 |
wana | -4.390 |
gar | -4.363 |
Token | inks |
Token ID | 2973 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
gypt | +0.148 |
bee | +0.101 |
gar | +0.098 |
wana | +0.097 |
Bees | +0.096 |
Neg logit contributions | |
MMA | -0.246 |
Vi | -0.246 |
Priv | -0.239 |
LX | -0.235 |
MV | -0.232 |
Token | / |
Token ID | 14 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
MMA | +1.643 |
Vi | +1.606 |
Priv | +1.534 |
LX | +1.468 |
MV | +1.415 |
Neg logit contributions | |
gypt | -3.782 |
Bees | -3.096 |
bee | -3.089 |
wana | -3.072 |
gars | -3.038 |
Token | 2016 |
Token ID | 5304 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
MMA | +2.740 |
Vi | +2.713 |
Priv | +2.636 |
LX | +2.528 |
MV | +2.470 |
Neg logit contributions | |
gypt | -4.012 |
Bees | -3.166 |
bee | -3.146 |
wana | -3.108 |
gar | -3.081 |
Token | / |
Token ID | 14 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
MMA | +2.225 |
Vi | +2.137 |
Priv | +2.044 |
LX | +1.930 |
MV | +1.871 |
Neg logit contributions | |
gypt | -5.562 |
Bees | -4.559 |
wana | -4.552 |
bee | -4.517 |
gars | -4.508 |
Token | 05 |
Token ID | 2713 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
MMA | +2.575 |
Vi | +2.553 |
Priv | +2.486 |
LX | +2.415 |
MV | +2.356 |
Neg logit contributions | |
gypt | -2.771 |
bee | -2.107 |
Bees | -2.103 |
wana | -2.074 |
gar | -2.049 |
Token | driving |
Token ID | 5059 |
Feature activation | +1.82e-04 |
Pos logit contributions | |
gypt | +0.485 |
bee | +0.382 |
Bees | +0.375 |
gar | +0.375 |
wana | +0.371 |
Neg logit contributions | |
MMA | -0.388 |
Vi | -0.387 |
Priv | -0.379 |
LX | -0.368 |
MV | -0.356 |
Token | licence |
Token ID | 17098 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
gypt | +0.002 |
bee | +0.001 |
Bees | +0.001 |
gar | +0.001 |
wana | +0.001 |
Neg logit contributions | |
Vi | -0.001 |
MMA | -0.001 |
Priv | -0.001 |
LX | -0.001 |
MV | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
gypt | +1.569 |
bee | +1.271 |
gar | +1.245 |
wana | +1.237 |
Bees | +1.231 |
Neg logit contributions | |
MMA | -0.995 |
Vi | -0.992 |
Priv | -0.970 |
LX | -0.930 |
MV | -0.899 |
Token | However |
Token ID | 2102 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
MMA | +1.409 |
Vi | +1.399 |
Priv | +1.343 |
LX | +1.316 |
MV | +1.281 |
Neg logit contributions | |
gypt | -1.848 |
bee | -1.453 |
Bees | -1.423 |
gar | -1.423 |
wana | -1.420 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
gypt | +2.307 |
bee | +1.866 |
gar | +1.824 |
Bees | +1.816 |
wana | +1.795 |
Neg logit contributions | |
Vi | -1.580 |
MMA | -1.577 |
Priv | -1.548 |
LX | -1.506 |
MV | -1.435 |
Token | they |
Token ID | 484 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
MMA | +0.123 |
Vi | +0.122 |
Priv | +0.119 |
LX | +0.115 |
MV | +0.112 |
Neg logit contributions | |
gypt | -0.166 |
bee | -0.132 |
Bees | -0.129 |
gar | -0.129 |
wana | -0.128 |
Token | can |
Token ID | 460 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
gypt | +0.540 |
bee | +0.432 |
gar | +0.423 |
Bees | +0.423 |
wana | +0.421 |
Neg logit contributions | |
MMA | -0.364 |
Vi | -0.362 |
Priv | -0.348 |
LX | -0.340 |
MV | -0.330 |
Token | still |
Token ID | 991 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
MMA | +0.386 |
Vi | +0.384 |
Priv | +0.369 |
LX | +0.361 |
MV | +0.350 |
Neg logit contributions | |
gypt | -0.554 |
bee | -0.442 |
Bees | -0.433 |
gar | -0.433 |
wana | -0.431 |
Token | race |
Token ID | 3234 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
gypt | +0.128 |
bee | +0.101 |
gar | +0.099 |
Bees | +0.099 |
wana | +0.098 |
Neg logit contributions | |
MMA | -0.099 |
Vi | -0.099 |
Priv | -0.096 |
LX | -0.093 |
MV | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
MMA | +0.460 |
Vi | +0.457 |
Priv | +0.442 |
LX | +0.430 |
MV | +0.417 |
Neg logit contributions | |
gypt | -0.661 |
bee | -0.528 |
Bees | -0.519 |
gar | -0.519 |
wana | -0.515 |
Token | Like |
Token ID | 4525 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
MMA | +1.062 |
Vi | +1.055 |
Priv | +1.016 |
LX | +0.995 |
MV | +0.967 |
Neg logit contributions | |
gypt | -1.360 |
bee | -1.069 |
Bees | -1.050 |
gar | -1.047 |
wana | -1.043 |
Token | type |
Token ID | 2099 |
Feature activation | -5.88e-03 |
Pos logit contributions | |
MMA | +0.139 |
Vi | +0.138 |
Priv | +0.134 |
LX | +0.131 |
MV | +0.127 |
Neg logit contributions | |
gypt | -0.162 |
bee | -0.125 |
Bees | -0.123 |
gar | -0.123 |
wana | -0.122 |
Token | ( |
Token ID | 357 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
MMA | +0.039 |
Vi | +0.038 |
Priv | +0.037 |
LX | +0.036 |
MV | +0.035 |
Neg logit contributions | |
gypt | -0.060 |
bee | -0.049 |
Bees | -0.048 |
gar | -0.048 |
wana | -0.047 |
Token | of |
Token ID | 1659 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
gypt | +0.710 |
bee | +0.560 |
gar | +0.550 |
wana | +0.545 |
Bees | +0.544 |
Neg logit contributions | |
MMA | -0.562 |
Vi | -0.557 |
Priv | -0.535 |
LX | -0.527 |
MV | -0.512 |
Token | the |
Token ID | 262 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
gypt | +1.178 |
bee | +0.923 |
Bees | +0.906 |
gar | +0.906 |
wana | +0.902 |
Neg logit contributions | |
MMA | -0.943 |
Vi | -0.933 |
Priv | -0.903 |
LX | -0.883 |
MV | -0.858 |
Token | party |
Token ID | 2151 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
MMA | +0.490 |
Vi | +0.487 |
Priv | +0.470 |
LX | +0.460 |
MV | +0.448 |
Neg logit contributions | |
gypt | -0.588 |
bee | -0.458 |
Bees | -0.449 |
gar | -0.448 |
wana | -0.446 |
Token | of |
Token ID | 286 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
gypt | +2.672 |
bee | +2.152 |
gar | +2.105 |
wana | +2.101 |
Bees | +2.085 |
Neg logit contributions | |
MMA | -1.925 |
Vi | -1.899 |
Priv | -1.849 |
LX | -1.784 |
MV | -1.735 |
Token | a |
Token ID | 257 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
gypt | +1.423 |
bee | +1.117 |
Bees | +1.096 |
gar | +1.096 |
wana | +1.091 |
Neg logit contributions | |
MMA | -1.140 |
Vi | -1.130 |
Priv | -1.093 |
LX | -1.068 |
MV | -1.038 |
Token | new |
Token ID | 649 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
gypt | +2.885 |
bee | +2.241 |
gar | +2.201 |
wana | +2.181 |
Bees | +2.174 |
Neg logit contributions | |
MMA | -2.594 |
Vi | -2.536 |
Priv | -2.491 |
LX | -2.430 |
MV | -2.370 |
Token | type |
Token ID | 2099 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
gypt | +3.113 |
bee | +2.391 |
gar | +2.319 |
wana | +2.303 |
Bees | +2.302 |
Neg logit contributions | |
MMA | -3.189 |
Vi | -3.135 |
Priv | -3.097 |
LX | -3.004 |
MV | -2.927 |
Token | ), |
Token ID | 828 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
gypt | +1.531 |
bee | +1.232 |
gar | +1.208 |
Bees | +1.204 |
wana | +1.202 |
Neg logit contributions | |
MMA | -1.024 |
Vi | -1.016 |
Priv | -0.979 |
LX | -0.949 |
MV | -0.920 |
Token | new |
Token ID | 3605 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
gypt | +2.196 |
bee | +1.733 |
gar | +1.701 |
wana | +1.692 |
Bees | +1.681 |
Neg logit contributions | |
MMA | -1.726 |
Vi | -1.707 |
Priv | -1.644 |
LX | -1.613 |
MV | -1.570 |
Token | met |
Token ID | 1138 |
Feature activation | +8.45e-03 |
Pos logit contributions | |
gypt | +3.260 |
bee | +2.620 |
gar | +2.587 |
Bees | +2.554 |
wana | +2.544 |
Neg logit contributions | |
MMA | -2.424 |
Vi | -2.386 |
Priv | -2.360 |
LX | -2.282 |
MV | -2.195 |
Token | the |
Token ID | 262 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
gypt | +0.078 |
bee | +0.061 |
Bees | +0.059 |
gar | +0.059 |
wana | +0.059 |
Neg logit contributions | |
MMA | -0.065 |
Vi | -0.064 |
Priv | -0.062 |
LX | -0.061 |
MV | -0.059 |
Token | flight |
Token ID | 5474 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
gypt | +2.031 |
bee | +1.605 |
Bees | +1.582 |
gar | +1.576 |
wana | +1.560 |
Neg logit contributions | |
MMA | -1.565 |
Vi | -1.554 |
Priv | -1.514 |
LX | -1.470 |
MV | -1.420 |
Token | after |
Token ID | 706 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
MMA | +2.605 |
Vi | +2.588 |
Priv | +2.444 |
LX | +2.419 |
MV | +2.381 |
Neg logit contributions | |
gypt | -3.695 |
bee | -2.936 |
Bees | -2.899 |
wana | -2.881 |
gars | -2.877 |
Token | the |
Token ID | 262 |
Feature activation | -5.49e-03 |
Pos logit contributions | |
MMA | +0.247 |
Vi | +0.246 |
Priv | +0.236 |
LX | +0.232 |
MV | +0.225 |
Neg logit contributions | |
gypt | -0.323 |
bee | -0.255 |
Bees | -0.250 |
gar | -0.249 |
wana | -0.248 |
Token | emergency |
Token ID | 6334 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
MMA | +0.043 |
Vi | +0.042 |
Priv | +0.041 |
LX | +0.040 |
MV | +0.039 |
Neg logit contributions | |
gypt | -0.050 |
bee | -0.039 |
Bees | -0.038 |
gar | -0.038 |
wana | -0.038 |
Token | landing |
Token ID | 9581 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
MMA | +1.369 |
Vi | +1.362 |
Priv | +1.302 |
LX | +1.282 |
MV | +1.247 |
Neg logit contributions | |
gypt | -1.842 |
bee | -1.448 |
wana | -1.424 |
gar | -1.423 |
Bees | -1.422 |
Token | , |
Token ID | 11 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
MMA | +2.543 |
Vi | +2.531 |
Priv | +2.370 |
LX | +2.328 |
MV | +2.279 |
Neg logit contributions | |
gypt | -4.444 |
bee | -3.571 |
Bees | -3.545 |
wana | -3.533 |
gar | -3.518 |
Token | 50 |
Token ID | 2026 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
gypt | +0.691 |
bee | +0.547 |
Bees | +0.537 |
gar | +0.536 |
wana | +0.533 |
Neg logit contributions | |
MMA | -0.526 |
Vi | -0.521 |
Priv | -0.505 |
LX | -0.493 |
MV | -0.478 |
Token | minutes |
Token ID | 2431 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
MMA | +0.261 |
Vi | +0.259 |
Priv | +0.248 |
LX | +0.242 |
MV | +0.235 |
Neg logit contributions | |
gypt | -0.394 |
bee | -0.315 |
Bees | -0.309 |
gar | -0.309 |
wana | -0.308 |
Token | after |
Token ID | 706 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
gypt | +0.487 |
bee | +0.388 |
Bees | +0.381 |
gar | +0.380 |
wana | +0.379 |
Neg logit contributions | |
MMA | -0.340 |
Vi | -0.337 |
Priv | -0.325 |
LX | -0.317 |
MV | -0.308 |
Token | we |
Token ID | 356 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
MMA | +1.363 |
Vi | +1.354 |
Priv | +1.303 |
LX | +1.275 |
MV | +1.239 |
Neg logit contributions | |
gypt | -1.823 |
bee | -1.440 |
Bees | -1.413 |
gar | -1.411 |
wana | -1.405 |
Token | � |
Token ID | 447 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
MMA | +0.834 |
Vi | +0.827 |
Priv | +0.793 |
LX | +0.776 |
MV | +0.754 |
Neg logit contributions | |
gypt | -1.191 |
bee | -0.947 |
Bees | -0.932 |
gar | -0.928 |
wana | -0.926 |
Token | � |
Token ID | 247 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
gypt | +0.408 |
bee | +0.320 |
gar | +0.315 |
Bees | +0.313 |
wana | +0.309 |
Neg logit contributions | |
MMA | -0.327 |
Vi | -0.325 |
Priv | -0.315 |
LX | -0.307 |
MV | -0.299 |
Token | re |
Token ID | 260 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
MMA | +0.437 |
Vi | +0.433 |
Priv | +0.421 |
LX | +0.409 |
MV | +0.399 |
Neg logit contributions | |
gypt | -0.592 |
bee | -0.469 |
gar | -0.462 |
Bees | -0.454 |
wana | -0.454 |
Token | not |
Token ID | 407 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
gypt | +1.511 |
bee | +1.190 |
gar | +1.177 |
wana | +1.154 |
Bees | +1.149 |
Neg logit contributions | |
MMA | -1.226 |
Vi | -1.225 |
Priv | -1.185 |
LX | -1.160 |
MV | -1.125 |
Token | seeing |
Token ID | 4379 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
MMA | +0.035 |
Vi | +0.034 |
Priv | +0.033 |
LX | +0.033 |
MV | +0.032 |
Neg logit contributions | |
gypt | -0.042 |
bee | -0.033 |
Bees | -0.032 |
gar | -0.032 |
wana | -0.032 |
Token | what |
Token ID | 644 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
MMA | +2.972 |
Vi | +2.954 |
Priv | +2.818 |
LX | +2.767 |
MV | +2.694 |
Neg logit contributions | |
gypt | -3.917 |
bee | -3.080 |
Bees | -3.029 |
wana | -3.011 |
gar | -3.001 |
Token | the |
Token ID | 262 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
MMA | +2.568 |
Vi | +2.557 |
Priv | +2.436 |
LX | +2.398 |
MV | +2.334 |
Neg logit contributions | |
gypt | -3.433 |
bee | -2.707 |
Bees | -2.656 |
wana | -2.652 |
gar | -2.652 |
Token | membership |
Token ID | 9931 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
MMA | +1.815 |
Vi | +1.803 |
Priv | +1.734 |
LX | +1.697 |
MV | +1.650 |
Neg logit contributions | |
gypt | -2.418 |
bee | -1.908 |
Bees | -1.873 |
gar | -1.869 |
wana | -1.863 |
Token | anticipated |
Token ID | 14486 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
gypt | +0.438 |
bee | +0.345 |
gar | +0.339 |
wana | +0.338 |
Bees | +0.337 |
Neg logit contributions | |
MMA | -0.337 |
Vi | -0.335 |
Priv | -0.324 |
LX | -0.316 |
MV | -0.307 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
MMA | +1.810 |
Vi | +1.796 |
Priv | +1.718 |
LX | +1.674 |
MV | +1.625 |
Neg logit contributions | |
gypt | -2.921 |
bee | -2.347 |
Bees | -2.310 |
gar | -2.303 |
wana | -2.293 |
Token | This |
Token ID | 1212 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
gypt | +0.614 |
bee | +0.478 |
gar | +0.467 |
Bees | +0.463 |
wana | +0.460 |
Neg logit contributions | |
MMA | -0.569 |
Vi | -0.566 |
Priv | -0.540 |
LX | -0.538 |
MV | -0.522 |
Token | classic |
Token ID | 6833 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
gypt | +1.627 |
bee | +1.280 |
Bees | +1.258 |
gar | +1.250 |
wana | +1.234 |
Neg logit contributions | |
MMA | -1.316 |
Vi | -1.298 |
Priv | -1.275 |
LX | -1.237 |
MV | -1.185 |
Token | game |
Token ID | 983 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
MMA | +1.020 |
Vi | +1.013 |
Priv | +0.975 |
LX | +0.954 |
MV | +0.928 |
Neg logit contributions | |
gypt | -1.329 |
bee | -1.046 |
Bees | -1.027 |
gar | -1.025 |
wana | -1.021 |
Token | is |
Token ID | 318 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
gypt | +0.952 |
bee | +0.764 |
gar | +0.749 |
wana | +0.748 |
Bees | +0.748 |
Neg logit contributions | |
MMA | -0.624 |
Vi | -0.620 |
Priv | -0.601 |
LX | -0.580 |
MV | -0.559 |
Token | part |
Token ID | 636 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
MMA | +0.207 |
Vi | +0.206 |
Priv | +0.199 |
LX | +0.194 |
MV | +0.189 |
Neg logit contributions | |
gypt | -0.258 |
bee | -0.202 |
Bees | -0.199 |
gar | -0.198 |
wana | -0.198 |
Token | of |
Token ID | 286 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
gypt | +0.616 |
bee | +0.494 |
Bees | +0.485 |
gar | +0.483 |
wana | +0.481 |
Neg logit contributions | |
MMA | -0.413 |
Vi | -0.410 |
Priv | -0.397 |
LX | -0.385 |
MV | -0.371 |
Token | the |
Token ID | 262 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
MMA | +1.871 |
Vi | +1.865 |
Priv | +1.771 |
LX | +1.746 |
MV | +1.702 |
Neg logit contributions | |
gypt | -2.625 |
bee | -2.077 |
gar | -2.041 |
Bees | -2.035 |
wana | -2.031 |
Token | Virtual |
Token ID | 15595 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
MMA | +1.362 |
Vi | +1.355 |
Priv | +1.292 |
LX | +1.270 |
MV | +1.236 |
Neg logit contributions | |
gypt | -1.962 |
bee | -1.558 |
gar | -1.529 |
Bees | -1.529 |
wana | -1.523 |
Token | Console |
Token ID | 24371 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
MMA | +0.970 |
Vi | +0.960 |
Priv | +0.915 |
LX | +0.893 |
MV | +0.859 |
Neg logit contributions | |
gypt | -1.861 |
bee | -1.525 |
Bees | -1.500 |
gar | -1.496 |
wana | -1.491 |
Token | service |
Token ID | 2139 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
gypt | +1.156 |
bee | +0.881 |
gar | +0.871 |
Bees | +0.863 |
wana | +0.850 |
Neg logit contributions | |
MMA | -1.168 |
Vi | -1.145 |
LX | -1.110 |
Priv | -1.105 |
Mort | -1.064 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
MMA | +1.388 |
Vi | +1.381 |
Priv | +1.319 |
LX | +1.287 |
MV | +1.240 |
Neg logit contributions | |
gypt | -2.308 |
bee | -1.864 |
Bees | -1.841 |
gar | -1.832 |
wana | -1.831 |
Token | NH |
Token ID | 33863 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
MMA | +1.964 |
Vi | +1.958 |
Priv | +1.888 |
LX | +1.849 |
MV | +1.805 |
Neg logit contributions | |
gypt | -2.297 |
bee | -1.781 |
Bees | -1.761 |
wana | -1.735 |
gar | -1.727 |
Token | 7 |
Token ID | 22 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
MMA | +2.137 |
Vi | +2.124 |
Priv | +2.023 |
LX | +2.000 |
MV | +1.948 |
Neg logit contributions | |
gypt | -2.885 |
bee | -2.281 |
Bees | -2.232 |
wana | -2.226 |
gar | -2.217 |
Token | ) |
Token ID | 8 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
MMA | +3.529 |
Vi | +3.524 |
Priv | +3.332 |
LX | +3.306 |
MV | +3.224 |
Neg logit contributions | |
gypt | -4.942 |
bee | -3.894 |
Bees | -3.837 |
wana | -3.829 |
gar | -3.806 |
Token | is |
Token ID | 318 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
gypt | +2.136 |
bee | +1.689 |
gar | +1.668 |
Bees | +1.662 |
wana | +1.656 |
Neg logit contributions | |
MMA | -1.579 |
Vi | -1.549 |
Priv | -1.512 |
LX | -1.471 |
MV | -1.420 |
Token | the |
Token ID | 262 |
Feature activation | +6.30e-03 |
Pos logit contributions | |
gypt | +0.835 |
bee | +0.656 |
Bees | +0.645 |
gar | +0.644 |
wana | +0.640 |
Neg logit contributions | |
MMA | -0.630 |
Vi | -0.625 |
Priv | -0.608 |
LX | -0.591 |
MV | -0.572 |
Token | temple |
Token ID | 12505 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
gypt | +0.060 |
bee | +0.048 |
Bees | +0.047 |
gar | +0.047 |
wana | +0.047 |
Neg logit contributions | |
MMA | -0.045 |
Vi | -0.045 |
Priv | -0.044 |
LX | -0.043 |
MV | -0.041 |
Token | dedicated |
Token ID | 7256 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
MMA | +2.164 |
Vi | +2.157 |
Priv | +2.035 |
LX | +2.006 |
MV | +1.964 |
Neg logit contributions | |
gypt | -3.146 |
bee | -2.510 |
Bees | -2.473 |
wana | -2.461 |
gar | -2.456 |
Token | to |
Token ID | 284 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
MMA | +0.629 |
Vi | +0.625 |
Priv | +0.593 |
LX | +0.581 |
MV | +0.567 |
Neg logit contributions | |
gypt | -0.953 |
bee | -0.761 |
Bees | -0.751 |
wana | -0.749 |
gar | -0.748 |
Token | Lord |
Token ID | 4453 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
MMA | +1.485 |
Vi | +1.477 |
Priv | +1.392 |
LX | +1.378 |
MV | +1.350 |
Neg logit contributions | |
gypt | -1.923 |
bee | -1.514 |
Bees | -1.485 |
gar | -1.480 |
wana | -1.479 |
Token | Vish |
Token ID | 36900 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
MMA | +0.421 |
Vi | +0.418 |
Priv | +0.403 |
LX | +0.395 |
MV | +0.385 |
Neg logit contributions | |
gypt | -0.498 |
bee | -0.388 |
Bees | -0.380 |
gar | -0.379 |
wana | -0.378 |
Token | nu |
Token ID | 28803 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
MMA | +0.802 |
Vi | +0.799 |
Priv | +0.726 |
LX | +0.695 |
MV | +0.665 |
Neg logit contributions | |
gypt | -2.798 |
bee | -2.354 |
Bees | -2.338 |
gar | -2.318 |
wana | -2.308 |
Token | fight |
Token ID | 1907 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
gypt | +1.099 |
bee | +0.867 |
gar | +0.854 |
Bees | +0.849 |
wana | +0.842 |
Neg logit contributions | |
MMA | -0.864 |
Vi | -0.856 |
Priv | -0.832 |
LX | -0.814 |
MV | -0.789 |
Token | an |
Token ID | 281 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
gypt | +1.125 |
bee | +0.883 |
Bees | +0.866 |
gar | +0.865 |
wana | +0.851 |
Neg logit contributions | |
MMA | -0.991 |
Vi | -0.984 |
Priv | -0.962 |
LX | -0.936 |
MV | -0.908 |
Token | appeal |
Token ID | 5198 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
gypt | +0.208 |
bee | +0.165 |
Bees | +0.161 |
gar | +0.160 |
wana | +0.158 |
Neg logit contributions | |
Vi | -0.175 |
MMA | -0.174 |
Priv | -0.171 |
LX | -0.165 |
シャ | -0.159 |
Token | or |
Token ID | 393 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
gypt | +3.057 |
bee | +2.465 |
gar | +2.425 |
Bees | +2.390 |
wana | +2.371 |
Neg logit contributions | |
MMA | -1.940 |
Vi | -1.933 |
Priv | -1.884 |
LX | -1.824 |
MV | -1.754 |
Token | rec |
Token ID | 664 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
gypt | +2.809 |
bee | +2.245 |
gar | +2.200 |
Bees | +2.197 |
wana | +2.169 |
Neg logit contributions | |
MMA | -2.125 |
Vi | -2.119 |
Priv | -2.064 |
LX | -2.008 |
MV | -1.933 |
Token | irc |
Token ID | 1980 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
MMA | +1.227 |
Vi | +1.217 |
Priv | +1.153 |
LX | +1.123 |
MV | +1.084 |
Neg logit contributions | |
gypt | -2.412 |
bee | -1.972 |
Bees | -1.948 |
gar | -1.938 |
wana | -1.934 |
Token | ulating |
Token ID | 8306 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
MMA | +2.694 |
Vi | +2.679 |
Priv | +2.563 |
LX | +2.518 |
MV | +2.447 |
Neg logit contributions | |
gypt | -3.550 |
bee | -2.784 |
Bees | -2.764 |
wana | -2.744 |
gar | -2.728 |
Token | for |
Token ID | 329 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
gypt | +1.114 |
bee | +0.885 |
Bees | +0.868 |
gar | +0.866 |
wana | +0.857 |
Neg logit contributions | |
MMA | -0.861 |
Vi | -0.852 |
Priv | -0.830 |
LX | -0.808 |
MV | -0.783 |
Token | the |
Token ID | 262 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
gypt | +1.248 |
bee | +0.986 |
Bees | +0.965 |
gar | +0.962 |
wana | +0.957 |
Neg logit contributions | |
MMA | -1.018 |
Vi | -1.009 |
Priv | -0.977 |
LX | -0.958 |
MV | -0.929 |
Token | spring |
Token ID | 6076 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
gypt | +2.088 |
bee | +1.667 |
Bees | +1.648 |
gar | +1.620 |
wana | +1.606 |
Neg logit contributions | |
MMA | -1.679 |
Vi | -1.658 |
Priv | -1.628 |
LX | -1.576 |
MV | -1.523 |
Token | election |
Token ID | 3071 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
MMA | +0.223 |
Vi | +0.220 |
Priv | +0.215 |
LX | +0.209 |
MV | +0.203 |
Neg logit contributions | |
gypt | -0.291 |
bee | -0.233 |
gar | -0.227 |
Bees | -0.227 |
wana | -0.223 |
Token | _ |
Token ID | 62 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
gypt | +2.087 |
bee | +1.622 |
gar | +1.585 |
Bees | +1.533 |
wana | +1.532 |
Neg logit contributions | |
Vi | -2.198 |
MMA | -2.178 |
Priv | -2.088 |
LX | -2.081 |
MV | -2.021 |
Token | OR |
Token ID | 1581 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
MMA | +1.846 |
Vi | +1.823 |
Priv | +1.768 |
LX | +1.718 |
MV | +1.670 |
Neg logit contributions | |
gypt | -2.608 |
bee | -2.050 |
Bees | -2.032 |
wana | -2.022 |
gar | -2.000 |
Token | ) |
Token ID | 8 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
gypt | +0.514 |
bee | +0.413 |
gar | +0.404 |
Bees | +0.404 |
wana | +0.401 |
Neg logit contributions | |
MMA | -0.349 |
Vi | -0.348 |
Priv | -0.334 |
LX | -0.327 |
MV | -0.316 |
Token | May |
Token ID | 1737 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
MMA | +0.176 |
Vi | +0.175 |
Priv | +0.168 |
LX | +0.165 |
MV | +0.161 |
Neg logit contributions | |
gypt | -0.214 |
bee | -0.167 |
Bees | -0.163 |
gar | -0.163 |
wana | -0.163 |
Token | 29 |
Token ID | 2808 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
gypt | +2.576 |
bee | +1.989 |
Bees | +1.945 |
gar | +1.903 |
wana | +1.867 |
Neg logit contributions | |
Vi | -2.776 |
MMA | -2.774 |
Priv | -2.749 |
LX | -2.669 |
Orn | -2.584 |
Token | , |
Token ID | 11 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
MMA | +0.129 |
Vi | +0.128 |
Priv | +0.122 |
LX | +0.119 |
MV | +0.115 |
Neg logit contributions | |
gypt | -0.221 |
bee | -0.180 |
Bees | -0.177 |
gar | -0.176 |
wana | -0.176 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
MMA | +2.786 |
Vi | +2.703 |
Priv | +2.501 |
MV | +2.478 |
LX | +2.464 |
Neg logit contributions | |
gypt | -5.871 |
bee | -4.711 |
Bees | -4.686 |
gars | -4.674 |
wana | -4.666 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
MMA | +0.673 |
Vi | +0.668 |
Priv | +0.642 |
LX | +0.628 |
MV | +0.610 |
Neg logit contributions | |
gypt | -0.936 |
bee | -0.742 |
Bees | -0.728 |
gar | -0.727 |
wana | -0.725 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
MMA | +0.940 |
Vi | +0.930 |
Priv | +0.893 |
LX | +0.869 |
MV | +0.847 |
Neg logit contributions | |
gypt | -1.367 |
bee | -1.079 |
Bees | -1.065 |
wana | -1.062 |
gar | -1.057 |
Token | A |
Token ID | 32 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
gypt | +1.068 |
bee | +0.825 |
gar | +0.810 |
Bees | +0.793 |
wana | +0.791 |
Neg logit contributions | |
Vi | -1.030 |
MMA | -1.029 |
LX | -0.981 |
Priv | -0.968 |
MV | -0.954 |
Token | men |
Token ID | 3653 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
MMA | +0.964 |
Vi | +0.957 |
Priv | +0.922 |
LX | +0.906 |
MV | +0.881 |
Neg logit contributions | |
gypt | -1.165 |
bee | -0.910 |
gar | -0.892 |
Bees | -0.890 |
wana | -0.886 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
MMA | +0.872 |
Vi | +0.863 |
Priv | +0.821 |
LX | +0.795 |
MV | +0.769 |
Neg logit contributions | |
gypt | -1.749 |
bee | -1.429 |
Bees | -1.411 |
wana | -1.407 |
gar | -1.403 |
Token | The |
Token ID | 383 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
MMA | +1.610 |
Vi | +1.600 |
Priv | +1.538 |
LX | +1.508 |
MV | +1.469 |
Neg logit contributions | |
gypt | -2.001 |
bee | -1.565 |
Bees | -1.534 |
gar | -1.531 |
wana | -1.529 |
Token | player |
Token ID | 2137 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
MMA | +2.717 |
Vi | +2.694 |
Priv | +2.552 |
LX | +2.504 |
MV | +2.465 |
Neg logit contributions | |
gypt | -3.615 |
bee | -2.822 |
wana | -2.798 |
Bees | -2.795 |
gars | -2.760 |
Token | must |
Token ID | 1276 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
MMA | +4.198 |
Vi | +4.161 |
LX | +3.769 |
Priv | +3.752 |
Mort | +3.704 |
Neg logit contributions | |
gypt | -7.684 |
wana | -6.187 |
bee | -6.082 |
Bees | -6.065 |
gars | -6.028 |
Token | know |
Token ID | 760 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
MMA | +3.402 |
Vi | +3.387 |
Priv | +3.192 |
LX | +3.102 |
MV | +3.040 |
Neg logit contributions | |
gypt | -5.014 |
bee | -3.962 |
gar | -3.879 |
Bees | -3.877 |
wana | -3.869 |
Token | choose |
Token ID | 3853 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
Vi | +5.858 |
MMA | +5.834 |
LX | +5.363 |
Priv | +5.350 |
Mort | +5.281 |
Neg logit contributions | |
gypt | -9.033 |
bee | -7.234 |
Bees | -7.118 |
wana | -7.110 |
gars | -7.019 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
MMA | +6.396 |
Vi | +6.392 |
LX | +5.924 |
Priv | +5.887 |
Mort | +5.876 |
Neg logit contributions | |
gypt | -9.134 |
bee | -7.248 |
wana | -7.244 |
gars | -7.088 |
gar | -7.069 |
Token | Permanent |
Token ID | 36814 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
Vi | +2.769 |
MMA | +2.765 |
Priv | +2.626 |
LX | +2.569 |
Mort | +2.533 |
Neg logit contributions | |
gypt | -3.775 |
bee | -2.968 |
wana | -2.939 |
gar | -2.896 |
gars | -2.888 |
Token | Voices |
Token ID | 40440 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
MMA | +0.031 |
Vi | +0.030 |
Priv | +0.029 |
LX | +0.029 |
MV | +0.028 |
Neg logit contributions | |
gypt | -0.039 |
bee | -0.031 |
Bees | -0.030 |
gar | -0.030 |
wana | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
gypt | +0.130 |
bee | +0.103 |
Bees | +0.101 |
gar | +0.101 |
wana | +0.100 |
Neg logit contributions | |
MMA | -0.094 |
Vi | -0.093 |
Priv | -0.090 |
LX | -0.088 |
MV | -0.085 |
Token | Your |
Token ID | 3406 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
MMA | +0.867 |
Vi | +0.861 |
Priv | +0.827 |
LX | +0.810 |
MV | +0.787 |
Neg logit contributions | |
gypt | -1.175 |
bee | -0.929 |
Bees | -0.912 |
gar | -0.910 |
wana | -0.908 |
Token | s |
Token ID | 82 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
gypt | +0.627 |
bee | +0.500 |
gar | +0.492 |
Bees | +0.487 |
gars | +0.481 |
Neg logit contributions | |
MMA | -0.505 |
Vi | -0.505 |
Priv | -0.490 |
LX | -0.480 |
MV | -0.465 |
Token | )} |
Token ID | 38165 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
gypt | +0.856 |
bee | +0.693 |
Bees | +0.676 |
gar | +0.675 |
wana | +0.667 |
Neg logit contributions | |
Vi | -0.583 |
MMA | -0.582 |
Priv | -0.561 |
LX | -0.547 |
MV | -0.529 |
Token | 13 |
Token ID | 1511 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
MMA | +1.689 |
Vi | +1.676 |
Priv | +1.582 |
LX | +1.534 |
MV | +1.481 |
Neg logit contributions | |
gypt | -3.652 |
bee | -3.002 |
Bees | -2.957 |
gar | -2.953 |
wana | -2.949 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
gypt | +1.365 |
bee | +1.122 |
gar | +1.102 |
Bees | +1.101 |
wana | +1.078 |
Neg logit contributions | |
MMA | -0.779 |
Vi | -0.772 |
Priv | -0.740 |
LX | -0.729 |
MV | -0.699 |
Token | R |
Token ID | 371 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
Vi | +2.483 |
MMA | +2.478 |
Priv | +2.334 |
LX | +2.302 |
MV | +2.240 |
Neg logit contributions | |
gypt | -3.676 |
bee | -2.908 |
wana | -2.871 |
gar | -2.858 |
gars | -2.840 |
Token | c |
Token ID | 66 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
MMA | +2.798 |
Vi | +2.781 |
Priv | +2.715 |
LX | +2.611 |
MV | +2.516 |
Neg logit contributions | |
gypt | -3.552 |
Bees | -2.766 |
bee | -2.722 |
wana | -2.706 |
gar | -2.670 |
Token | 1 |
Token ID | 16 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
MMA | +5.897 |
Vi | +5.808 |
Priv | +5.795 |
LX | +5.384 |
strength | +5.176 |
Neg logit contributions | |
gypt | -9.811 |
Bees | -7.969 |
wana | -7.882 |
acca | -7.819 |
gars | -7.784 |
Token | { |
Token ID | 1391 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
MMA | +4.044 |
Vi | +4.010 |
Priv | +3.704 |
LX | +3.574 |
MV | +3.420 |
Neg logit contributions | |
gypt | -9.466 |
wana | -7.857 |
gars | -7.679 |
bee | -7.673 |
gar | -7.648 |
Token | ( |
Token ID | 7 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
MMA | +0.725 |
Vi | +0.719 |
Priv | +0.691 |
LX | +0.674 |
MV | +0.655 |
Neg logit contributions | |
gypt | -1.052 |
bee | -0.836 |
Bees | -0.824 |
gar | -0.820 |
wana | -0.819 |
Token | 12 |
Token ID | 1065 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
MMA | +0.630 |
Vi | +0.627 |
Priv | +0.604 |
LX | +0.591 |
MV | +0.576 |
Neg logit contributions | |
gypt | -0.758 |
bee | -0.592 |
Bees | -0.580 |
gar | -0.579 |
wana | -0.576 |
Token | 59 |
Token ID | 3270 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
gypt | +0.432 |
bee | +0.341 |
Bees | +0.334 |
gar | +0.334 |
wana | +0.330 |
Neg logit contributions | |
MMA | -0.348 |
Vi | -0.346 |
Priv | -0.335 |
LX | -0.327 |
MV | -0.317 |
Token | s |
Token ID | 82 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
gypt | +1.305 |
bee | +1.034 |
Bees | +1.014 |
gar | +1.012 |
wana | +1.004 |
Neg logit contributions | |
MMA | -0.982 |
Vi | -0.974 |
Priv | -0.940 |
LX | -0.920 |
MV | -0.894 |
Token | )} |
Token ID | 38165 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
gypt | +0.739 |
bee | +0.598 |
Bees | +0.585 |
gar | +0.584 |
wana | +0.578 |
Neg logit contributions | |
MMA | -0.491 |
Vi | -0.490 |
Priv | -0.471 |
LX | -0.460 |
MV | -0.445 |
Token | 7 |
Token ID | 767 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
MMA | +0.484 |
Vi | +0.481 |
Priv | +0.462 |
LX | +0.452 |
MV | +0.436 |
Neg logit contributions | |
gypt | -0.761 |
bee | -0.612 |
Bees | -0.603 |
gar | -0.600 |
wana | -0.598 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
gypt | +0.478 |
bee | +0.392 |
gar | +0.385 |
Bees | +0.385 |
wana | +0.380 |
Neg logit contributions | |
MMA | -0.261 |
Vi | -0.259 |
Priv | -0.247 |
LX | -0.243 |
MV | -0.233 |
Token | N |
Token ID | 399 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
MMA | +1.986 |
Vi | +1.979 |
Priv | +1.880 |
LX | +1.849 |
MV | +1.797 |
Neg logit contributions | |
gypt | -2.816 |
bee | -2.224 |
wana | -2.188 |
gar | -2.184 |
Bees | -2.175 |
Token | b |
Token ID | 65 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
MMA | +2.316 |
Vi | +2.298 |
Priv | +2.230 |
LX | +2.150 |
MV | +2.071 |
Neg logit contributions | |
gypt | -3.430 |
Bees | -2.710 |
bee | -2.700 |
wana | -2.687 |
gar | -2.658 |
Token | 3 |
Token ID | 18 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
Vi | +6.256 |
MMA | +6.136 |
Priv | +5.959 |
LX | +5.691 |
Orn | +5.292 |
Neg logit contributions | |
gypt | -11.585 |
Bees | -9.378 |
wana | -9.334 |
gars | -9.297 |
gar | -9.125 |
Token | { |
Token ID | 1391 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
MMA | +3.687 |
Vi | +3.650 |
Priv | +3.370 |
LX | +3.283 |
MV | +3.142 |
Neg logit contributions | |
gypt | -8.290 |
wana | -6.816 |
bee | -6.699 |
gars | -6.681 |
gar | -6.679 |
Token | ( |
Token ID | 7 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
MMA | +0.122 |
Vi | +0.122 |
Priv | +0.116 |
LX | +0.114 |
MV | +0.111 |
Neg logit contributions | |
gypt | -0.169 |
bee | -0.135 |
gar | -0.132 |
Bees | -0.132 |
wana | -0.131 |
Token | 244 |
Token ID | 25707 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
MMA | +0.664 |
Vi | +0.660 |
Priv | +0.635 |
LX | +0.622 |
MV | +0.605 |
Neg logit contributions | |
gypt | -0.840 |
bee | -0.660 |
Bees | -0.646 |
gar | -0.646 |
wana | -0.642 |
Token | s |
Token ID | 82 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
gypt | +2.327 |
bee | +1.863 |
gar | +1.840 |
Bees | +1.794 |
gars | +1.789 |
Neg logit contributions | |
MMA | -1.996 |
Vi | -1.990 |
Priv | -1.948 |
LX | -1.913 |
MV | -1.840 |
Token | x |
Token ID | 2124 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
MMA | +0.525 |
Vi | +0.521 |
Priv | +0.494 |
LX | +0.477 |
MV | +0.458 |
Neg logit contributions | |
gypt | -1.214 |
bee | -1.007 |
Bees | -0.992 |
gar | -0.991 |
wana | -0.987 |
Token | . |
Token ID | 13 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
gypt | +1.340 |
bee | +1.103 |
gar | +1.086 |
Bees | +1.070 |
wana | +1.062 |
Neg logit contributions | |
Vi | -0.774 |
MMA | -0.771 |
Priv | -0.733 |
LX | -0.724 |
MV | -0.696 |
Token | x |
Token ID | 87 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
gypt | +0.570 |
bee | +0.462 |
gar | +0.456 |
wana | +0.449 |
Bees | +0.449 |
Neg logit contributions | |
MMA | -0.356 |
Vi | -0.355 |
Priv | -0.338 |
LX | -0.331 |
MV | -0.321 |
Token | . |
Token ID | 13 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
gypt | +1.134 |
bee | +0.932 |
gar | +0.917 |
Bees | +0.908 |
wana | +0.901 |
Neg logit contributions | |
Vi | -0.643 |
MMA | -0.641 |
Priv | -0.610 |
LX | -0.599 |
MV | -0.577 |
Token | x |
Token ID | 87 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
gypt | +0.321 |
bee | +0.260 |
gar | +0.257 |
wana | +0.253 |
Bees | +0.252 |
Neg logit contributions | |
MMA | -0.202 |
Vi | -0.202 |
Priv | -0.191 |
LX | -0.188 |
MV | -0.183 |
Token | . |
Token ID | 13 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
MMA | +1.653 |
Vi | +1.629 |
Priv | +1.555 |
LX | +1.505 |
MV | +1.448 |
Neg logit contributions | |
gypt | -3.368 |
bee | -2.747 |
Bees | -2.724 |
wana | -2.711 |
gar | -2.700 |
Token | 122 |
Token ID | 18376 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
MMA | +4.231 |
Priv | +4.128 |
Vi | +3.906 |
LX | +3.606 |
Mort | +3.453 |
Neg logit contributions | |
gypt | -11.320 |
Bees | -9.495 |
wana | -9.297 |
gars | -9.269 |
bee | -9.202 |
Token | 110 |
Token ID | 9796 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
MMA | +1.948 |
Vi | +1.932 |
Priv | +1.843 |
LX | +1.800 |
MV | +1.740 |
Neg logit contributions | |
gypt | -3.390 |
bee | -2.746 |
Bees | -2.702 |
gar | -2.697 |
wana | -2.691 |
Token | 75 |
Token ID | 2425 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
gypt | +1.018 |
bee | +0.798 |
gar | +0.775 |
Bees | +0.772 |
wana | +0.760 |
Neg logit contributions | |
Vi | -0.950 |
MMA | -0.950 |
Priv | -0.908 |
LX | -0.895 |
MV | -0.874 |
Token | 46 |
Token ID | 3510 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
MMA | +0.492 |
Vi | +0.489 |
Priv | +0.471 |
LX | +0.462 |
MV | +0.450 |
Neg logit contributions | |
gypt | -0.583 |
bee | -0.455 |
Bees | -0.446 |
gar | -0.445 |
wana | -0.442 |
Token | x |
Token ID | 2124 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
MMA | +0.321 |
Vi | +0.318 |
Priv | +0.304 |
LX | +0.291 |
MV | +0.281 |
Neg logit contributions | |
gypt | -0.716 |
bee | -0.595 |
Bees | -0.585 |
gar | -0.584 |
wana | -0.581 |
Token | from |
Token ID | 422 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
gypt | +0.948 |
bee | +0.738 |
Bees | +0.723 |
gar | +0.722 |
wana | +0.720 |
Neg logit contributions | |
MMA | -0.813 |
Vi | -0.808 |
Priv | -0.789 |
LX | -0.765 |
MV | -0.743 |
Token | im |
Token ID | 545 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
MMA | +0.176 |
Vi | +0.175 |
Priv | +0.167 |
LX | +0.165 |
MV | +0.161 |
Neg logit contributions | |
gypt | -0.212 |
bee | -0.165 |
Bees | -0.162 |
wana | -0.161 |
gar | -0.161 |
Token | utils |
Token ID | 26791 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
gypt | +1.188 |
bee | +0.772 |
gar | +0.752 |
wana | +0.735 |
gars | +0.721 |
Neg logit contributions | |
Vi | -2.229 |
MMA | -2.228 |
Priv | -2.168 |
LX | -2.138 |
MV | -2.102 |
Token | import |
Token ID | 1330 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
gypt | +0.912 |
bee | +0.694 |
Bees | +0.677 |
gar | +0.676 |
wana | +0.674 |
Neg logit contributions | |
MMA | -0.910 |
Vi | -0.905 |
Priv | -0.880 |
LX | -0.860 |
MV | -0.839 |
Token | paths |
Token ID | 13532 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
MMA | +1.807 |
Vi | +1.795 |
Priv | +1.641 |
LX | +1.632 |
MV | +1.550 |
Neg logit contributions | |
gypt | -4.494 |
bee | -3.749 |
wana | -3.691 |
gar | -3.690 |
Bees | -3.688 |
Token | import |
Token ID | 1330 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
gypt | +0.994 |
bee | +0.756 |
Bees | +0.738 |
gar | +0.737 |
wana | +0.735 |
Neg logit contributions | |
MMA | -0.991 |
Vi | -0.984 |
Priv | -0.959 |
LX | -0.936 |
MV | -0.912 |
Token | n |
Token ID | 299 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Vi | +4.974 |
MMA | +4.938 |
LX | +4.479 |
MV | +4.339 |
Priv | +4.239 |
Neg logit contributions | |
gypt | -10.449 |
bee | -8.625 |
gars | -8.537 |
gar | -8.521 |
wana | -8.477 |
Token | umpy |
Token ID | 32152 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
gypt | +2.422 |
bee | +1.584 |
gar | +1.567 |
wana | +1.526 |
gars | +1.479 |
Neg logit contributions | |
Vi | -4.727 |
MMA | -4.702 |
Priv | -4.589 |
LX | -4.567 |
シャ | -4.439 |
Token | as |
Token ID | 355 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
MMA | +0.321 |
Vi | +0.319 |
Priv | +0.307 |
LX | +0.299 |
MV | +0.290 |
Neg logit contributions | |
gypt | -0.481 |
bee | -0.385 |
Bees | -0.377 |
gar | -0.377 |
wana | -0.376 |
Token | np |
Token ID | 45941 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
MMA | +3.395 |
Vi | +3.350 |
Priv | +3.134 |
LX | +3.130 |
MV | +3.059 |
Neg logit contributions | |
gypt | -5.013 |
bee | -3.976 |
gar | -3.959 |
Bees | -3.932 |
gars | -3.904 |
Token | import |
Token ID | 1330 |
Feature activation | -7.88e-02 |
Pos logit contributions | |
gypt | +1.793 |
bee | +1.354 |
Bees | +1.323 |
gar | +1.320 |
wana | +1.317 |
Neg logit contributions | |
MMA | -1.879 |
Vi | -1.862 |
Priv | -1.841 |
LX | -1.778 |
MV | -1.729 |