Token | . |
Token ID | 764 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Conserv | +0.947 |
oros | +0.931 |
� | +0.922 |
Hoo | +0.919 |
Relief | +0.912 |
Neg logit contributions | |
fetal | -0.882 |
touch | -0.788 |
hail | -0.784 |
STATE | -0.773 |
primates | -0.773 |
Token | Follow |
Token ID | 7281 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Conserv | +0.579 |
oros | +0.563 |
Hoo | +0.560 |
� | +0.558 |
Relief | +0.546 |
Neg logit contributions | |
fetal | -1.142 |
touch | -1.051 |
hail | -1.047 |
packages | -1.036 |
STATE | -1.036 |
Token | him |
Token ID | 683 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
Conserv | +0.597 |
Hoo | +0.579 |
oros | +0.578 |
� | +0.571 |
Relief | +0.567 |
Neg logit contributions | |
fetal | -0.748 |
touch | -0.681 |
hail | -0.679 |
packages | -0.671 |
STATE | -0.671 |
Token | on |
Token ID | 319 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Conserv | +0.453 |
oros | +0.448 |
Hoo | +0.443 |
� | +0.441 |
Relief | +0.437 |
Neg logit contributions | |
fetal | -0.308 |
touch | -0.269 |
hail | -0.267 |
STATE | -0.262 |
packages | -0.262 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Conserv | +1.072 |
oros | +1.047 |
Hoo | +1.039 |
� | +1.035 |
Relief | +1.011 |
Neg logit contributions | |
fetal | -1.707 |
touch | -1.562 |
hail | -1.560 |
STATE | -1.546 |
packages | -1.546 |
Token | @ |
Token ID | 2488 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Conserv | +1.064 |
oros | +1.044 |
Hoo | +1.031 |
� | +1.025 |
Relief | +1.010 |
Neg logit contributions | |
fetal | -1.612 |
touch | -1.474 |
hail | -1.471 |
STATE | -1.451 |
packages | -1.451 |
Token | jon |
Token ID | 46286 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
oros | +4.859 |
KK | +4.739 |
Conserv | +4.672 |
avy | +4.667 |
Hoo | +4.592 |
Neg logit contributions | |
fetal | -6.589 |
hail | -6.076 |
touch | -5.993 |
presume | -5.959 |
primates | -5.898 |
Token | chest |
Token ID | 46713 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
oros | +1.830 |
avy | +1.812 |
Conserv | +1.803 |
glers | +1.772 |
Hoo | +1.768 |
Neg logit contributions | |
fetal | -2.528 |
hail | -2.286 |
touch | -2.279 |
WHERE | -2.261 |
primates | -2.258 |
Token | o |
Token ID | 78 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
fetal | +0.694 |
touch | +0.631 |
hail | +0.626 |
STATE | +0.616 |
packages | +0.615 |
Neg logit contributions | |
Conserv | -0.545 |
oros | -0.535 |
Hoo | -0.531 |
� | -0.525 |
Relief | -0.522 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Conserv | +0.827 |
oros | +0.815 |
Hoo | +0.805 |
� | +0.798 |
Relief | +0.792 |
Neg logit contributions | |
fetal | -1.275 |
touch | -1.159 |
hail | -1.158 |
primates | -1.145 |
packages | -1.143 |
Token | An |
Token ID | 2025 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Conserv | +0.698 |
oros | +0.690 |
� | +0.678 |
Hoo | +0.678 |
KK | +0.672 |
Neg logit contributions | |
fetal | -0.958 |
touch | -0.873 |
hail | -0.870 |
primates | -0.855 |
presume | -0.853 |
Token | January |
Token ID | 3269 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
fetal | +0.368 |
touch | +0.335 |
hail | +0.330 |
packages | +0.325 |
primates | +0.325 |
Neg logit contributions | |
oros | -0.269 |
Conserv | -0.269 |
Hoo | -0.263 |
� | -0.262 |
)=( | -0.258 |
Token | 20 |
Token ID | 1160 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
fetal | +0.264 |
touch | +0.239 |
hail | +0.236 |
packages | +0.229 |
WHERE | +0.229 |
Neg logit contributions | |
oros | -0.277 |
Conserv | -0.276 |
Hoo | -0.271 |
� | -0.269 |
Relief | -0.267 |
Token | , |
Token ID | 11 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
Conserv | +1.449 |
oros | +1.421 |
Hoo | +1.413 |
� | +1.400 |
Relief | +1.393 |
Neg logit contributions | |
fetal | -1.504 |
touch | -1.353 |
hail | -1.342 |
STATE | -1.320 |
packages | -1.320 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Conserv | +1.989 |
Hoo | +1.910 |
oros | +1.906 |
Relief | +1.891 |
� | +1.887 |
Neg logit contributions | |
fetal | -2.633 |
touch | -2.399 |
STATE | -2.396 |
WHERE | -2.389 |
hail | -2.385 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
Conserv | +0.918 |
oros | +0.901 |
Hoo | +0.896 |
Relief | +0.891 |
� | +0.884 |
Neg logit contributions | |
fetal | -1.081 |
touch | -0.979 |
hail | -0.975 |
STATE | -0.962 |
WHERE | -0.961 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Conserv | +1.122 |
Hoo | +1.073 |
Relief | +1.069 |
oros | +1.059 |
� | +1.049 |
Neg logit contributions | |
fetal | -1.974 |
touch | -1.817 |
hail | -1.812 |
primates | -1.792 |
presume | -1.787 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Conserv | +3.155 |
Relief | +2.862 |
Hoo | +2.822 |
� | +2.768 |
Cream | +2.700 |
Neg logit contributions | |
fetal | -8.462 |
presume | -7.972 |
hail | -7.960 |
touch | -7.947 |
packages | -7.933 |
Token | 8 |
Token ID | 807 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
Conserv | +1.840 |
oros | +1.812 |
Hoo | +1.791 |
� | +1.779 |
Relief | +1.762 |
Neg logit contributions | |
fetal | -2.350 |
touch | -2.146 |
hail | -2.121 |
STATE | -2.087 |
packages | -2.087 |
Token | of |
Token ID | 286 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Conserv | +0.128 |
oros | +0.126 |
Hoo | +0.126 |
Relief | +0.124 |
� | +0.124 |
Neg logit contributions | |
fetal | -0.108 |
touch | -0.097 |
hail | -0.095 |
WHERE | -0.093 |
packages | -0.093 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Conserv | +1.665 |
oros | +1.652 |
Hoo | +1.626 |
� | +1.611 |
Relief | +1.600 |
Neg logit contributions | |
fetal | -2.030 |
touch | -1.855 |
hail | -1.825 |
STATE | -1.796 |
packages | -1.791 |
Token | Photos |
Token ID | 9434 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Conserv | +0.993 |
oros | +0.962 |
Hoo | +0.948 |
� | +0.930 |
Relief | +0.919 |
Neg logit contributions | |
fetal | -3.010 |
touch | -2.807 |
hail | -2.789 |
packages | -2.759 |
STATE | -2.758 |
Token | � |
Token ID | 247 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Conserv | +0.353 |
oros | +0.347 |
Hoo | +0.344 |
� | +0.340 |
Relief | +0.337 |
Neg logit contributions | |
fetal | -0.482 |
touch | -0.441 |
hail | -0.436 |
STATE | -0.430 |
packages | -0.430 |
Token | ll |
Token ID | 297 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Conserv | +0.727 |
oros | +0.717 |
Hoo | +0.714 |
� | +0.705 |
Relief | +0.703 |
Neg logit contributions | |
fetal | -0.652 |
touch | -0.582 |
hail | -0.576 |
packages | -0.564 |
STATE | -0.564 |
Token | send |
Token ID | 3758 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
Conserv | +1.256 |
oros | +1.249 |
glers | +1.246 |
Hoo | +1.246 |
Relief | +1.215 |
Neg logit contributions | |
fetal | -1.276 |
touch | -1.195 |
hail | -1.143 |
presume | -1.136 |
swipe | -1.107 |
Token | you |
Token ID | 345 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
Conserv | +2.575 |
oros | +2.539 |
Hoo | +2.532 |
� | +2.511 |
Relief | +2.493 |
Neg logit contributions | |
fetal | -1.965 |
touch | -1.745 |
hail | -1.718 |
STATE | -1.682 |
packages | -1.679 |
Token | three |
Token ID | 1115 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
Conserv | +3.697 |
oros | +3.663 |
� | +3.592 |
Relief | +3.572 |
Hoo | +3.547 |
Neg logit contributions | |
fetal | -3.662 |
packages | -3.350 |
STATE | -3.320 |
WHERE | -3.311 |
hail | -3.308 |
Token | meaningful |
Token ID | 11570 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Conserv | +2.823 |
oros | +2.707 |
Hoo | +2.682 |
� | +2.674 |
Relief | +2.672 |
Neg logit contributions | |
fetal | -4.958 |
touch | -4.515 |
hail | -4.515 |
WHERE | -4.505 |
packages | -4.488 |
Token | actions |
Token ID | 4028 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Conserv | +3.676 |
oros | +3.499 |
Relief | +3.472 |
� | +3.398 |
Cream | +3.376 |
Neg logit contributions | |
fetal | -7.733 |
auna | -7.135 |
WHERE | -7.135 |
STATE | -7.115 |
hail | -7.107 |
Token | you |
Token ID | 345 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Conserv | +5.693 |
Hoo | +5.427 |
� | +5.394 |
Relief | +5.344 |
)=( | +5.257 |
Neg logit contributions | |
fetal | -5.614 |
WHERE | -5.016 |
STATE | -5.015 |
packages | -4.998 |
presume | -4.943 |
Token | can |
Token ID | 460 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
Conserv | +5.277 |
� | +5.091 |
Relief | +5.002 |
avy | +4.877 |
Cream | +4.868 |
Neg logit contributions | |
fetal | -5.525 |
WHERE | -5.156 |
packages | -5.134 |
STATE | -5.110 |
auna | -5.100 |
Token | take |
Token ID | 1011 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
Conserv | +4.932 |
Hoo | +4.742 |
� | +4.742 |
Relief | +4.739 |
oros | +4.650 |
Neg logit contributions | |
fetal | -3.404 |
WHERE | -3.104 |
packages | -3.051 |
STATE | -3.000 |
primates | -2.936 |
Token | each |
Token ID | 1123 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Conserv | +2.267 |
oros | +2.213 |
Hoo | +2.204 |
Relief | +2.187 |
� | +2.184 |
Neg logit contributions | |
fetal | -2.172 |
touch | -1.943 |
hail | -1.929 |
packages | -1.903 |
STATE | -1.894 |
Token | ll |
Token ID | 297 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Conserv | +0.727 |
oros | +0.717 |
Hoo | +0.714 |
� | +0.705 |
Relief | +0.703 |
Neg logit contributions | |
fetal | -0.652 |
touch | -0.582 |
hail | -0.576 |
packages | -0.564 |
STATE | -0.564 |
Token | send |
Token ID | 3758 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
Conserv | +1.256 |
oros | +1.249 |
glers | +1.246 |
Hoo | +1.246 |
Relief | +1.215 |
Neg logit contributions | |
fetal | -1.276 |
touch | -1.195 |
hail | -1.143 |
presume | -1.136 |
swipe | -1.107 |
Token | you |
Token ID | 345 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
Conserv | +2.575 |
oros | +2.539 |
Hoo | +2.532 |
� | +2.511 |
Relief | +2.493 |
Neg logit contributions | |
fetal | -1.965 |
touch | -1.745 |
hail | -1.718 |
STATE | -1.682 |
packages | -1.679 |
Token | three |
Token ID | 1115 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
Conserv | +3.697 |
oros | +3.663 |
� | +3.592 |
Relief | +3.572 |
Hoo | +3.547 |
Neg logit contributions | |
fetal | -3.662 |
packages | -3.350 |
STATE | -3.320 |
WHERE | -3.311 |
hail | -3.308 |
Token | meaningful |
Token ID | 11570 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Conserv | +2.823 |
oros | +2.707 |
Hoo | +2.682 |
� | +2.674 |
Relief | +2.672 |
Neg logit contributions | |
fetal | -4.958 |
touch | -4.515 |
hail | -4.515 |
WHERE | -4.505 |
packages | -4.488 |
Token | actions |
Token ID | 4028 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Conserv | +3.676 |
oros | +3.499 |
Relief | +3.472 |
� | +3.398 |
Cream | +3.376 |
Neg logit contributions | |
fetal | -7.733 |
auna | -7.135 |
WHERE | -7.135 |
STATE | -7.115 |
hail | -7.107 |
Token | you |
Token ID | 345 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Conserv | +5.693 |
Hoo | +5.427 |
� | +5.394 |
Relief | +5.344 |
)=( | +5.257 |
Neg logit contributions | |
fetal | -5.614 |
WHERE | -5.016 |
STATE | -5.015 |
packages | -4.998 |
presume | -4.943 |
Token | can |
Token ID | 460 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
Conserv | +5.277 |
� | +5.091 |
Relief | +5.002 |
avy | +4.877 |
Cream | +4.868 |
Neg logit contributions | |
fetal | -5.525 |
WHERE | -5.156 |
packages | -5.134 |
STATE | -5.110 |
auna | -5.100 |
Token | take |
Token ID | 1011 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
Conserv | +4.932 |
Hoo | +4.742 |
� | +4.742 |
Relief | +4.739 |
oros | +4.650 |
Neg logit contributions | |
fetal | -3.404 |
WHERE | -3.104 |
packages | -3.051 |
STATE | -3.000 |
primates | -2.936 |
Token | each |
Token ID | 1123 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Conserv | +2.267 |
oros | +2.213 |
Hoo | +2.204 |
Relief | +2.187 |
� | +2.184 |
Neg logit contributions | |
fetal | -2.172 |
touch | -1.943 |
hail | -1.929 |
packages | -1.903 |
STATE | -1.894 |
Token | week |
Token ID | 1285 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
Conserv | +1.050 |
oros | +1.043 |
Hoo | +1.034 |
� | +1.020 |
Relief | +1.016 |
Neg logit contributions | |
fetal | -0.865 |
touch | -0.770 |
hail | -0.756 |
STATE | -0.739 |
packages | -0.737 |
Token | � |
Token ID | 447 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
Conserv | +1.794 |
� | +1.755 |
oros | +1.745 |
Hoo | +1.736 |
Relief | +1.720 |
Neg logit contributions | |
fetal | -1.954 |
hail | -1.751 |
touch | -1.743 |
STATE | -1.734 |
packages | -1.730 |
Token | � |
Token ID | 247 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
Conserv | +0.050 |
oros | +0.049 |
Hoo | +0.048 |
� | +0.047 |
Relief | +0.047 |
Neg logit contributions | |
fetal | -0.093 |
touch | -0.086 |
hail | -0.085 |
STATE | -0.084 |
WHERE | -0.084 |
Token | s |
Token ID | 82 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Conserv | +0.316 |
oros | +0.310 |
Hoo | +0.309 |
� | +0.307 |
Relief | +0.305 |
Neg logit contributions | |
fetal | -0.308 |
touch | -0.275 |
hail | -0.273 |
STATE | -0.268 |
packages | -0.268 |
Token | heartbreaking |
Token ID | 37154 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Conserv | +1.035 |
oros | +1.015 |
Hoo | +1.012 |
� | +1.004 |
Relief | +0.998 |
Neg logit contributions | |
fetal | -0.944 |
touch | -0.841 |
hail | -0.835 |
STATE | -0.823 |
packages | -0.823 |
Token | to |
Token ID | 284 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Conserv | +1.004 |
oros | +0.981 |
Hoo | +0.978 |
� | +0.972 |
Relief | +0.966 |
Neg logit contributions | |
fetal | -1.069 |
touch | -0.961 |
hail | -0.958 |
packages | -0.944 |
STATE | -0.944 |
Token | find |
Token ID | 1064 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Conserv | +2.084 |
Hoo | +2.032 |
oros | +2.020 |
� | +2.004 |
Relief | +1.997 |
Neg logit contributions | |
fetal | -2.147 |
packages | -1.928 |
WHERE | -1.920 |
STATE | -1.917 |
touch | -1.896 |
Token | that |
Token ID | 326 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
Conserv | +5.216 |
Hoo | +4.919 |
Relief | +4.877 |
� | +4.869 |
oros | +4.828 |
Neg logit contributions | |
fetal | -5.863 |
packages | -5.356 |
STATE | -5.337 |
auna | -5.321 |
simulate | -5.214 |
Token | our |
Token ID | 674 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Conserv | +1.613 |
Hoo | +1.563 |
oros | +1.562 |
� | +1.551 |
Relief | +1.542 |
Neg logit contributions | |
fetal | -1.630 |
touch | -1.457 |
hail | -1.450 |
packages | -1.444 |
STATE | -1.436 |
Token | memorial |
Token ID | 17357 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
Conserv | +0.659 |
oros | +0.647 |
Hoo | +0.644 |
� | +0.639 |
Relief | +0.636 |
Neg logit contributions | |
fetal | -0.556 |
touch | -0.494 |
hail | -0.489 |
packages | -0.480 |
STATE | -0.480 |
Token | to |
Token ID | 284 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
fetal | +1.770 |
touch | +1.611 |
hail | +1.574 |
primates | +1.540 |
packages | +1.539 |
Neg logit contributions | |
Conserv | -1.949 |
oros | -1.946 |
Hoo | -1.919 |
)=( | -1.885 |
Relief | -1.885 |
Token | the |
Token ID | 262 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
fetal | +0.055 |
touch | +0.049 |
hail | +0.049 |
STATE | +0.048 |
packages | +0.048 |
Neg logit contributions | |
Conserv | -0.054 |
oros | -0.053 |
Hoo | -0.053 |
� | -0.053 |
Relief | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
fetal | +3.544 |
touch | +3.245 |
hail | +3.185 |
packages | +3.151 |
presume | +3.107 |
Neg logit contributions | |
Conserv | -3.907 |
oros | -3.897 |
� | -3.888 |
Relief | -3.808 |
)=( | -3.801 |
Token | Roth |
Token ID | 16131 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
oros | +0.157 |
� | +0.155 |
)=( | +0.153 |
glers | +0.153 |
Relief | +0.151 |
Neg logit contributions | |
fetal | -0.193 |
hail | -0.176 |
touch | -0.174 |
packages | -0.172 |
STATE | -0.169 |
Token | bard |
Token ID | 23024 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Conserv | +0.297 |
oros | +0.279 |
Hoo | +0.274 |
� | +0.263 |
Relief | +0.256 |
Neg logit contributions | |
fetal | -1.870 |
touch | -1.759 |
hail | -1.749 |
packages | -1.732 |
STATE | -1.731 |
Token | ( |
Token ID | 357 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Conserv | +1.463 |
� | +1.385 |
Hoo | +1.382 |
oros | +1.379 |
Relief | +1.372 |
Neg logit contributions | |
fetal | -2.123 |
hail | -1.960 |
touch | -1.950 |
primates | -1.949 |
packages | -1.939 |
Token | Prom |
Token ID | 24129 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
Conserv | +1.674 |
KK | +1.648 |
Hoo | +1.627 |
� | +1.627 |
Relief | +1.625 |
Neg logit contributions | |
fetal | -2.573 |
primates | -2.354 |
touch | -2.343 |
hail | -2.318 |
presume | -2.310 |
Token | etheus |
Token ID | 36916 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
oros | +1.380 |
Conserv | +1.365 |
Relief | +1.328 |
Hoo | +1.322 |
� | +1.314 |
Neg logit contributions | |
fetal | -1.814 |
hail | -1.664 |
packages | -1.649 |
touch | -1.645 |
primates | -1.641 |
Token | Books |
Token ID | 13661 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
Conserv | +3.897 |
Relief | +3.772 |
oros | +3.651 |
Cream | +3.620 |
Isles | +3.606 |
Neg logit contributions | |
fetal | -7.015 |
WHERE | -6.784 |
auna | -6.752 |
STATE | -6.646 |
packages | -6.644 |
Token | , |
Token ID | 11 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
Conserv | +2.595 |
oros | +2.480 |
� | +2.465 |
Hoo | +2.456 |
Cream | +2.453 |
Neg logit contributions | |
fetal | -3.195 |
packages | -2.920 |
STATE | -2.915 |
touch | -2.898 |
WHERE | -2.884 |
Token | 2000 |
Token ID | 4751 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Conserv | +1.999 |
oros | +1.948 |
Hoo | +1.945 |
� | +1.932 |
Relief | +1.926 |
Neg logit contributions | |
fetal | -1.957 |
touch | -1.753 |
hail | -1.736 |
packages | -1.719 |
primates | -1.717 |
Token | ), |
Token ID | 828 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Conserv | +0.874 |
oros | +0.855 |
Hoo | +0.854 |
� | +0.843 |
Relief | +0.842 |
Neg logit contributions | |
fetal | -1.050 |
touch | -0.945 |
STATE | -0.939 |
hail | -0.932 |
WHERE | -0.929 |
Token | my |
Token ID | 616 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
Conserv | +1.117 |
Relief | +1.085 |
� | +1.078 |
Hoo | +1.072 |
oros | +1.063 |
Neg logit contributions | |
fetal | -1.524 |
touch | -1.391 |
primates | -1.374 |
packages | -1.372 |
hail | -1.369 |
Token | to |
Token ID | 284 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
fetal | +0.707 |
touch | +0.634 |
hail | +0.630 |
STATE | +0.622 |
packages | +0.621 |
Neg logit contributions | |
Conserv | -0.716 |
oros | -0.705 |
Hoo | -0.701 |
� | -0.694 |
Relief | -0.691 |
Token | other |
Token ID | 584 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Conserv | +0.910 |
Hoo | +0.893 |
oros | +0.892 |
� | +0.881 |
Relief | +0.878 |
Neg logit contributions | |
fetal | -0.844 |
touch | -0.751 |
STATE | -0.745 |
hail | -0.745 |
packages | -0.744 |
Token | means |
Token ID | 1724 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Conserv | +2.184 |
Hoo | +2.130 |
oros | +2.115 |
� | +2.092 |
Relief | +2.090 |
Neg logit contributions | |
fetal | -2.182 |
STATE | -1.950 |
touch | -1.945 |
packages | -1.941 |
hail | -1.932 |
Token | BW |
Token ID | 37869 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
Conserv | +0.637 |
oros | +0.623 |
Hoo | +0.622 |
� | +0.616 |
Relief | +0.613 |
Neg logit contributions | |
fetal | -0.654 |
touch | -0.587 |
hail | -0.583 |
STATE | -0.575 |
packages | -0.575 |
Token | Editor |
Token ID | 12058 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Conserv | +2.624 |
Hoo | +2.573 |
oros | +2.573 |
Relief | +2.536 |
� | +2.535 |
Neg logit contributions | |
fetal | -2.462 |
packages | -2.179 |
touch | -2.176 |
hail | -2.167 |
primates | -2.148 |
Token | - |
Token ID | 12 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Conserv | +1.454 |
Hoo | +1.423 |
oros | +1.412 |
� | +1.408 |
Relief | +1.393 |
Neg logit contributions | |
fetal | -1.618 |
touch | -1.453 |
hail | -1.442 |
packages | -1.441 |
STATE | -1.435 |
Token | In |
Token ID | 818 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Conserv | +3.679 |
Hoo | +3.583 |
� | +3.565 |
KK | +3.551 |
oros | +3.451 |
Neg logit contributions | |
fetal | -7.107 |
hail | -6.544 |
touch | -6.525 |
primates | -6.474 |
packages | -6.466 |
Token | - |
Token ID | 12 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Conserv | +1.582 |
oros | +1.557 |
Hoo | +1.548 |
� | +1.535 |
Relief | +1.526 |
Neg logit contributions | |
fetal | -1.469 |
touch | -1.316 |
hail | -1.303 |
STATE | -1.276 |
packages | -1.275 |
Token | Chief |
Token ID | 23675 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
Conserv | +1.287 |
oros | +1.264 |
Hoo | +1.256 |
� | +1.245 |
Relief | +1.239 |
Neg logit contributions | |
fetal | -1.380 |
touch | -1.244 |
hail | -1.234 |
packages | -1.214 |
STATE | -1.212 |
Token | " |
Token ID | 366 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
Conserv | +3.458 |
Hoo | +3.385 |
� | +3.366 |
oros | +3.346 |
Relief | +3.291 |
Neg logit contributions | |
fetal | -4.058 |
packages | -3.700 |
touch | -3.676 |
STATE | -3.655 |
presume | -3.626 |
Token | Watch |
Token ID | 10723 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Conserv | +0.043 |
oros | +0.042 |
Hoo | +0.042 |
� | +0.042 |
Relief | +0.041 |
Neg logit contributions | |
fetal | -0.060 |
touch | -0.054 |
hail | -0.054 |
packages | -0.053 |
STATE | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
fetal | +0.458 |
touch | +0.415 |
hail | +0.411 |
packages | +0.401 |
primates | +0.401 |
Neg logit contributions | |
Conserv | -0.429 |
oros | -0.423 |
Hoo | -0.418 |
� | -0.415 |
Relief | -0.412 |
Token | Baltimore |
Token ID | 10346 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
Conserv | +0.420 |
oros | +0.413 |
Hoo | +0.409 |
� | +0.406 |
Relief | +0.402 |
Neg logit contributions | |
fetal | -0.492 |
touch | -0.448 |
hail | -0.443 |
packages | -0.435 |
primates | -0.434 |
Token | has |
Token ID | 468 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Conserv | +1.968 |
Hoo | +1.917 |
oros | +1.910 |
Relief | +1.893 |
� | +1.882 |
Neg logit contributions | |
fetal | -2.217 |
touch | -1.991 |
hail | -1.980 |
STATE | -1.967 |
WHERE | -1.958 |
Token | allowed |
Token ID | 3142 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Conserv | +0.828 |
oros | +0.811 |
Hoo | +0.808 |
� | +0.799 |
Relief | +0.796 |
Neg logit contributions | |
fetal | -0.894 |
touch | -0.805 |
hail | -0.800 |
STATE | -0.789 |
packages | -0.788 |
Token | at |
Token ID | 379 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Conserv | +2.125 |
Hoo | +2.078 |
Relief | +2.052 |
oros | +2.049 |
� | +2.038 |
Neg logit contributions | |
fetal | -2.120 |
STATE | -1.898 |
WHERE | -1.888 |
hail | -1.877 |
touch | -1.867 |
Token | least |
Token ID | 1551 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Conserv | +2.220 |
Hoo | +2.152 |
oros | +2.124 |
Relief | +2.122 |
� | +2.094 |
Neg logit contributions | |
fetal | -2.914 |
WHERE | -2.681 |
STATE | -2.658 |
presume | -2.650 |
primates | -2.650 |
Token | 20 |
Token ID | 1160 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Conserv | +4.659 |
Relief | +4.565 |
Hoo | +4.486 |
oros | +4.451 |
Playoff | +4.385 |
Neg logit contributions | |
fetal | -5.935 |
STATE | -5.514 |
auna | -5.476 |
WHERE | -5.456 |
packages | -5.394 |
Token | Fantasy |
Token ID | 10982 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
Conserv | +1.247 |
oros | +1.221 |
Relief | +1.217 |
Hoo | +1.207 |
� | +1.202 |
Neg logit contributions | |
fetal | -1.599 |
STATE | -1.446 |
WHERE | -1.436 |
packages | -1.435 |
auna | -1.435 |
Token | points |
Token ID | 2173 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Conserv | +0.389 |
oros | +0.384 |
Hoo | +0.382 |
� | +0.378 |
Relief | +0.375 |
Neg logit contributions | |
fetal | -0.333 |
touch | -0.298 |
hail | -0.293 |
packages | -0.287 |
STATE | -0.287 |
Token | to |
Token ID | 284 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Conserv | +0.587 |
oros | +0.575 |
Hoo | +0.572 |
� | +0.567 |
Relief | +0.564 |
Neg logit contributions | |
fetal | -0.601 |
touch | -0.538 |
hail | -0.535 |
STATE | -0.528 |
packages | -0.527 |
Token | quarterbacks |
Token ID | 23643 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
Conserv | +0.981 |
Hoo | +0.956 |
oros | +0.955 |
� | +0.943 |
Relief | +0.943 |
Neg logit contributions | |
fetal | -1.080 |
touch | -0.968 |
hail | -0.964 |
STATE | -0.955 |
packages | -0.948 |
Token | in |
Token ID | 287 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Conserv | +1.894 |
oros | +1.841 |
Hoo | +1.839 |
Relief | +1.808 |
� | +1.801 |
Neg logit contributions | |
fetal | -2.195 |
touch | -1.976 |
hail | -1.968 |
STATE | -1.951 |
packages | -1.941 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Conserv | +0.840 |
Hoo | +0.820 |
oros | +0.816 |
Relief | +0.806 |
� | +0.803 |
Neg logit contributions | |
fetal | -0.873 |
touch | -0.784 |
hail | -0.778 |
STATE | -0.776 |
packages | -0.769 |
Token | , |
Token ID | 11 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
Conserv | +1.486 |
oros | +1.446 |
Hoo | +1.445 |
Relief | +1.417 |
� | +1.405 |
Neg logit contributions | |
fetal | -1.745 |
touch | -1.571 |
hail | -1.567 |
STATE | -1.554 |
primates | -1.544 |
Token | California |
Token ID | 3442 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
Conserv | +0.245 |
Hoo | +0.238 |
oros | +0.237 |
Relief | +0.236 |
� | +0.234 |
Neg logit contributions | |
fetal | -0.173 |
touch | -0.151 |
hail | -0.150 |
STATE | -0.149 |
packages | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Conserv | +3.212 |
oros | +3.114 |
Hoo | +3.106 |
Relief | +3.065 |
Cream | +3.032 |
Neg logit contributions | |
fetal | -4.126 |
hail | -3.738 |
touch | -3.733 |
primates | -3.705 |
STATE | -3.703 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Conserv | +1.493 |
Hoo | +1.424 |
Relief | +1.423 |
oros | +1.389 |
� | +1.381 |
Neg logit contributions | |
fetal | -2.665 |
touch | -2.451 |
hail | -2.440 |
primates | -2.422 |
presume | -2.415 |
Token | Caption |
Token ID | 11260 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Conserv | +3.093 |
Relief | +2.825 |
Hoo | +2.795 |
� | +2.730 |
Cream | +2.672 |
Neg logit contributions | |
fetal | -7.901 |
presume | -7.398 |
hail | -7.396 |
touch | -7.389 |
packages | -7.360 |
Token | 12 |
Token ID | 1105 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
Conserv | +1.210 |
oros | +1.201 |
Hoo | +1.185 |
� | +1.178 |
Relief | +1.165 |
Neg logit contributions | |
fetal | -1.381 |
touch | -1.257 |
hail | -1.243 |
STATE | -1.220 |
packages | -1.219 |
Token | of |
Token ID | 286 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Conserv | +0.362 |
oros | +0.359 |
Hoo | +0.357 |
� | +0.352 |
Relief | +0.352 |
Neg logit contributions | |
fetal | -0.311 |
touch | -0.279 |
hail | -0.274 |
packages | -0.268 |
STATE | -0.268 |
Token | 15 |
Token ID | 1315 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
Conserv | +1.954 |
oros | +1.931 |
Hoo | +1.906 |
� | +1.888 |
Relief | +1.877 |
Neg logit contributions | |
fetal | -2.410 |
touch | -2.199 |
hail | -2.167 |
STATE | -2.135 |
packages | -2.130 |
Token | Photos |
Token ID | 9434 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Conserv | +1.116 |
oros | +1.073 |
Hoo | +1.062 |
� | +1.042 |
Relief | +1.030 |
Neg logit contributions | |
fetal | -3.450 |
touch | -3.218 |
hail | -3.199 |
packages | -3.163 |
STATE | -3.163 |
Token | Han |
Token ID | 9530 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Conserv | +0.269 |
Hoo | +0.261 |
oros | +0.258 |
� | +0.254 |
Relief | +0.253 |
Neg logit contributions | |
fetal | -0.451 |
hail | -0.412 |
touch | -0.412 |
packages | -0.408 |
STATE | -0.408 |
Token | z |
Token ID | 89 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
fetal | +1.180 |
touch | +1.066 |
hail | +1.057 |
STATE | +1.039 |
packages | +1.039 |
Neg logit contributions | |
Conserv | -1.067 |
oros | -1.047 |
Hoo | -1.040 |
� | -1.030 |
Relief | -1.024 |
Token | us |
Token ID | 385 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
fetal | +0.969 |
touch | +0.852 |
hail | +0.848 |
STATE | +0.835 |
packages | +0.832 |
Neg logit contributions | |
Conserv | -1.178 |
oros | -1.166 |
Hoo | -1.157 |
� | -1.147 |
Relief | -1.141 |
Token | on |
Token ID | 319 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Conserv | +0.237 |
oros | +0.232 |
Hoo | +0.232 |
� | +0.230 |
Relief | +0.229 |
Neg logit contributions | |
fetal | -0.172 |
touch | -0.151 |
hail | -0.149 |
STATE | -0.147 |
primates | -0.147 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Conserv | +1.308 |
Hoo | +1.272 |
oros | +1.272 |
� | +1.257 |
Relief | +1.244 |
Neg logit contributions | |
fetal | -2.066 |
touch | -1.886 |
hail | -1.882 |
STATE | -1.858 |
packages | -1.858 |
Token | @ |
Token ID | 2488 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Conserv | +1.577 |
oros | +1.550 |
Hoo | +1.542 |
� | +1.529 |
Relief | +1.510 |
Neg logit contributions | |
fetal | -2.272 |
hail | -2.074 |
touch | -2.062 |
STATE | -2.044 |
primates | -2.044 |
Token | dan |
Token ID | 25604 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
oros | +4.674 |
avy | +4.567 |
KK | +4.552 |
Conserv | +4.513 |
Hoo | +4.443 |
Neg logit contributions | |
fetal | -6.112 |
touch | -5.557 |
hail | -5.540 |
primates | -5.452 |
presume | -5.430 |
Token | han |
Token ID | 7637 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
oros | +1.735 |
Conserv | +1.729 |
Hoo | +1.704 |
� | +1.694 |
avy | +1.694 |
Neg logit contributions | |
fetal | -1.493 |
touch | -1.320 |
hail | -1.308 |
WHERE | -1.289 |
STATE | -1.288 |
Token | z |
Token ID | 89 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
fetal | +1.572 |
touch | +1.424 |
hail | +1.402 |
packages | +1.387 |
STATE | +1.383 |
Neg logit contributions | |
Conserv | -1.636 |
Hoo | -1.613 |
� | -1.582 |
oros | -1.568 |
Relief | -1.567 |
Token | us |
Token ID | 385 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
fetal | +0.954 |
touch | +0.872 |
packages | +0.850 |
hail | +0.849 |
auna | +0.837 |
Neg logit contributions | |
Conserv | -1.568 |
Hoo | -1.563 |
Relief | -1.542 |
� | -1.537 |
glers | -1.518 |
Token | and |
Token ID | 290 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
fetal | +1.416 |
touch | +1.284 |
hail | +1.268 |
STATE | +1.250 |
packages | +1.247 |
Neg logit contributions | |
Conserv | -1.289 |
oros | -1.266 |
Hoo | -1.256 |
� | -1.243 |
Relief | -1.236 |
Token | ua |
Token ID | 6413 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Conserv | +1.314 |
oros | +1.290 |
Hoo | +1.272 |
Relief | +1.262 |
� | +1.259 |
Neg logit contributions | |
fetal | -1.510 |
touch | -1.356 |
hail | -1.349 |
primates | -1.331 |
STATE | -1.329 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
fetal | +0.655 |
touch | +0.590 |
hail | +0.585 |
packages | +0.575 |
STATE | +0.575 |
Neg logit contributions | |
Conserv | -0.623 |
oros | -0.610 |
Hoo | -0.608 |
� | -0.600 |
Relief | -0.599 |
Token | New |
Token ID | 968 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Conserv | +0.567 |
Hoo | +0.556 |
Relief | +0.537 |
� | +0.536 |
oros | +0.533 |
Neg logit contributions | |
fetal | -0.746 |
touch | -0.675 |
packages | -0.669 |
hail | -0.668 |
presume | -0.668 |
Token | Hampshire |
Token ID | 13910 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Conserv | +0.676 |
Hoo | +0.664 |
oros | +0.660 |
� | +0.655 |
Relief | +0.654 |
Neg logit contributions | |
fetal | -0.449 |
touch | -0.391 |
hail | -0.385 |
primates | -0.380 |
packages | -0.379 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Conserv | +2.312 |
Hoo | +2.245 |
oros | +2.241 |
Relief | +2.221 |
Cream | +2.189 |
Neg logit contributions | |
fetal | -2.892 |
touch | -2.622 |
hail | -2.613 |
WHERE | -2.583 |
STATE | -2.568 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Conserv | +0.355 |
oros | +0.343 |
Hoo | +0.343 |
� | +0.337 |
Relief | +0.337 |
Neg logit contributions | |
fetal | -0.641 |
touch | -0.590 |
hail | -0.586 |
packages | -0.578 |
STATE | -0.577 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
Conserv | +3.031 |
Relief | +2.748 |
Hoo | +2.741 |
� | +2.680 |
Cream | +2.611 |
Neg logit contributions | |
fetal | -7.909 |
presume | -7.420 |
hail | -7.420 |
touch | -7.418 |
packages | -7.366 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Conserv | +2.012 |
oros | +1.969 |
Hoo | +1.963 |
� | +1.945 |
Relief | +1.934 |
Neg logit contributions | |
fetal | -2.009 |
touch | -1.803 |
hail | -1.791 |
packages | -1.760 |
STATE | -1.756 |
Token | of |
Token ID | 286 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
Conserv | +1.048 |
oros | +1.032 |
Hoo | +1.027 |
� | +1.017 |
Relief | +1.013 |
Neg logit contributions | |
fetal | -0.952 |
touch | -0.852 |
hail | -0.841 |
packages | -0.826 |
STATE | -0.826 |
Token | 15 |
Token ID | 1315 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
Conserv | +2.386 |
oros | +2.323 |
Hoo | +2.319 |
� | +2.293 |
Relief | +2.278 |
Neg logit contributions | |
fetal | -3.133 |
touch | -2.844 |
hail | -2.832 |
packages | -2.792 |
STATE | -2.788 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Conserv | +1.158 |
oros | +1.105 |
Hoo | +1.098 |
� | +1.077 |
Relief | +1.065 |
Neg logit contributions | |
fetal | -3.664 |
touch | -3.418 |
hail | -3.400 |
STATE | -3.361 |
packages | -3.360 |
Token | send |
Token ID | 3758 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
Conserv | +1.256 |
oros | +1.249 |
glers | +1.246 |
Hoo | +1.246 |
Relief | +1.215 |
Neg logit contributions | |
fetal | -1.276 |
touch | -1.195 |
hail | -1.143 |
presume | -1.136 |
swipe | -1.107 |
Token | you |
Token ID | 345 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
Conserv | +2.575 |
oros | +2.539 |
Hoo | +2.532 |
� | +2.511 |
Relief | +2.493 |
Neg logit contributions | |
fetal | -1.965 |
touch | -1.745 |
hail | -1.718 |
STATE | -1.682 |
packages | -1.679 |
Token | three |
Token ID | 1115 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
Conserv | +3.697 |
oros | +3.663 |
� | +3.592 |
Relief | +3.572 |
Hoo | +3.547 |
Neg logit contributions | |
fetal | -3.662 |
packages | -3.350 |
STATE | -3.320 |
WHERE | -3.311 |
hail | -3.308 |
Token | meaningful |
Token ID | 11570 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Conserv | +2.823 |
oros | +2.707 |
Hoo | +2.682 |
� | +2.674 |
Relief | +2.672 |
Neg logit contributions | |
fetal | -4.958 |
touch | -4.515 |
hail | -4.515 |
WHERE | -4.505 |
packages | -4.488 |
Token | actions |
Token ID | 4028 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Conserv | +3.676 |
oros | +3.499 |
Relief | +3.472 |
� | +3.398 |
Cream | +3.376 |
Neg logit contributions | |
fetal | -7.733 |
auna | -7.135 |
WHERE | -7.135 |
STATE | -7.115 |
hail | -7.107 |
Token | you |
Token ID | 345 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Conserv | +5.693 |
Hoo | +5.427 |
� | +5.394 |
Relief | +5.344 |
)=( | +5.257 |
Neg logit contributions | |
fetal | -5.614 |
WHERE | -5.016 |
STATE | -5.015 |
packages | -4.998 |
presume | -4.943 |
Token | can |
Token ID | 460 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
Conserv | +5.277 |
� | +5.091 |
Relief | +5.002 |
avy | +4.877 |
Cream | +4.868 |
Neg logit contributions | |
fetal | -5.525 |
WHERE | -5.156 |
packages | -5.134 |
STATE | -5.110 |
auna | -5.100 |
Token | take |
Token ID | 1011 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
Conserv | +4.932 |
Hoo | +4.742 |
� | +4.742 |
Relief | +4.739 |
oros | +4.650 |
Neg logit contributions | |
fetal | -3.404 |
WHERE | -3.104 |
packages | -3.051 |
STATE | -3.000 |
primates | -2.936 |
Token | each |
Token ID | 1123 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Conserv | +2.267 |
oros | +2.213 |
Hoo | +2.204 |
Relief | +2.187 |
� | +2.184 |
Neg logit contributions | |
fetal | -2.172 |
touch | -1.943 |
hail | -1.929 |
packages | -1.903 |
STATE | -1.894 |
Token | week |
Token ID | 1285 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
Conserv | +1.050 |
oros | +1.043 |
Hoo | +1.034 |
� | +1.020 |
Relief | +1.016 |
Neg logit contributions | |
fetal | -0.865 |
touch | -0.770 |
hail | -0.756 |
STATE | -0.739 |
packages | -0.737 |
Token | . |
Token ID | 13 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
Conserv | +2.941 |
� | +2.842 |
Hoo | +2.830 |
oros | +2.828 |
Relief | +2.801 |
Neg logit contributions | |
fetal | -3.462 |
hail | -3.156 |
packages | -3.119 |
touch | -3.111 |
presume | -3.093 |
Token | Voice |
Token ID | 15282 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
fetal | +0.840 |
touch | +0.780 |
STATE | +0.744 |
hail | +0.737 |
smarter | +0.734 |
Neg logit contributions | |
oros | -0.925 |
Hoo | -0.908 |
)=( | -0.908 |
glers | -0.903 |
Conserv | -0.901 |
Token | louder |
Token ID | 27089 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
fetal | +0.292 |
touch | +0.262 |
hail | +0.259 |
STATE | +0.255 |
smarter | +0.255 |
Neg logit contributions | |
Conserv | -0.289 |
oros | -0.286 |
Hoo | -0.283 |
� | -0.281 |
Relief | -0.279 |
Token | ! |
Token ID | 0 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Conserv | +1.094 |
oros | +1.075 |
Hoo | +1.069 |
� | +1.058 |
Relief | +1.054 |
Neg logit contributions | |
fetal | -1.026 |
touch | -0.917 |
hail | -0.909 |
packages | -0.894 |
STATE | -0.893 |
Token | Share |
Token ID | 8734 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
Conserv | +1.550 |
Relief | +1.482 |
Hoo | +1.481 |
oros | +1.478 |
� | +1.469 |
Neg logit contributions | |
fetal | -1.385 |
hail | -1.231 |
touch | -1.220 |
primates | -1.212 |
STATE | -1.208 |
Token | To |
Token ID | 1675 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
Conserv | +3.027 |
oros | +2.957 |
Hoo | +2.952 |
� | +2.920 |
Relief | +2.913 |
Neg logit contributions | |
fetal | -2.978 |
touch | -2.662 |
hail | -2.652 |
STATE | -2.613 |
primates | -2.593 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
fetal | +0.205 |
touch | +0.184 |
hail | +0.180 |
STATE | +0.176 |
packages | +0.175 |
Neg logit contributions | |
Conserv | -0.270 |
oros | -0.267 |
Hoo | -0.266 |
� | -0.263 |
Relief | -0.261 |
Token | To |
Token ID | 1675 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Conserv | +4.899 |
Relief | +4.761 |
� | +4.718 |
)=( | +4.677 |
Hoo | +4.660 |
Neg logit contributions | |
fetal | -6.059 |
hail | -5.521 |
presume | -5.405 |
touch | -5.360 |
packages | -5.342 |
Token |
|
Token ID | 198 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Conserv | +1.113 |
Hoo | +1.074 |
oros | +1.071 |
� | +1.067 |
Relief | +1.061 |
Neg logit contributions | |
fetal | -1.359 |
hail | -1.225 |
touch | -1.215 |
primates | -1.208 |
WHERE | -1.205 |
Token |
|
Token ID | 198 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Conserv | +0.653 |
oros | +0.644 |
Hoo | +0.639 |
� | +0.631 |
Relief | +0.628 |
Neg logit contributions | |
fetal | -0.706 |
touch | -0.638 |
hail | -0.631 |
STATE | -0.625 |
WHERE | -0.622 |
Token | In |
Token ID | 818 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
Conserv | +0.620 |
oros | +0.610 |
Hoo | +0.602 |
� | +0.600 |
KK | +0.596 |
Neg logit contributions | |
fetal | -0.877 |
touch | -0.801 |
hail | -0.798 |
primates | -0.784 |
presume | -0.783 |
Token | n |
Token ID | 77 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
fetal | +0.215 |
touch | +0.194 |
hail | +0.192 |
STATE | +0.189 |
packages | +0.189 |
Neg logit contributions | |
Conserv | -0.209 |
oros | -0.205 |
Hoo | -0.204 |
� | -0.202 |
Relief | -0.201 |
Token | from |
Token ID | 422 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
fetal | +0.358 |
touch | +0.322 |
hail | +0.319 |
packages | +0.311 |
primates | +0.311 |
Neg logit contributions | |
Conserv | -0.370 |
oros | -0.366 |
Hoo | -0.363 |
� | -0.359 |
Relief | -0.358 |
Token | Smy |
Token ID | 45083 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Conserv | +0.449 |
Hoo | +0.437 |
oros | +0.435 |
� | +0.428 |
Relief | +0.428 |
Neg logit contributions | |
fetal | -0.552 |
touch | -0.500 |
hail | -0.498 |
STATE | -0.494 |
packages | -0.493 |
Token | r |
Token ID | 81 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Conserv | +0.667 |
oros | +0.659 |
Hoo | +0.655 |
Relief | +0.644 |
avy | +0.641 |
Neg logit contributions | |
fetal | -0.623 |
touch | -0.554 |
hail | -0.544 |
STATE | -0.544 |
WHERE | -0.537 |
Token | na |
Token ID | 2616 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Conserv | +1.233 |
oros | +1.209 |
Hoo | +1.203 |
� | +1.193 |
Relief | +1.185 |
Neg logit contributions | |
fetal | -1.220 |
touch | -1.095 |
hail | -1.085 |
STATE | -1.066 |
packages | -1.063 |
Token | at |
Token ID | 379 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Conserv | +0.667 |
oros | +0.652 |
Hoo | +0.650 |
Relief | +0.639 |
� | +0.638 |
Neg logit contributions | |
fetal | -0.738 |
touch | -0.663 |
hail | -0.661 |
STATE | -0.651 |
packages | -0.650 |
Token | least |
Token ID | 1551 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Conserv | +1.664 |
Hoo | +1.615 |
oros | +1.600 |
� | +1.589 |
Relief | +1.586 |
Neg logit contributions | |
fetal | -1.627 |
touch | -1.454 |
hail | -1.453 |
presume | -1.439 |
packages | -1.437 |
Token | twice |
Token ID | 5403 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Conserv | +4.460 |
Hoo | +4.265 |
oros | +4.258 |
Relief | +4.227 |
� | +4.217 |
Neg logit contributions | |
fetal | -6.058 |
STATE | -5.576 |
auna | -5.504 |
packages | -5.474 |
WHERE | -5.456 |
Token | a |
Token ID | 257 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Conserv | +0.552 |
oros | +0.543 |
Hoo | +0.540 |
� | +0.535 |
Relief | +0.532 |
Neg logit contributions | |
fetal | -0.514 |
touch | -0.459 |
hail | -0.455 |
STATE | -0.447 |
packages | -0.447 |
Token | week |
Token ID | 1285 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Conserv | +1.443 |
Hoo | +1.407 |
oros | +1.404 |
� | +1.394 |
Relief | +1.391 |
Neg logit contributions | |
fetal | -1.185 |
touch | -1.047 |
hail | -1.041 |
packages | -1.036 |
STATE | -1.031 |
Token | to |
Token ID | 284 |
Feature activation | +7.43e-03 |
Pos logit contributions | |
Conserv | +1.583 |
oros | +1.547 |
Hoo | +1.543 |
� | +1.529 |
Relief | +1.524 |
Neg logit contributions | |
fetal | -1.679 |
touch | -1.505 |
STATE | -1.500 |
hail | -1.496 |
packages | -1.483 |
Token | hunt |
Token ID | 12601 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
Conserv | +0.037 |
Hoo | +0.037 |
oros | +0.037 |
� | +0.036 |
Relief | +0.036 |
Neg logit contributions | |
fetal | -0.027 |
touch | -0.024 |
hail | -0.023 |
STATE | -0.023 |
packages | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Conserv | +0.397 |
Hoo | +0.386 |
oros | +0.385 |
� | +0.381 |
Relief | +0.381 |
Neg logit contributions | |
fetal | -0.440 |
touch | -0.396 |
hail | -0.395 |
STATE | -0.390 |
packages | -0.389 |
Token | Irvine |
Token ID | 37277 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Conserv | +0.041 |
oros | +0.040 |
Hoo | +0.040 |
� | +0.040 |
Relief | +0.039 |
Neg logit contributions | |
fetal | -0.065 |
touch | -0.059 |
hail | -0.059 |
STATE | -0.058 |
packages | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Conserv | +2.122 |
Hoo | +2.081 |
oros | +2.064 |
Cream | +2.034 |
Relief | +2.027 |
Neg logit contributions | |
fetal | -2.675 |
hail | -2.423 |
touch | -2.393 |
packages | -2.385 |
STATE | -2.379 |
Token | California |
Token ID | 3442 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
Conserv | +1.314 |
Hoo | +1.286 |
oros | +1.274 |
Relief | +1.264 |
� | +1.264 |
Neg logit contributions | |
fetal | -0.905 |
touch | -0.783 |
hail | -0.779 |
STATE | -0.771 |
packages | -0.769 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Conserv | +2.511 |
oros | +2.477 |
Hoo | +2.458 |
Relief | +2.425 |
avy | +2.410 |
Neg logit contributions | |
fetal | -3.242 |
hail | -2.944 |
touch | -2.928 |
STATE | -2.894 |
primates | -2.885 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Conserv | +0.805 |
Hoo | +0.780 |
oros | +0.777 |
Relief | +0.774 |
� | +0.767 |
Neg logit contributions | |
fetal | -0.973 |
touch | -0.882 |
hail | -0.877 |
primates | -0.863 |
WHERE | -0.860 |
Token | Caption |
Token ID | 11260 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Conserv | +3.024 |
Relief | +2.757 |
Hoo | +2.724 |
� | +2.669 |
Cream | +2.621 |
Neg logit contributions | |
fetal | -7.841 |
hail | -7.352 |
presume | -7.345 |
touch | -7.332 |
packages | -7.325 |
Token | 9 |
Token ID | 860 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
Conserv | +1.867 |
Hoo | +1.806 |
oros | +1.805 |
� | +1.788 |
Relief | +1.784 |
Neg logit contributions | |
fetal | -2.289 |
touch | -2.076 |
hail | -2.068 |
STATE | -2.036 |
packages | -2.036 |
Token | of |
Token ID | 286 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
Conserv | +1.322 |
oros | +1.300 |
Hoo | +1.293 |
� | +1.281 |
Relief | +1.275 |
Neg logit contributions | |
fetal | -1.226 |
touch | -1.097 |
hail | -1.086 |
packages | -1.066 |
STATE | -1.066 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
Conserv | +1.845 |
oros | +1.820 |
Hoo | +1.798 |
� | +1.781 |
Relief | +1.769 |
Neg logit contributions | |
fetal | -2.296 |
touch | -2.093 |
hail | -2.067 |
STATE | -2.035 |
packages | -2.032 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Conserv | +1.043 |
oros | +1.006 |
Hoo | +0.994 |
� | +0.975 |
Relief | +0.963 |
Neg logit contributions | |
fetal | -3.199 |
touch | -2.984 |
hail | -2.966 |
packages | -2.933 |
STATE | -2.933 |
Token | Mor |
Token ID | 3461 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
Conserv | +0.413 |
oros | +0.403 |
Hoo | +0.403 |
� | +0.397 |
Relief | +0.396 |
Neg logit contributions | |
fetal | -0.514 |
touch | -0.466 |
hail | -0.462 |
STATE | -0.457 |
packages | -0.456 |
Token | aga |
Token ID | 8126 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Conserv | +1.937 |
oros | +1.912 |
Hoo | +1.880 |
avy | +1.844 |
Relief | +1.843 |
Neg logit contributions | |
fetal | -3.964 |
touch | -3.654 |
STATE | -3.615 |
hail | -3.603 |
WHERE | -3.601 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Conserv | +0.750 |
Hoo | +0.732 |
oros | +0.732 |
Relief | +0.721 |
� | +0.714 |
Neg logit contributions | |
fetal | -0.847 |
touch | -0.767 |
hail | -0.763 |
packages | -0.758 |
presume | -0.753 |
Token | California |
Token ID | 3442 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
Conserv | +1.105 |
Hoo | +1.085 |
oros | +1.067 |
Relief | +1.060 |
� | +1.058 |
Neg logit contributions | |
fetal | -0.879 |
touch | -0.774 |
packages | -0.770 |
STATE | -0.769 |
hail | -0.769 |
Token | . |
Token ID | 13 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Conserv | +2.312 |
oros | +2.273 |
Hoo | +2.255 |
Relief | +2.229 |
� | +2.210 |
Neg logit contributions | |
fetal | -2.808 |
touch | -2.546 |
hail | -2.541 |
STATE | -2.504 |
primates | -2.494 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Conserv | +0.822 |
Hoo | +0.789 |
Relief | +0.782 |
oros | +0.780 |
� | +0.765 |
Neg logit contributions | |
fetal | -1.554 |
touch | -1.429 |
hail | -1.423 |
primates | -1.406 |
STATE | -1.403 |
Token | Caption |
Token ID | 11260 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Conserv | +3.062 |
Relief | +2.794 |
Hoo | +2.774 |
� | +2.705 |
Cream | +2.661 |
Neg logit contributions | |
fetal | -7.808 |
hail | -7.304 |
presume | -7.299 |
touch | -7.296 |
packages | -7.268 |
Token | 13 |
Token ID | 1511 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
Conserv | +1.728 |
oros | +1.684 |
Hoo | +1.679 |
� | +1.667 |
Relief | +1.663 |
Neg logit contributions | |
fetal | -1.674 |
touch | -1.499 |
hail | -1.492 |
packages | -1.470 |
STATE | -1.465 |
Token | of |
Token ID | 286 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Conserv | +0.058 |
oros | +0.058 |
Hoo | +0.057 |
� | +0.056 |
Relief | +0.056 |
Neg logit contributions | |
fetal | -0.049 |
touch | -0.044 |
hail | -0.043 |
WHERE | -0.042 |
packages | -0.042 |
Token | 15 |
Token ID | 1315 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Conserv | +1.908 |
oros | +1.885 |
Hoo | +1.861 |
� | +1.843 |
Relief | +1.832 |
Neg logit contributions | |
fetal | -2.360 |
touch | -2.153 |
hail | -2.123 |
STATE | -2.092 |
packages | -2.088 |
Token | Photos |
Token ID | 9434 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
Conserv | +1.203 |
oros | +1.143 |
Hoo | +1.137 |
� | +1.118 |
Relief | +1.106 |
Neg logit contributions | |
fetal | -3.819 |
touch | -3.562 |
hail | -3.543 |
STATE | -3.503 |
packages | -3.501 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Conserv | +0.438 |
oros | +0.432 |
Hoo | +0.429 |
� | +0.424 |
Relief | +0.423 |
Neg logit contributions | |
fetal | -0.437 |
touch | -0.394 |
hail | -0.389 |
STATE | -0.381 |
packages | -0.381 |
Token | check |
Token ID | 2198 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Conserv | +0.661 |
oros | +0.649 |
Hoo | +0.646 |
� | +0.642 |
Relief | +0.638 |
Neg logit contributions | |
fetal | -0.528 |
touch | -0.467 |
hail | -0.463 |
packages | -0.455 |
STATE | -0.455 |
Token | out |
Token ID | 503 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Conserv | +0.597 |
oros | +0.592 |
Hoo | +0.590 |
� | +0.581 |
Relief | +0.581 |
Neg logit contributions | |
fetal | -0.496 |
touch | -0.446 |
hail | -0.438 |
smarter | -0.426 |
swipe | -0.424 |
Token | our |
Token ID | 674 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
fetal | +0.865 |
touch | +0.789 |
hail | +0.762 |
smarter | +0.748 |
swipe | +0.747 |
Neg logit contributions | |
oros | -0.940 |
Hoo | -0.939 |
Conserv | -0.931 |
avy | -0.925 |
glers | -0.918 |
Token | latest |
Token ID | 3452 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
fetal | +1.658 |
touch | +1.488 |
smarter | +1.462 |
swipe | +1.448 |
hail | +1.447 |
Neg logit contributions | |
)=( | -1.777 |
oros | -1.769 |
Hoo | -1.757 |
Conserv | -1.744 |
Relief | -1.718 |
Token | issue |
Token ID | 2071 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
fetal | +1.262 |
touch | +1.134 |
hail | +1.111 |
swipe | +1.082 |
smarter | +1.061 |
Neg logit contributions | |
oros | -1.705 |
Hoo | -1.700 |
Conserv | -1.693 |
� | -1.677 |
Relief | -1.670 |
Token |
|
Token ID | 198 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Conserv | +4.468 |
� | +4.297 |
oros | +4.219 |
Hoo | +4.213 |
Relief | +4.197 |
Neg logit contributions | |
fetal | -6.290 |
hail | -5.680 |
touch | -5.671 |
primates | -5.656 |
presume | -5.631 |
Token |
|
Token ID | 198 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
Conserv | +0.818 |
oros | +0.805 |
Hoo | +0.800 |
� | +0.790 |
Relief | +0.787 |
Neg logit contributions | |
fetal | -0.891 |
touch | -0.806 |
hail | -0.796 |
STATE | -0.785 |
packages | -0.784 |
Token | Travel |
Token ID | 33074 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Conserv | +0.239 |
Hoo | +0.238 |
oros | +0.231 |
Relief | +0.228 |
� | +0.227 |
Neg logit contributions | |
fetal | -0.504 |
touch | -0.467 |
STATE | -0.464 |
hail | -0.463 |
WHERE | -0.461 |
Token | With |
Token ID | 2080 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Conserv | +2.197 |
� | +2.087 |
Hoo | +2.074 |
Relief | +2.056 |
oros | +2.053 |
Neg logit contributions | |
fetal | -3.110 |
hail | -2.882 |
touch | -2.868 |
packages | -2.829 |
presume | -2.822 |
Token | The |
Token ID | 383 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
Conserv | +1.028 |
oros | +1.003 |
Hoo | +0.997 |
� | +0.987 |
Relief | +0.981 |
Neg logit contributions | |
fetal | -1.506 |
touch | -1.377 |
hail | -1.366 |
packages | -1.347 |
STATE | -1.347 |
Token | able |
Token ID | 1498 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Conserv | +1.565 |
oros | +1.540 |
Hoo | +1.532 |
� | +1.525 |
Relief | +1.511 |
Neg logit contributions | |
fetal | -1.372 |
touch | -1.215 |
hail | -1.210 |
STATE | -1.196 |
packages | -1.192 |
Token | to |
Token ID | 284 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Conserv | +1.147 |
oros | +1.128 |
Hoo | +1.122 |
� | +1.111 |
Relief | +1.106 |
Neg logit contributions | |
fetal | -1.077 |
touch | -0.966 |
hail | -0.955 |
packages | -0.937 |
STATE | -0.935 |
Token | buy |
Token ID | 2822 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
Conserv | +0.643 |
oros | +0.633 |
Hoo | +0.629 |
� | +0.626 |
Relief | +0.621 |
Neg logit contributions | |
fetal | -0.461 |
touch | -0.402 |
hail | -0.399 |
STATE | -0.395 |
WHERE | -0.393 |
Token | more |
Token ID | 517 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
fetal | +0.099 |
touch | +0.088 |
hail | +0.088 |
packages | +0.086 |
STATE | +0.086 |
Neg logit contributions | |
Conserv | -0.101 |
oros | -0.099 |
Hoo | -0.098 |
� | -0.097 |
Relief | -0.097 |
Token | at |
Token ID | 379 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Conserv | +1.056 |
oros | +1.034 |
Hoo | +1.030 |
� | +1.024 |
Relief | +1.018 |
Neg logit contributions | |
fetal | -1.018 |
touch | -0.909 |
hail | -0.902 |
STATE | -0.898 |
packages | -0.890 |
Token | least |
Token ID | 1551 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Conserv | +0.652 |
oros | +0.639 |
Hoo | +0.637 |
� | +0.631 |
Relief | +0.628 |
Neg logit contributions | |
fetal | -0.652 |
touch | -0.585 |
hail | -0.580 |
packages | -0.571 |
STATE | -0.571 |
Token | once |
Token ID | 1752 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
Conserv | +5.210 |
Hoo | +5.104 |
� | +5.090 |
Relief | +5.077 |
oros | +5.043 |
Neg logit contributions | |
fetal | -5.141 |
STATE | -4.705 |
hail | -4.554 |
WHERE | -4.531 |
presume | -4.511 |
Token | in |
Token ID | 287 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Conserv | +2.265 |
oros | +2.207 |
Hoo | +2.203 |
� | +2.185 |
Relief | +2.181 |
Neg logit contributions | |
fetal | -2.561 |
touch | -2.291 |
STATE | -2.290 |
hail | -2.279 |
WHERE | -2.266 |
Token | the |
Token ID | 262 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Conserv | +0.578 |
oros | +0.564 |
Hoo | +0.564 |
� | +0.557 |
Relief | +0.556 |
Neg logit contributions | |
fetal | -0.616 |
touch | -0.553 |
hail | -0.551 |
STATE | -0.546 |
packages | -0.543 |
Token | last |
Token ID | 938 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
Conserv | +0.978 |
oros | +0.956 |
Hoo | +0.954 |
� | +0.946 |
Relief | +0.942 |
Neg logit contributions | |
fetal | -1.015 |
touch | -0.913 |
hail | -0.905 |
STATE | -0.894 |
packages | -0.893 |
Token | 12 |
Token ID | 1105 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
Conserv | +0.198 |
oros | +0.194 |
Hoo | +0.194 |
� | +0.192 |
Relief | +0.191 |
Neg logit contributions | |
fetal | -0.183 |
touch | -0.163 |
hail | -0.162 |
STATE | -0.160 |
packages | -0.160 |
Token | obtained |
Token ID | 6492 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
Conserv | +0.270 |
oros | +0.265 |
Hoo | +0.264 |
� | +0.261 |
Relief | +0.260 |
Neg logit contributions | |
fetal | -0.259 |
touch | -0.232 |
hail | -0.230 |
packages | -0.227 |
STATE | -0.226 |
Token | conc |
Token ID | 1673 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
Conserv | +0.084 |
oros | +0.083 |
Hoo | +0.082 |
� | +0.082 |
Relief | +0.081 |
Neg logit contributions | |
fetal | -0.074 |
touch | -0.066 |
hail | -0.065 |
primates | -0.064 |
STATE | -0.064 |
Token | ord |
Token ID | 585 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
fetal | +0.495 |
touch | +0.461 |
hail | +0.458 |
packages | +0.453 |
primates | +0.452 |
Neg logit contributions | |
Conserv | -0.189 |
Hoo | -0.183 |
� | -0.180 |
oros | -0.180 |
Relief | -0.176 |
Token | ant |
Token ID | 415 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Conserv | +1.152 |
oros | +1.137 |
Hoo | +1.120 |
� | +1.115 |
Relief | +1.109 |
Neg logit contributions | |
fetal | -1.338 |
touch | -1.209 |
hail | -1.201 |
STATE | -1.190 |
WHERE | -1.187 |
Token | C |
Token ID | 327 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Conserv | +0.932 |
oros | +0.910 |
Hoo | +0.906 |
� | +0.898 |
Relief | +0.893 |
Neg logit contributions | |
fetal | -1.045 |
touch | -0.945 |
hail | -0.938 |
packages | -0.930 |
STATE | -0.930 |
Token | - |
Token ID | 12 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Conserv | +1.260 |
oros | +1.240 |
Hoo | +1.233 |
� | +1.223 |
avy | +1.213 |
Neg logit contributions | |
fetal | -1.323 |
touch | -1.189 |
hail | -1.182 |
packages | -1.173 |
WHERE | -1.165 |
Token | 14 |
Token ID | 1415 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
Conserv | +3.600 |
avy | +3.544 |
� | +3.522 |
oros | +3.484 |
� | +3.479 |
Neg logit contributions | |
fetal | -6.681 |
hail | -6.174 |
touch | -6.107 |
WHERE | -6.102 |
presume | -6.078 |
Token | results |
Token ID | 2482 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Conserv | +2.346 |
Hoo | +2.256 |
� | +2.249 |
oros | +2.247 |
Relief | +2.235 |
Neg logit contributions | |
fetal | -2.520 |
touch | -2.272 |
hail | -2.266 |
packages | -2.262 |
STATE | -2.257 |
Token | which |
Token ID | 543 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
fetal | +0.917 |
touch | +0.829 |
hail | +0.814 |
primates | +0.800 |
presume | +0.798 |
Neg logit contributions | |
Conserv | -0.898 |
oros | -0.889 |
Hoo | -0.881 |
Relief | -0.866 |
� | -0.866 |
Token | were |
Token ID | 547 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Conserv | +0.145 |
oros | +0.142 |
Hoo | +0.141 |
� | +0.140 |
Relief | +0.139 |
Neg logit contributions | |
fetal | -0.138 |
touch | -0.123 |
hail | -0.122 |
packages | -0.120 |
STATE | -0.120 |
Token | well |
Token ID | 880 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Conserv | +0.907 |
oros | +0.890 |
Hoo | +0.887 |
� | +0.880 |
Relief | +0.874 |
Neg logit contributions | |
fetal | -0.728 |
touch | -0.644 |
hail | -0.639 |
packages | -0.628 |
STATE | -0.628 |
Token | Tiff |
Token ID | 35775 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
Conserv | +0.696 |
Hoo | +0.679 |
oros | +0.672 |
Relief | +0.666 |
� | +0.664 |
Neg logit contributions | |
fetal | -0.907 |
touch | -0.826 |
hail | -0.819 |
STATE | -0.814 |
packages | -0.814 |
Token | in |
Token ID | 259 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
oros | +2.492 |
Conserv | +2.477 |
avy | +2.406 |
Hoo | +2.394 |
Relief | +2.354 |
Neg logit contributions | |
fetal | -4.727 |
touch | -4.303 |
STATE | -4.287 |
primates | -4.253 |
hail | -4.248 |
Token | , |
Token ID | 11 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Conserv | +1.011 |
Hoo | +0.991 |
oros | +0.984 |
Relief | +0.972 |
� | +0.967 |
Neg logit contributions | |
fetal | -1.139 |
touch | -1.023 |
hail | -1.018 |
packages | -1.008 |
primates | -1.002 |
Token | Iowa |
Token ID | 9406 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
Conserv | +1.536 |
Hoo | +1.506 |
Relief | +1.474 |
oros | +1.468 |
Cream | +1.463 |
Neg logit contributions | |
fetal | -1.459 |
touch | -1.295 |
hail | -1.293 |
packages | -1.292 |
WHERE | -1.290 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Conserv | +3.009 |
Hoo | +2.945 |
oros | +2.924 |
Relief | +2.914 |
Cream | +2.889 |
Neg logit contributions | |
fetal | -3.942 |
touch | -3.578 |
hail | -3.577 |
primates | -3.538 |
WHERE | -3.534 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Conserv | +0.662 |
Hoo | +0.639 |
oros | +0.638 |
� | +0.628 |
Relief | +0.627 |
Neg logit contributions | |
fetal | -1.187 |
touch | -1.092 |
hail | -1.085 |
packages | -1.070 |
primates | -1.070 |
Token | Caption |
Token ID | 11260 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Conserv | +2.951 |
Hoo | +2.689 |
Relief | +2.658 |
� | +2.625 |
KK | +2.579 |
Neg logit contributions | |
fetal | -7.727 |
presume | -7.256 |
hail | -7.255 |
touch | -7.251 |
packages | -7.187 |
Token | 5 |
Token ID | 642 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Conserv | +2.638 |
Relief | +2.518 |
Hoo | +2.517 |
� | +2.508 |
Cream | +2.488 |
Neg logit contributions | |
fetal | -2.577 |
hail | -2.358 |
primates | -2.294 |
presume | -2.291 |
touch | -2.284 |
Token | of |
Token ID | 286 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Conserv | +1.030 |
oros | +1.014 |
Hoo | +1.009 |
� | +0.998 |
Relief | +0.995 |
Neg logit contributions | |
fetal | -0.936 |
touch | -0.838 |
hail | -0.828 |
STATE | -0.813 |
packages | -0.813 |
Token | 15 |
Token ID | 1315 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
Conserv | +2.001 |
oros | +1.960 |
Hoo | +1.948 |
� | +1.927 |
Relief | +1.915 |
Neg logit contributions | |
fetal | -2.560 |
touch | -2.329 |
hail | -2.309 |
packages | -2.274 |
STATE | -2.273 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
Conserv | +1.086 |
oros | +1.031 |
Hoo | +1.029 |
� | +1.008 |
Relief | +0.998 |
Neg logit contributions | |
fetal | -3.492 |
touch | -3.257 |
hail | -3.242 |
STATE | -3.204 |
packages | -3.203 |
Token | . |
Token ID | 13 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
fetal | +0.342 |
touch | +0.309 |
hail | +0.307 |
STATE | +0.305 |
WHERE | +0.303 |
Neg logit contributions | |
Conserv | -0.293 |
oros | -0.287 |
Hoo | -0.285 |
Relief | -0.282 |
� | -0.281 |
Token |
|
Token ID | 198 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
fetal | +0.260 |
touch | +0.236 |
hail | +0.234 |
packages | +0.230 |
primates | +0.230 |
Neg logit contributions | |
Conserv | -0.220 |
oros | -0.215 |
Hoo | -0.214 |
� | -0.211 |
Relief | -0.211 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
fetal | +0.296 |
touch | +0.268 |
hail | +0.264 |
STATE | +0.261 |
packages | +0.260 |
Neg logit contributions | |
Conserv | -0.290 |
oros | -0.288 |
Hoo | -0.286 |
� | -0.281 |
Relief | -0.281 |
Token | Story |
Token ID | 11605 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
fetal | +0.190 |
touch | +0.173 |
hail | +0.173 |
primates | +0.170 |
presume | +0.169 |
Neg logit contributions | |
Conserv | -0.141 |
oros | -0.139 |
Hoo | -0.137 |
� | -0.136 |
Relief | -0.135 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
fetal | +1.634 |
touch | +1.492 |
hail | +1.429 |
smarter | +1.417 |
packages | +1.416 |
Neg logit contributions | |
oros | -1.579 |
Hoo | -1.576 |
Conserv | -1.571 |
Relief | -1.542 |
� | -1.532 |
Token | below |
Token ID | 2174 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
fetal | +1.691 |
touch | +1.462 |
smarter | +1.376 |
hail | +1.365 |
swipe | +1.358 |
Neg logit contributions | |
oros | -3.333 |
Conserv | -3.308 |
Hoo | -3.297 |
Relief | -3.272 |
)=( | -3.255 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
fetal | +3.801 |
touch | +3.238 |
swipe | +3.065 |
blast | +2.965 |
emphasis | +2.951 |
Neg logit contributions | |
� | -9.005 |
Relief | -8.821 |
oros | -8.820 |
glers | -8.813 |
ロ | -8.777 |
Token |
|
Token ID | 198 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
fetal | +0.921 |
touch | +0.831 |
hail | +0.815 |
STATE | +0.811 |
WHERE | +0.810 |
Neg logit contributions | |
Conserv | -0.976 |
oros | -0.971 |
Hoo | -0.965 |
Relief | -0.951 |
� | -0.947 |
Token |
|
Token ID | 198 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
fetal | +1.631 |
touch | +1.478 |
hail | +1.439 |
STATE | +1.439 |
WHERE | +1.432 |
Neg logit contributions | |
oros | -1.828 |
Conserv | -1.816 |
Hoo | -1.801 |
� | -1.767 |
Relief | -1.766 |
Token | " |
Token ID | 1 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
fetal | +1.714 |
touch | +1.559 |
hail | +1.543 |
STATE | +1.540 |
WHERE | +1.537 |
Neg logit contributions | |
Conserv | -1.359 |
Hoo | -1.327 |
oros | -1.326 |
� | -1.310 |
Relief | -1.301 |
Token | Interestingly |
Token ID | 33092 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Conserv | +0.707 |
oros | +0.689 |
Hoo | +0.684 |
� | +0.678 |
Relief | +0.674 |
Neg logit contributions | |
fetal | -1.055 |
touch | -0.964 |
hail | -0.958 |
primates | -0.943 |
packages | -0.940 |
Token | race |
Token ID | 3234 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
fetal | +1.965 |
touch | +1.762 |
hail | +1.700 |
smarter | +1.665 |
swipe | +1.657 |
Neg logit contributions | |
oros | -2.555 |
Conserv | -2.537 |
Hoo | -2.513 |
avy | -2.489 |
)=( | -2.486 |
Token | less |
Token ID | 1342 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
fetal | +0.538 |
touch | +0.480 |
hail | +0.474 |
STATE | +0.463 |
packages | +0.462 |
Neg logit contributions | |
Conserv | -0.632 |
oros | -0.625 |
Hoo | -0.620 |
� | -0.615 |
Relief | -0.611 |
Token | about |
Token ID | 546 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
fetal | +1.873 |
touch | +1.709 |
hail | +1.641 |
primates | +1.600 |
STATE | +1.596 |
Neg logit contributions | |
oros | -2.272 |
Conserv | -2.268 |
Hoo | -2.241 |
� | -2.230 |
Relief | -2.227 |
Token | Washington |
Token ID | 2669 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
fetal | +0.064 |
touch | +0.058 |
hail | +0.057 |
packages | +0.056 |
STATE | +0.056 |
Neg logit contributions | |
Conserv | -0.058 |
oros | -0.057 |
Hoo | -0.057 |
� | -0.056 |
Relief | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Conserv | +0.387 |
oros | +0.379 |
Hoo | +0.377 |
� | +0.373 |
Relief | +0.372 |
Neg logit contributions | |
fetal | -0.393 |
touch | -0.354 |
hail | -0.351 |
packages | -0.346 |
STATE | -0.346 |
Token | more |
Token ID | 517 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
fetal | +1.229 |
touch | +1.020 |
hail | +1.001 |
STATE | +0.967 |
packages | +0.966 |
Neg logit contributions | |
Conserv | -2.926 |
oros | -2.891 |
Hoo | -2.878 |
� | -2.859 |
Relief | -2.848 |
Token | about |
Token ID | 546 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
fetal | +4.964 |
touch | +4.559 |
hail | +4.290 |
smarter | +4.211 |
emphasis | +4.179 |
Neg logit contributions | |
oros | -7.348 |
glers | -7.245 |
Hoo | -7.187 |
KK | -7.130 |
� | -7.090 |
Token | Cassidy |
Token ID | 41373 |
Feature activation | +4.07e-03 |
Pos logit contributions | |
fetal | +2.621 |
touch | +2.407 |
hail | +2.330 |
smarter | +2.274 |
primates | +2.250 |
Neg logit contributions | |
oros | -2.546 |
glers | -2.491 |
Hoo | -2.472 |
Conserv | -2.472 |
avy | -2.470 |
Token | and |
Token ID | 290 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Conserv | +0.016 |
oros | +0.015 |
Hoo | +0.015 |
� | +0.015 |
Relief | +0.015 |
Neg logit contributions | |
fetal | -0.019 |
touch | -0.018 |
hail | -0.018 |
packages | -0.017 |
STATE | -0.017 |
Token | Louisiana |
Token ID | 13340 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Conserv | +1.041 |
oros | +1.016 |
Hoo | +1.013 |
� | +1.003 |
Relief | +0.997 |
Neg logit contributions | |
fetal | -1.123 |
touch | -1.012 |
hail | -1.005 |
packages | -0.992 |
STATE | -0.990 |
Token | . |
Token ID | 13 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Conserv | +1.152 |
oros | +1.119 |
Hoo | +1.115 |
� | +1.103 |
Relief | +1.101 |
Neg logit contributions | |
fetal | -1.306 |
touch | -1.177 |
hail | -1.173 |
packages | -1.156 |
STATE | -1.153 |
Token | . |
Token ID | 13 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
Conserv | +1.999 |
Hoo | +1.945 |
oros | +1.931 |
Relief | +1.927 |
� | +1.910 |
Neg logit contributions | |
fetal | -2.196 |
packages | -1.974 |
STATE | -1.971 |
hail | -1.950 |
WHERE | -1.948 |
Token |
|
Token ID | 198 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
Conserv | +0.380 |
Hoo | +0.371 |
oros | +0.370 |
Relief | +0.366 |
� | +0.365 |
Neg logit contributions | |
fetal | -0.441 |
touch | -0.399 |
hail | -0.396 |
packages | -0.390 |
STATE | -0.390 |
Token |
|
Token ID | 198 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
Conserv | +0.037 |
oros | +0.037 |
Hoo | +0.037 |
� | +0.036 |
Relief | +0.036 |
Neg logit contributions | |
fetal | -0.039 |
touch | -0.035 |
hail | -0.035 |
STATE | -0.034 |
packages | -0.034 |
Token | Story |
Token ID | 11605 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
fetal | +0.110 |
touch | +0.100 |
hail | +0.099 |
primates | +0.098 |
presume | +0.097 |
Neg logit contributions | |
Conserv | -0.082 |
oros | -0.080 |
Hoo | -0.080 |
� | -0.079 |
Relief | -0.079 |
Token | continues |
Token ID | 4477 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
fetal | +0.981 |
touch | +0.897 |
hail | +0.862 |
smarter | +0.852 |
primates | +0.852 |
Neg logit contributions | |
oros | -0.949 |
Conserv | -0.945 |
Hoo | -0.945 |
Relief | -0.935 |
� | -0.922 |
Token | below |
Token ID | 2174 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
fetal | +1.270 |
touch | +1.104 |
smarter | +1.043 |
hail | +1.034 |
swipe | +1.023 |
Neg logit contributions | |
oros | -2.471 |
Conserv | -2.468 |
Hoo | -2.449 |
Relief | -2.439 |
� | -2.419 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
fetal | +3.606 |
touch | +3.094 |
swipe | +2.922 |
blast | +2.840 |
emphasis | +2.829 |
Neg logit contributions | |
� | -8.679 |
glers | -8.533 |
Relief | -8.500 |
ロ | -8.482 |
oros | -8.479 |
Token |
|
Token ID | 198 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
fetal | +0.276 |
touch | +0.249 |
hail | +0.245 |
STATE | +0.243 |
WHERE | +0.242 |
Neg logit contributions | |
Conserv | -0.280 |
oros | -0.278 |
Hoo | -0.276 |
Relief | -0.272 |
� | -0.272 |
Token |
|
Token ID | 198 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
fetal | +1.180 |
touch | +1.068 |
hail | +1.044 |
STATE | +1.039 |
WHERE | +1.034 |
Neg logit contributions | |
oros | -1.265 |
Conserv | -1.258 |
Hoo | -1.245 |
� | -1.224 |
Relief | -1.222 |
Token | Story |
Token ID | 11605 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
fetal | +1.328 |
touch | +1.208 |
hail | +1.195 |
STATE | +1.190 |
WHERE | +1.187 |
Neg logit contributions | |
Conserv | -1.066 |
oros | -1.042 |
Hoo | -1.037 |
� | -1.025 |
Relief | -1.018 |
Token | continues |
Token ID | 4477 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
fetal | +1.747 |
touch | +1.608 |
hail | +1.539 |
presume | +1.516 |
smarter | +1.515 |
Neg logit contributions | |
oros | -1.756 |
Conserv | -1.739 |
Hoo | -1.736 |
Relief | -1.722 |
� | -1.682 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
fetal | +3.369 |
touch | +2.895 |
swipe | +2.602 |
hail | +2.571 |
blast | +2.571 |
Neg logit contributions | |
oros | -7.041 |
)=( | -7.033 |
� | -6.997 |
Hoo | -6.992 |
� | -6.950 |
Token |
|
Token ID | 198 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
fetal | +0.699 |
touch | +0.630 |
hail | +0.619 |
STATE | +0.616 |
WHERE | +0.614 |
Neg logit contributions | |
Conserv | -0.723 |
oros | -0.720 |
Hoo | -0.713 |
Relief | -0.701 |
� | -0.700 |
Token |
|
Token ID | 198 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
fetal | +1.302 |
touch | +1.178 |
hail | +1.153 |
STATE | +1.149 |
WHERE | +1.143 |
Neg logit contributions | |
oros | -1.404 |
Conserv | -1.395 |
Hoo | -1.381 |
� | -1.357 |
Relief | -1.355 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
fetal | +1.653 |
touch | +1.504 |
hail | +1.487 |
STATE | +1.480 |
WHERE | +1.475 |
Neg logit contributions | |
Conserv | -1.311 |
oros | -1.283 |
Hoo | -1.280 |
� | -1.262 |
Relief | -1.257 |
Token | continues |
Token ID | 4477 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
fetal | +2.674 |
touch | +2.458 |
packages | +2.299 |
hail | +2.298 |
smarter | +2.294 |
Neg logit contributions | |
oros | -2.849 |
Hoo | -2.814 |
Relief | -2.790 |
Conserv | -2.788 |
� | -2.736 |
Token | below |
Token ID | 2174 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
fetal | +2.253 |
touch | +1.948 |
smarter | +1.837 |
swipe | +1.783 |
hail | +1.781 |
Neg logit contributions | |
oros | -4.782 |
Hoo | -4.740 |
Conserv | -4.740 |
Relief | -4.737 |
)=( | -4.691 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
fetal | +3.547 |
touch | +3.070 |
swipe | +2.868 |
emphasis | +2.797 |
blast | +2.766 |
Neg logit contributions | |
� | -8.439 |
Relief | -8.360 |
glers | -8.359 |
oros | -8.342 |
� | -8.301 |
Token |
|
Token ID | 198 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
fetal | +1.116 |
touch | +1.005 |
STATE | +0.988 |
hail | +0.986 |
WHERE | +0.986 |
Neg logit contributions | |
oros | -1.222 |
Conserv | -1.219 |
Hoo | -1.205 |
Relief | -1.188 |
� | -1.185 |
Token |
|
Token ID | 198 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
fetal | +1.765 |
touch | +1.600 |
hail | +1.559 |
STATE | +1.557 |
WHERE | +1.553 |
Neg logit contributions | |
oros | -2.007 |
Conserv | -1.990 |
Hoo | -1.974 |
Relief | -1.937 |
� | -1.934 |
Token | The |
Token ID | 464 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
fetal | +2.227 |
STATE | +2.031 |
WHERE | +2.028 |
touch | +2.020 |
packages | +2.000 |
Neg logit contributions | |
Conserv | -1.845 |
Hoo | -1.813 |
oros | -1.803 |
Relief | -1.774 |
� | -1.773 |
Token | government |
Token ID | 1230 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
Conserv | +0.334 |
oros | +0.328 |
Hoo | +0.326 |
� | +0.323 |
Relief | +0.322 |
Neg logit contributions | |
fetal | -0.308 |
touch | -0.275 |
hail | -0.273 |
STATE | -0.269 |
packages | -0.269 |
Token | . |
Token ID | 13 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
fetal | +1.960 |
touch | +1.783 |
hail | +1.763 |
primates | +1.709 |
presume | +1.701 |
Neg logit contributions | |
oros | -1.998 |
Conserv | -1.997 |
� | -1.951 |
)=( | -1.941 |
Hoo | -1.936 |
Token |
|
Token ID | 198 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
fetal | +1.395 |
touch | +1.260 |
hail | +1.250 |
WHERE | +1.228 |
STATE | +1.227 |
Neg logit contributions | |
Conserv | -1.306 |
oros | -1.305 |
Hoo | -1.275 |
� | -1.270 |
avy | -1.254 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
fetal | +0.796 |
touch | +0.721 |
hail | +0.707 |
STATE | +0.700 |
packages | +0.697 |
Neg logit contributions | |
Conserv | -0.827 |
oros | -0.825 |
Hoo | -0.817 |
� | -0.802 |
Relief | -0.801 |
Token | Story |
Token ID | 11605 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
fetal | +0.750 |
touch | +0.682 |
hail | +0.676 |
STATE | +0.666 |
packages | +0.666 |
Neg logit contributions | |
Conserv | -0.605 |
oros | -0.593 |
Hoo | -0.589 |
� | -0.583 |
Relief | -0.579 |
Token | continues |
Token ID | 4477 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
fetal | +0.896 |
touch | +0.822 |
hail | +0.792 |
presume | +0.781 |
smarter | +0.779 |
Neg logit contributions | |
oros | -0.857 |
Conserv | -0.856 |
Hoo | -0.852 |
Relief | -0.844 |
� | -0.829 |
Token | below |
Token ID | 2174 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
fetal | +1.210 |
touch | +1.051 |
smarter | +0.994 |
hail | +0.991 |
swipe | +0.976 |
Neg logit contributions | |
Conserv | -2.313 |
oros | -2.305 |
Hoo | -2.286 |
Relief | -2.281 |
� | -2.260 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
fetal | +3.545 |
touch | +3.076 |
swipe | +2.874 |
catch | +2.822 |
blast | +2.797 |
Neg logit contributions | |
� | -8.302 |
glers | -8.171 |
oros | -8.156 |
Relief | -8.127 |
� | -8.103 |
Token |
|
Token ID | 198 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
fetal | +0.691 |
touch | +0.623 |
hail | +0.612 |
STATE | +0.607 |
WHERE | +0.607 |
Neg logit contributions | |
Conserv | -0.725 |
oros | -0.721 |
Hoo | -0.716 |
Relief | -0.706 |
� | -0.703 |
Token |
|
Token ID | 198 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
fetal | +1.282 |
touch | +1.162 |
hail | +1.133 |
STATE | +1.129 |
WHERE | +1.123 |
Neg logit contributions | |
oros | -1.393 |
Conserv | -1.389 |
Hoo | -1.374 |
� | -1.349 |
Relief | -1.347 |
Token | He |
Token ID | 1544 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
fetal | +1.370 |
touch | +1.246 |
STATE | +1.234 |
WHERE | +1.233 |
hail | +1.232 |
Neg logit contributions | |
Conserv | -1.139 |
oros | -1.116 |
Hoo | -1.109 |
� | -1.096 |
Relief | -1.086 |
Token | eventually |
Token ID | 4191 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
fetal | +0.452 |
touch | +0.409 |
hail | +0.406 |
presume | +0.394 |
primates | +0.393 |
Neg logit contributions | |
Conserv | -0.469 |
oros | -0.461 |
Hoo | -0.458 |
� | -0.453 |
Relief | -0.451 |
Token | . |
Token ID | 13 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
fetal | +1.241 |
touch | +1.117 |
hail | +1.106 |
packages | +1.086 |
STATE | +1.085 |
Neg logit contributions | |
Conserv | -1.218 |
oros | -1.196 |
Hoo | -1.189 |
� | -1.178 |
Relief | -1.171 |
Token |
|
Token ID | 198 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
Conserv | +0.370 |
oros | +0.363 |
Hoo | +0.360 |
� | +0.357 |
Relief | +0.355 |
Neg logit contributions | |
fetal | -0.432 |
touch | -0.392 |
hail | -0.388 |
packages | -0.382 |
STATE | -0.382 |
Token |
|
Token ID | 198 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
Conserv | +0.296 |
oros | +0.291 |
Hoo | +0.289 |
� | +0.286 |
Relief | +0.285 |
Neg logit contributions | |
fetal | -0.318 |
touch | -0.288 |
hail | -0.285 |
STATE | -0.281 |
packages | -0.280 |
Token | Story |
Token ID | 11605 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Conserv | +0.205 |
oros | +0.202 |
� | +0.198 |
Hoo | +0.198 |
Relief | +0.196 |
Neg logit contributions | |
fetal | -0.277 |
touch | -0.252 |
hail | -0.251 |
primates | -0.247 |
presume | -0.247 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
fetal | +1.393 |
touch | +1.275 |
hail | +1.226 |
presume | +1.213 |
smarter | +1.211 |
Neg logit contributions | |
oros | -1.327 |
Conserv | -1.322 |
Hoo | -1.322 |
Relief | -1.294 |
� | -1.284 |
Token | below |
Token ID | 2174 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
fetal | +1.729 |
touch | +1.500 |
smarter | +1.411 |
hail | +1.395 |
swipe | +1.387 |
Neg logit contributions | |
oros | -3.422 |
Conserv | -3.412 |
Hoo | -3.393 |
Relief | -3.376 |
)=( | -3.348 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
fetal | +3.608 |
touch | +3.079 |
swipe | +2.924 |
emphasis | +2.820 |
blast | +2.819 |
Neg logit contributions | |
� | -8.218 |
oros | -8.102 |
glers | -8.070 |
Relief | -8.065 |
� | -8.019 |
Token |
|
Token ID | 198 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
fetal | +0.709 |
touch | +0.640 |
hail | +0.628 |
STATE | +0.625 |
WHERE | +0.623 |
Neg logit contributions | |
Conserv | -0.742 |
oros | -0.736 |
Hoo | -0.732 |
Relief | -0.721 |
� | -0.718 |
Token |
|
Token ID | 198 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
fetal | +1.315 |
touch | +1.192 |
hail | +1.163 |
STATE | +1.158 |
WHERE | +1.154 |
Neg logit contributions | |
oros | -1.429 |
Conserv | -1.422 |
Hoo | -1.408 |
� | -1.384 |
Relief | -1.382 |
Token | It |
Token ID | 1026 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
fetal | +1.552 |
touch | +1.409 |
STATE | +1.396 |
hail | +1.394 |
WHERE | +1.393 |
Neg logit contributions | |
Conserv | -1.243 |
Hoo | -1.216 |
oros | -1.213 |
� | -1.196 |
Relief | -1.189 |
Token | 's |
Token ID | 338 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Conserv | +0.813 |
oros | +0.799 |
Hoo | +0.794 |
� | +0.788 |
Relief | +0.783 |
Neg logit contributions | |
fetal | -0.730 |
touch | -0.651 |
hail | -0.644 |
STATE | -0.635 |
packages | -0.634 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Conserv | +0.233 |
oros | +0.228 |
Hoo | +0.227 |
� | +0.224 |
Relief | +0.224 |
Neg logit contributions | |
fetal | -0.248 |
touch | -0.222 |
hail | -0.221 |
STATE | -0.219 |
packages | -0.218 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
fetal | +1.279 |
touch | +1.157 |
hail | +1.147 |
packages | +1.130 |
STATE | +1.129 |
Neg logit contributions | |
Conserv | -1.109 |
oros | -1.085 |
Hoo | -1.081 |
� | -1.068 |
Relief | -1.064 |
Token |
|
Token ID | 198 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
Conserv | +0.094 |
oros | +0.093 |
Hoo | +0.092 |
� | +0.091 |
Relief | +0.091 |
Neg logit contributions | |
fetal | -0.098 |
touch | -0.089 |
hail | -0.088 |
STATE | -0.087 |
WHERE | -0.086 |
Token | UN |
Token ID | 4944 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Conserv | +0.136 |
oros | +0.135 |
Hoo | +0.133 |
� | +0.133 |
KK | +0.132 |
Neg logit contributions | |
fetal | -0.148 |
touch | -0.133 |
hail | -0.133 |
primates | -0.130 |
presume | -0.130 |
Token | DE |
Token ID | 7206 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
fetal | +1.786 |
touch | +1.603 |
STATE | +1.585 |
hail | +1.579 |
WHERE | +1.574 |
Neg logit contributions | |
Conserv | -1.880 |
oros | -1.856 |
Hoo | -1.835 |
� | -1.819 |
Relief | -1.809 |
Token | AD |
Token ID | 2885 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
fetal | +3.585 |
WHERE | +3.388 |
STATE | +3.330 |
touch | +3.302 |
hail | +3.221 |
Neg logit contributions | |
oros | -2.667 |
Conserv | -2.638 |
glers | -2.601 |
Hoo | -2.559 |
Relief | -2.529 |
Token | * |
Token ID | 9 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
fetal | +5.555 |
STATE | +5.121 |
WHERE | +5.094 |
touch | +5.083 |
RESP | +4.903 |
Neg logit contributions | |
Conserv | -5.969 |
oros | -5.871 |
Hoo | -5.811 |
avy | -5.710 |
glers | -5.710 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
fetal | +1.506 |
touch | +1.360 |
hail | +1.348 |
packages | +1.329 |
primates | +1.326 |
Neg logit contributions | |
Conserv | -1.310 |
oros | -1.286 |
Hoo | -1.279 |
� | -1.267 |
Relief | -1.259 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
fetal | +0.106 |
touch | +0.096 |
hail | +0.095 |
STATE | +0.094 |
WHERE | +0.094 |
Neg logit contributions | |
Conserv | -0.106 |
oros | -0.105 |
Hoo | -0.105 |
� | -0.103 |
Relief | -0.103 |
Token | + |
Token ID | 10 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Conserv | +0.079 |
oros | +0.078 |
Hoo | +0.077 |
� | +0.077 |
Relief | +0.076 |
Neg logit contributions | |
fetal | -0.093 |
hail | -0.084 |
touch | -0.084 |
primates | -0.083 |
presume | -0.082 |
Token | Soul |
Token ID | 8653 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Conserv | +1.040 |
Hoo | +1.011 |
oros | +0.998 |
Relief | +0.996 |
� | +0.993 |
Neg logit contributions | |
fetal | -1.275 |
touch | -1.155 |
hail | -1.149 |
packages | -1.141 |
STATE | -1.131 |
Token | data |
Token ID | 7890 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
fetal | +2.742 |
packages | +2.446 |
touch | +2.419 |
hail | +2.346 |
presume | +2.344 |
Neg logit contributions | |
Conserv | -4.264 |
Hoo | -4.228 |
Relief | -4.153 |
� | -4.069 |
KK | -4.037 |
Token | _ |
Token ID | 4808 |
Feature activation | +4.51e-03 |
Pos logit contributions | |
fetal | +3.377 |
touch | +3.086 |
hail | +3.028 |
swipe | +2.914 |
smarter | +2.888 |
Neg logit contributions | |
oros | -3.173 |
Conserv | -3.169 |
Hoo | -3.110 |
glers | -3.106 |
)=( | -3.058 |
Token | full |
Token ID | 1336 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
Conserv | +0.021 |
oros | +0.021 |
Hoo | +0.021 |
� | +0.021 |
Relief | +0.020 |
Neg logit contributions | |
fetal | -0.018 |
touch | -0.016 |
hail | -0.016 |
STATE | -0.016 |
WHERE | -0.015 |
Token | v |
Token ID | 410 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
fetal | +1.019 |
touch | +0.942 |
hail | +0.924 |
swipe | +0.903 |
presume | +0.903 |
Neg logit contributions | |
Conserv | -0.758 |
oros | -0.750 |
Hoo | -0.748 |
Relief | -0.730 |
glers | -0.725 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
fetal | +0.710 |
touch | +0.617 |
hail | +0.606 |
WHERE | +0.579 |
packages | +0.579 |
Neg logit contributions | |
Conserv | -1.309 |
oros | -1.293 |
Hoo | -1.287 |
Relief | -1.277 |
� | -1.270 |
Token | { |
Token ID | 1391 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
fetal | +4.133 |
touch | +3.938 |
STATE | +3.702 |
hail | +3.694 |
smarter | +3.673 |
Neg logit contributions | |
)=( | -4.701 |
arrang | -4.691 |
oros | -4.672 |
Hoo | -4.616 |
Conserv | -4.615 |
Token | // |
Token ID | 3373 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
fetal | +6.031 |
touch | +5.636 |
hail | +5.350 |
presume | +5.220 |
swipe | +5.188 |
Neg logit contributions | |
oros | -5.578 |
Conserv | -5.460 |
glers | -5.381 |
Hoo | -5.366 |
)=( | -5.365 |
Token | Time |
Token ID | 3862 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
fetal | +0.398 |
hail | +0.353 |
touch | +0.353 |
packages | +0.348 |
primates | +0.347 |
Neg logit contributions | |
Conserv | -0.470 |
Hoo | -0.459 |
oros | -0.458 |
Relief | -0.456 |
� | -0.454 |
Token | component |
Token ID | 7515 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
fetal | +0.326 |
touch | +0.249 |
hail | +0.238 |
STATE | +0.224 |
primates | +0.223 |
Neg logit contributions | |
Conserv | -1.225 |
oros | -1.214 |
Hoo | -1.211 |
� | -1.201 |
Relief | -1.199 |
Token | const |
Token ID | 1500 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Conserv | +0.777 |
oros | +0.767 |
Hoo | +0.759 |
� | +0.750 |
Relief | +0.747 |
Neg logit contributions | |
fetal | -0.882 |
touch | -0.798 |
hail | -0.791 |
STATE | -0.775 |
packages | -0.774 |
Token | float |
Token ID | 12178 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
fetal | +1.991 |
touch | +1.824 |
hail | +1.708 |
presume | +1.663 |
blast | +1.649 |
Neg logit contributions | |
oros | -2.744 |
Conserv | -2.717 |
glers | -2.681 |
Hoo | -2.664 |
)=( | -2.646 |
Token | sum |
Token ID | 2160 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
fetal | +1.961 |
touch | +1.760 |
hail | +1.740 |
packages | +1.707 |
primates | +1.701 |
Neg logit contributions | |
Conserv | -2.180 |
oros | -2.161 |
Hoo | -2.147 |
� | -2.116 |
Relief | -2.114 |
Token | ( |
Token ID | 357 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
fetal | +0.218 |
touch | +0.193 |
hail | +0.191 |
presume | +0.187 |
primates | +0.187 |
Neg logit contributions | |
Conserv | -0.280 |
oros | -0.276 |
Hoo | -0.275 |
� | -0.273 |
Relief | -0.272 |
Token | count |
Token ID | 954 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
fetal | +1.737 |
touch | +1.562 |
hail | +1.543 |
packages | +1.518 |
STATE | +1.514 |
Neg logit contributions | |
Conserv | -1.822 |
oros | -1.794 |
Hoo | -1.784 |
� | -1.762 |
Relief | -1.755 |
Token | ) |
Token ID | 1267 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
Conserv | +0.333 |
oros | +0.331 |
� | +0.328 |
Hoo | +0.327 |
Relief | +0.323 |
Neg logit contributions | |
fetal | -0.279 |
hail | -0.247 |
touch | -0.247 |
presume | -0.242 |
primates | -0.240 |
Token | count |
Token ID | 954 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
fetal | +2.581 |
touch | +2.254 |
hail | +2.226 |
WHERE | +2.199 |
primates | +2.152 |
Neg logit contributions | |
Conserv | -4.158 |
oros | -4.118 |
Hoo | -4.077 |
� | -4.028 |
Relief | -4.012 |
Token | FROM |
Token ID | 16034 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
fetal | +0.356 |
touch | +0.317 |
hail | +0.314 |
packages | +0.309 |
STATE | +0.308 |
Neg logit contributions | |
Conserv | -0.406 |
oros | -0.400 |
Hoo | -0.397 |
� | -0.395 |
Relief | -0.393 |
Token | cl |
Token ID | 537 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
fetal | +5.531 |
touch | +5.098 |
hail | +4.983 |
primates | +4.845 |
packages | +4.839 |
Neg logit contributions | |
oros | -5.919 |
Conserv | -5.789 |
glers | -5.784 |
KK | -5.757 |
)=( | -5.736 |
Token | ojure |
Token ID | 32511 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
fetal | +0.297 |
touch | +0.256 |
hail | +0.253 |
packages | +0.248 |
primates | +0.247 |
Neg logit contributions | |
Conserv | -0.530 |
Hoo | -0.521 |
oros | -0.517 |
Relief | -0.516 |
� | -0.516 |
Token | . |
Token ID | 764 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
fetal | +2.591 |
touch | +2.302 |
hail | +2.279 |
packages | +2.233 |
STATE | +2.233 |
Neg logit contributions | |
Conserv | -3.097 |
oros | -3.046 |
Hoo | -3.029 |
� | -3.005 |
Relief | -2.990 |
Token | libraries |
Token ID | 12782 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
fetal | +1.238 |
touch | +1.110 |
hail | +1.099 |
packages | +1.081 |
STATE | +1.077 |
Neg logit contributions | |
Conserv | -1.301 |
oros | -1.281 |
Hoo | -1.274 |
� | -1.262 |
Relief | -1.254 |
Token | WHERE |
Token ID | 33411 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
fetal | +0.308 |
touch | +0.264 |
hail | +0.262 |
packages | +0.258 |
primates | +0.257 |
Neg logit contributions | |
Conserv | -0.516 |
oros | -0.508 |
Hoo | -0.507 |
� | -0.504 |
Relief | -0.502 |
Token |
|
Token ID | 198 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
fetal | +0.225 |
touch | +0.204 |
hail | +0.202 |
STATE | +0.199 |
packages | +0.198 |
Neg logit contributions | |
Conserv | -0.195 |
oros | -0.192 |
Hoo | -0.190 |
� | -0.188 |
Relief | -0.187 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
fetal | +0.172 |
touch | +0.156 |
hail | +0.153 |
STATE | +0.152 |
WHERE | +0.151 |
Neg logit contributions | |
Conserv | -0.171 |
oros | -0.169 |
Hoo | -0.168 |
� | -0.165 |
Relief | -0.165 |
Token | � |
Token ID | 447 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
fetal | +0.060 |
touch | +0.055 |
hail | +0.054 |
packages | +0.053 |
STATE | +0.053 |
Neg logit contributions | |
Conserv | -0.053 |
oros | -0.052 |
Hoo | -0.052 |
� | -0.051 |
Relief | -0.051 |
Token | � |
Token ID | 250 |
Feature activation | +3.31e-03 |
Pos logit contributions | |
Conserv | +0.358 |
oros | +0.349 |
� | +0.346 |
Hoo | +0.344 |
Relief | +0.340 |
Neg logit contributions | |
fetal | -0.802 |
touch | -0.744 |
hail | -0.742 |
packages | -0.730 |
STATE | -0.728 |
Token | Let |
Token ID | 5756 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Conserv | +0.012 |
oros | +0.012 |
Hoo | +0.012 |
� | +0.012 |
Relief | +0.012 |
Neg logit contributions | |
fetal | -0.016 |
touch | -0.015 |
hail | -0.015 |
packages | -0.015 |
STATE | -0.014 |
Token | me |
Token ID | 502 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
fetal | +0.746 |
touch | +0.674 |
hail | +0.666 |
STATE | +0.654 |
packages | +0.654 |
Neg logit contributions | |
Conserv | -0.658 |
oros | -0.648 |
Hoo | -0.643 |
� | -0.634 |
Relief | -0.633 |
Token | give |
Token ID | 1577 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
fetal | +4.680 |
touch | +4.443 |
presume | +4.186 |
hail | +4.117 |
swipe | +4.044 |
Neg logit contributions | |
Hoo | -6.757 |
oros | -6.754 |
Conserv | -6.738 |
glers | -6.658 |
Relief | -6.617 |
Token | you |
Token ID | 345 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
fetal | +1.885 |
touch | +1.669 |
hail | +1.637 |
primates | +1.598 |
presume | +1.589 |
Neg logit contributions | |
Conserv | -2.543 |
oros | -2.540 |
Hoo | -2.512 |
� | -2.480 |
avy | -2.463 |
Token | some |
Token ID | 617 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
fetal | +1.507 |
touch | +1.353 |
hail | +1.329 |
primates | +1.298 |
STATE | +1.295 |
Neg logit contributions | |
Conserv | -1.704 |
oros | -1.690 |
Hoo | -1.672 |
� | -1.647 |
Relief | -1.640 |
Token | truthful |
Token ID | 42278 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
fetal | +1.798 |
touch | +1.608 |
hail | +1.577 |
primates | +1.535 |
presume | +1.525 |
Neg logit contributions | |
Conserv | -2.339 |
oros | -2.333 |
Hoo | -2.306 |
� | -2.268 |
avy | -2.249 |
Token | euphem |
Token ID | 48732 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
Conserv | +0.504 |
oros | +0.493 |
Hoo | +0.492 |
� | +0.489 |
Relief | +0.486 |
Neg logit contributions | |
fetal | -0.440 |
touch | -0.391 |
hail | -0.388 |
packages | -0.383 |
STATE | -0.382 |
Token | . |
Token ID | 13 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
fetal | +0.699 |
touch | +0.628 |
hail | +0.625 |
STATE | +0.620 |
packages | +0.619 |
Neg logit contributions | |
Conserv | -0.648 |
oros | -0.634 |
Hoo | -0.633 |
� | -0.626 |
Relief | -0.624 |
Token |
|
Token ID | 198 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
fetal | +1.867 |
touch | +1.674 |
hail | +1.658 |
packages | +1.628 |
STATE | +1.628 |
Neg logit contributions | |
Conserv | -1.937 |
oros | -1.903 |
Hoo | -1.893 |
� | -1.876 |
Relief | -1.866 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
fetal | +0.811 |
touch | +0.735 |
hail | +0.722 |
STATE | +0.714 |
packages | +0.712 |
Neg logit contributions | |
Conserv | -0.836 |
oros | -0.832 |
Hoo | -0.825 |
� | -0.810 |
Relief | -0.809 |
Token | Story |
Token ID | 11605 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
fetal | +0.630 |
touch | +0.573 |
hail | +0.568 |
packages | +0.559 |
STATE | +0.559 |
Neg logit contributions | |
Conserv | -0.483 |
oros | -0.473 |
Hoo | -0.470 |
� | -0.465 |
Relief | -0.462 |
Token | continues |
Token ID | 4477 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
fetal | +1.272 |
touch | +1.170 |
hail | +1.125 |
presume | +1.109 |
smarter | +1.107 |
Neg logit contributions | |
oros | -1.241 |
Conserv | -1.234 |
Hoo | -1.231 |
Relief | -1.219 |
� | -1.194 |
Token | below |
Token ID | 2174 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
fetal | +1.231 |
touch | +1.072 |
smarter | +1.012 |
hail | +1.008 |
swipe | +0.992 |
Neg logit contributions | |
Conserv | -2.375 |
oros | -2.369 |
Hoo | -2.344 |
Relief | -2.342 |
� | -2.320 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
fetal | +3.525 |
touch | +3.053 |
swipe | +2.862 |
catch | +2.808 |
emphasis | +2.786 |
Neg logit contributions | |
� | -8.087 |
oros | -8.000 |
glers | -7.990 |
Relief | -7.922 |
� | -7.894 |
Token |
|
Token ID | 198 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
fetal | +0.903 |
touch | +0.814 |
hail | +0.799 |
STATE | +0.794 |
WHERE | +0.794 |
Neg logit contributions | |
Conserv | -0.960 |
oros | -0.956 |
Hoo | -0.949 |
Relief | -0.936 |
� | -0.930 |
Token |
|
Token ID | 198 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
fetal | +1.294 |
touch | +1.174 |
hail | +1.145 |
STATE | +1.139 |
WHERE | +1.135 |
Neg logit contributions | |
oros | -1.408 |
Conserv | -1.403 |
Hoo | -1.389 |
� | -1.363 |
Relief | -1.362 |
Token | He |
Token ID | 1544 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
fetal | +1.488 |
touch | +1.357 |
STATE | +1.345 |
WHERE | +1.343 |
hail | +1.340 |
Neg logit contributions | |
Conserv | -1.201 |
oros | -1.175 |
Hoo | -1.170 |
� | -1.154 |
Relief | -1.146 |
Token | participated |
Token ID | 14888 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
fetal | +0.894 |
touch | +0.811 |
hail | +0.802 |
presume | +0.778 |
primates | +0.776 |
Neg logit contributions | |
Conserv | -0.954 |
oros | -0.937 |
Hoo | -0.931 |
� | -0.921 |
Relief | -0.917 |
Token | female |
Token ID | 4048 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
fetal | +0.062 |
touch | +0.056 |
hail | +0.055 |
packages | +0.054 |
STATE | +0.054 |
Neg logit contributions | |
Conserv | -0.061 |
oros | -0.060 |
Hoo | -0.059 |
� | -0.059 |
Relief | -0.059 |
Token | characters |
Token ID | 3435 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
fetal | +0.894 |
touch | +0.792 |
hail | +0.782 |
packages | +0.765 |
STATE | +0.765 |
Neg logit contributions | |
Conserv | -1.134 |
oros | -1.117 |
Hoo | -1.111 |
� | -1.102 |
Relief | -1.097 |
Token | are |
Token ID | 389 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
fetal | +1.201 |
touch | +1.083 |
hail | +1.073 |
presume | +1.041 |
primates | +1.030 |
Neg logit contributions | |
Conserv | -1.413 |
oros | -1.406 |
Hoo | -1.387 |
� | -1.370 |
Relief | -1.369 |
Token | de |
Token ID | 390 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Conserv | +0.727 |
oros | +0.711 |
Hoo | +0.710 |
� | +0.702 |
Relief | +0.698 |
Neg logit contributions | |
fetal | -0.677 |
touch | -0.604 |
hail | -0.601 |
STATE | -0.595 |
packages | -0.593 |
Token | - |
Token ID | 12 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
fetal | +0.685 |
touch | +0.613 |
hail | +0.607 |
packages | +0.596 |
STATE | +0.596 |
Neg logit contributions | |
Conserv | -0.723 |
oros | -0.711 |
Hoo | -0.707 |
� | -0.701 |
Relief | -0.697 |
Token | em |
Token ID | 368 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
fetal | +2.703 |
touch | +2.412 |
hail | +2.364 |
packages | +2.344 |
WHERE | +2.324 |
Neg logit contributions | |
Conserv | -3.306 |
oros | -3.248 |
Hoo | -3.235 |
Relief | -3.206 |
� | -3.201 |
Token | phas |
Token ID | 5902 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
fetal | +3.730 |
touch | +3.142 |
packages | +3.125 |
hail | +3.109 |
auna | +3.100 |
Neg logit contributions | |
Hoo | -7.660 |
Conserv | -7.622 |
� | -7.578 |
oros | -7.551 |
glers | -7.522 |
Token | ized |
Token ID | 1143 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
fetal | +1.630 |
touch | +1.405 |
hail | +1.363 |
primates | +1.325 |
packages | +1.304 |
Neg logit contributions | |
Conserv | -3.317 |
Hoo | -3.277 |
oros | -3.273 |
Relief | -3.244 |
� | -3.235 |
Token | or |
Token ID | 393 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
fetal | +1.509 |
touch | +1.353 |
hail | +1.336 |
packages | +1.302 |
presume | +1.302 |
Neg logit contributions | |
Conserv | -1.685 |
oros | -1.669 |
Hoo | -1.653 |
� | -1.633 |
Relief | -1.627 |
Token | not |
Token ID | 407 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
fetal | +1.722 |
touch | +1.544 |
hail | +1.517 |
presume | +1.487 |
primates | +1.484 |
Neg logit contributions | |
Conserv | -1.925 |
oros | -1.909 |
Hoo | -1.882 |
� | -1.863 |
Relief | -1.856 |
Token | represented |
Token ID | 7997 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
fetal | +0.163 |
touch | +0.145 |
hail | +0.144 |
STATE | +0.142 |
packages | +0.142 |
Neg logit contributions | |
Conserv | -0.178 |
oros | -0.175 |
Hoo | -0.174 |
� | -0.173 |
Relief | -0.172 |
Token | Crim |
Token ID | 9822 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
fetal | +1.779 |
touch | +1.614 |
hail | +1.597 |
STATE | +1.593 |
primates | +1.576 |
Neg logit contributions | |
oros | -1.232 |
Conserv | -1.213 |
� | -1.198 |
Hoo | -1.191 |
glers | -1.191 |
Token | in |
Token ID | 259 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
fetal | +0.607 |
touch | +0.556 |
hail | +0.552 |
packages | +0.544 |
STATE | +0.544 |
Neg logit contributions | |
Conserv | -0.392 |
oros | -0.383 |
Hoo | -0.380 |
� | -0.375 |
Relief | -0.374 |
Token | ology |
Token ID | 1435 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
fetal | +1.913 |
touch | +1.713 |
hail | +1.676 |
primates | +1.661 |
STATE | +1.650 |
Neg logit contributions | |
Conserv | -1.961 |
Hoo | -1.952 |
oros | -1.935 |
� | -1.924 |
)=( | -1.919 |
Token | , |
Token ID | 11 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
fetal | +2.077 |
touch | +1.879 |
hail | +1.846 |
primates | +1.821 |
packages | +1.814 |
Neg logit contributions | |
Conserv | -2.021 |
Hoo | -2.004 |
oros | -1.999 |
� | -1.994 |
glers | -1.971 |
Token | 35 |
Token ID | 3439 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
fetal | +2.482 |
touch | +2.242 |
hail | +2.206 |
STATE | +2.175 |
primates | +2.147 |
Neg logit contributions | |
oros | -2.630 |
avy | -2.565 |
glers | -2.563 |
Conserv | -2.543 |
� | -2.541 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
fetal | +4.309 |
touch | +3.848 |
hail | +3.780 |
STATE | +3.725 |
packages | +3.717 |
Neg logit contributions | |
Conserv | -4.576 |
oros | -4.509 |
Hoo | -4.496 |
� | -4.442 |
Relief | -4.403 |
Token | 177 |
Token ID | 26607 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
fetal | +5.332 |
touch | +4.883 |
hail | +4.757 |
STATE | +4.655 |
swipe | +4.616 |
Neg logit contributions | |
oros | -5.899 |
glers | -5.834 |
Conserv | -5.701 |
avy | -5.676 |
)=( | -5.647 |
Token | - |
Token ID | 532 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
fetal | +3.341 |
touch | +3.021 |
STATE | +2.969 |
WHERE | +2.949 |
hail | +2.926 |
Neg logit contributions | |
oros | -3.772 |
Conserv | -3.760 |
Hoo | -3.734 |
glers | -3.708 |
)=( | -3.704 |
Token | 202 |
Token ID | 22131 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
fetal | +3.034 |
touch | +2.735 |
hail | +2.695 |
STATE | +2.582 |
WHERE | +2.575 |
Neg logit contributions | |
oros | -4.207 |
avy | -4.031 |
glers | -4.021 |
Conserv | -4.005 |
Hoo | -3.990 |
Token | . |
Token ID | 764 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
fetal | +2.198 |
touch | +1.943 |
STATE | +1.904 |
WHERE | +1.868 |
hail | +1.865 |
Neg logit contributions | |
oros | -3.751 |
Conserv | -3.726 |
)=( | -3.726 |
arrang | -3.713 |
Hoo | -3.707 |
Token |
|
Token ID | 198 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
fetal | +2.916 |
touch | +2.623 |
STATE | +2.594 |
WHERE | +2.566 |
hail | +2.534 |
Neg logit contributions | |
arrang | -3.905 |
oros | -3.839 |
Conserv | -3.774 |
Hoo | -3.759 |
glers | -3.750 |
Token |
|
Token ID | 198 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
Conserv | +1.256 |
oros | +1.226 |
Hoo | +1.225 |
Relief | +1.217 |
� | +1.207 |
Neg logit contributions | |
fetal | -1.683 |
touch | -1.529 |
hail | -1.522 |
primates | -1.512 |
presume | -1.510 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Conserv | +0.130 |
oros | +0.128 |
Hoo | +0.127 |
� | +0.126 |
Relief | +0.125 |
Neg logit contributions | |
fetal | -0.134 |
touch | -0.121 |
hail | -0.119 |
STATE | -0.118 |
WHERE | -0.118 |
Token | To |
Token ID | 2514 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
fetal | +0.574 |
touch | +0.524 |
hail | +0.520 |
STATE | +0.514 |
packages | +0.514 |
Neg logit contributions | |
Conserv | -0.402 |
oros | -0.393 |
Hoo | -0.390 |
� | -0.386 |
Relief | -0.383 |
Token | add |
Token ID | 751 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
fetal | +0.507 |
touch | +0.449 |
hail | +0.444 |
STATE | +0.433 |
packages | +0.433 |
Neg logit contributions | |
Conserv | -0.658 |
oros | -0.648 |
Hoo | -0.644 |
� | -0.640 |
Relief | -0.637 |
Token | insult |
Token ID | 13277 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
fetal | +0.331 |
STATE | +0.281 |
touch | +0.281 |
hail | +0.281 |
WHERE | +0.281 |
Neg logit contributions | |
Conserv | -0.530 |
Hoo | -0.522 |
oros | -0.519 |
Relief | -0.517 |
� | -0.516 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
fetal | +2.597 |
touch | +2.363 |
hail | +2.298 |
packages | +2.243 |
primates | +2.234 |
Neg logit contributions | |
Conserv | -3.033 |
oros | -2.982 |
Hoo | -2.956 |
� | -2.925 |
Relief | -2.898 |
Token | injury |
Token ID | 5095 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
fetal | +2.284 |
touch | +1.898 |
hail | +1.773 |
smarter | +1.565 |
primates | +1.557 |
Neg logit contributions | |
oros | -8.864 |
Conserv | -8.776 |
glers | -8.769 |
KK | -8.666 |
)=( | -8.650 |
Token | , |
Token ID | 11 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
Conserv | +1.189 |
Hoo | +1.168 |
oros | +1.164 |
Relief | +1.157 |
� | +1.148 |
Neg logit contributions | |
fetal | -1.316 |
touch | -1.168 |
hail | -1.165 |
STATE | -1.160 |
packages | -1.159 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Conserv | +0.209 |
oros | +0.204 |
Hoo | +0.203 |
� | +0.200 |
Relief | +0.199 |
Neg logit contributions | |
fetal | -0.286 |
touch | -0.260 |
hail | -0.258 |
STATE | -0.255 |
packages | -0.255 |
Token | young |
Token ID | 1862 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
Conserv | +0.591 |
Hoo | +0.577 |
oros | +0.576 |
Relief | +0.572 |
� | +0.570 |
Neg logit contributions | |
fetal | -0.506 |
touch | -0.447 |
hail | -0.444 |
STATE | -0.444 |
packages | -0.440 |
Token | guard |
Token ID | 4860 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
fetal | +0.146 |
touch | +0.129 |
hail | +0.128 |
STATE | +0.127 |
packages | +0.126 |
Neg logit contributions | |
Conserv | -0.165 |
oros | -0.161 |
Hoo | -0.161 |
� | -0.159 |
Relief | -0.159 |
Token |
|
Token ID | 198 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
Conserv | +0.320 |
oros | +0.317 |
Hoo | +0.314 |
� | +0.309 |
Relief | +0.308 |
Neg logit contributions | |
fetal | -0.331 |
touch | -0.299 |
hail | -0.294 |
STATE | -0.293 |
WHERE | -0.292 |
Token | But |
Token ID | 1537 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
fetal | +0.019 |
touch | +0.018 |
hail | +0.017 |
primates | +0.017 |
packages | +0.017 |
Neg logit contributions | |
Conserv | -0.014 |
oros | -0.014 |
Hoo | -0.014 |
� | -0.014 |
Relief | -0.014 |
Token | then |
Token ID | 788 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
fetal | +0.989 |
touch | +0.893 |
hail | +0.880 |
primates | +0.862 |
packages | +0.860 |
Neg logit contributions | |
Conserv | -0.980 |
oros | -0.968 |
Hoo | -0.957 |
� | -0.948 |
Relief | -0.942 |
Token | the |
Token ID | 262 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
fetal | +1.896 |
touch | +1.725 |
hail | +1.690 |
smarter | +1.652 |
primates | +1.650 |
Neg logit contributions | |
Conserv | -1.799 |
oros | -1.789 |
Hoo | -1.750 |
� | -1.743 |
avy | -1.733 |
Token | time |
Token ID | 640 |
Feature activation | -9.98e-02 |
Pos logit contributions | |
fetal | +1.175 |
touch | +1.049 |
hail | +1.030 |
primates | +1.002 |
packages | +1.000 |
Neg logit contributions | |
Conserv | -1.481 |
oros | -1.467 |
Hoo | -1.450 |
� | -1.441 |
avy | -1.428 |
Token | came |
Token ID | 1625 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
fetal | +0.438 |
touch | +0.392 |
hail | +0.391 |
STATE | +0.385 |
packages | +0.384 |
Neg logit contributions | |
Conserv | -0.425 |
oros | -0.416 |
Hoo | -0.415 |
� | -0.411 |
Relief | -0.410 |
Token | to |
Token ID | 284 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
fetal | +4.984 |
touch | +4.530 |
hail | +4.308 |
WHERE | +4.247 |
smarter | +4.227 |
Neg logit contributions | |
Conserv | -6.049 |
oros | -6.043 |
Hoo | -5.972 |
avy | -5.887 |
glers | -5.837 |
Token | actually |
Token ID | 1682 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
fetal | +1.304 |
touch | +1.168 |
hail | +1.135 |
presume | +1.103 |
swipe | +1.092 |
Neg logit contributions | |
Conserv | -1.922 |
oros | -1.910 |
Hoo | -1.890 |
� | -1.871 |
Relief | -1.867 |
Token | start |
Token ID | 923 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
fetal | +0.683 |
touch | +0.606 |
hail | +0.591 |
presume | +0.572 |
primates | +0.568 |
Neg logit contributions | |
Conserv | -1.074 |
oros | -1.062 |
Hoo | -1.056 |
Relief | -1.044 |
� | -1.044 |
Token | grading |
Token ID | 43165 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Conserv | +0.313 |
oros | +0.308 |
Hoo | +0.306 |
� | +0.303 |
Relief | +0.302 |
Neg logit contributions | |
fetal | -0.305 |
touch | -0.274 |
hail | -0.271 |
STATE | -0.267 |
packages | -0.267 |
Token | . |
Token ID | 13 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
fetal | +1.459 |
touch | +1.319 |
hail | +1.295 |
smarter | +1.273 |
primates | +1.271 |
Neg logit contributions | |
Conserv | -1.456 |
oros | -1.442 |
Hoo | -1.424 |
� | -1.406 |
avy | -1.400 |
Token | . |
Token ID | 13 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
fetal | +1.945 |
touch | +1.761 |
hail | +1.737 |
presume | +1.688 |
packages | +1.686 |
Neg logit contributions | |
Conserv | -1.983 |
oros | -1.963 |
Hoo | -1.942 |
� | -1.931 |
)=( | -1.913 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
fetal | +2.107 |
touch | +1.914 |
hail | +1.892 |
packages | +1.858 |
primates | +1.852 |
Neg logit contributions | |
Conserv | -1.777 |
oros | -1.763 |
Hoo | -1.748 |
� | -1.733 |
Relief | -1.714 |
Token |
|
Token ID | 198 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
fetal | +0.430 |
touch | +0.388 |
hail | +0.381 |
packages | +0.377 |
WHERE | +0.377 |
Neg logit contributions | |
Conserv | -0.438 |
oros | -0.435 |
Hoo | -0.431 |
� | -0.425 |
Relief | -0.423 |
Token | Sh |
Token ID | 2484 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
fetal | +0.344 |
touch | +0.312 |
hail | +0.310 |
presume | +0.304 |
primates | +0.303 |
Neg logit contributions | |
Conserv | -0.313 |
oros | -0.311 |
Hoo | -0.305 |
� | -0.303 |
Relief | -0.302 |
Token | ared |
Token ID | 1144 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
fetal | +0.719 |
touch | +0.641 |
hail | +0.636 |
packages | +0.625 |
STATE | +0.621 |
Neg logit contributions | |
Conserv | -0.819 |
Hoo | -0.804 |
oros | -0.797 |
� | -0.795 |
Relief | -0.790 |
Token | < |
Token ID | 27 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
fetal | +0.176 |
touch | +0.161 |
hail | +0.160 |
primates | +0.158 |
packages | +0.158 |
Neg logit contributions | |
Conserv | -0.118 |
oros | -0.115 |
Hoo | -0.114 |
� | -0.113 |
Relief | -0.112 |
Token | ' |
Token ID | 6 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
fetal | +5.097 |
touch | +4.611 |
STATE | +4.504 |
WHERE | +4.496 |
packages | +4.455 |
Neg logit contributions | |
Conserv | -5.767 |
oros | -5.749 |
Hoo | -5.732 |
� | -5.680 |
Relief | -5.627 |
Token | a |
Token ID | 64 |
Feature activation | +2.28e-03 |
Pos logit contributions | |
Conserv | +0.314 |
oros | +0.308 |
Hoo | +0.305 |
� | +0.303 |
Relief | +0.300 |
Neg logit contributions | |
fetal | -0.433 |
touch | -0.395 |
hail | -0.393 |
STATE | -0.387 |
presume | -0.387 |
Token | , |
Token ID | 11 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Conserv | +0.010 |
oros | +0.010 |
Hoo | +0.010 |
� | +0.010 |
Relief | +0.010 |
Neg logit contributions | |
fetal | -0.009 |
touch | -0.008 |
hail | -0.008 |
STATE | -0.008 |
packages | -0.008 |
Token | T |
Token ID | 309 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
fetal | +1.053 |
touch | +0.942 |
hail | +0.933 |
packages | +0.916 |
STATE | +0.916 |
Neg logit contributions | |
Conserv | -1.132 |
oros | -1.113 |
Hoo | -1.106 |
� | -1.097 |
Relief | -1.091 |
Token | > |
Token ID | 29 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
fetal | +0.283 |
touch | +0.250 |
hail | +0.248 |
packages | +0.243 |
STATE | +0.243 |
Neg logit contributions | |
Conserv | -0.357 |
oros | -0.352 |
Hoo | -0.351 |
� | -0.347 |
Relief | -0.345 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
fetal | +1.402 |
touch | +1.274 |
hail | +1.269 |
WHERE | +1.228 |
primates | +1.225 |
Neg logit contributions | |
Conserv | -1.487 |
oros | -1.476 |
� | -1.448 |
Hoo | -1.446 |
Relief | -1.431 |
Token | ( |
Token ID | 357 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Conserv | +0.796 |
Hoo | +0.772 |
oros | +0.769 |
� | +0.763 |
Relief | +0.762 |
Neg logit contributions | |
fetal | -1.028 |
touch | -0.932 |
hail | -0.925 |
primates | -0.914 |
presume | -0.914 |
Token | Photo |
Token ID | 6191 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
Conserv | +0.416 |
oros | +0.404 |
� | +0.401 |
Hoo | +0.401 |
KK | +0.395 |
Neg logit contributions | |
fetal | -0.684 |
touch | -0.625 |
hail | -0.623 |
primates | -0.614 |
presume | -0.614 |
Token | : |
Token ID | 25 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
fetal | +0.250 |
touch | +0.227 |
hail | +0.225 |
packages | +0.223 |
WHERE | +0.222 |
Neg logit contributions | |
Conserv | -0.196 |
oros | -0.191 |
� | -0.190 |
Hoo | -0.189 |
Relief | -0.187 |
Token | Kare |
Token ID | 49396 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
Conserv | +0.711 |
Hoo | +0.691 |
oros | +0.686 |
� | +0.684 |
Relief | +0.679 |
Neg logit contributions | |
fetal | -0.903 |
touch | -0.821 |
hail | -0.815 |
presume | -0.805 |
packages | -0.805 |
Token | em |
Token ID | 368 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Conserv | +0.183 |
oros | +0.180 |
Hoo | +0.179 |
� | +0.178 |
Relief | +0.177 |
Neg logit contributions | |
fetal | -0.092 |
touch | -0.078 |
hail | -0.077 |
STATE | -0.074 |
packages | -0.074 |
Token | El |
Token ID | 2574 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
fetal | +4.254 |
hail | +3.792 |
blast | +3.544 |
RESP | +3.479 |
auna | +3.460 |
Neg logit contributions | |
glers | -6.826 |
)=( | -6.635 |
oros | -6.548 |
� | -6.537 |
� | -6.497 |
Token | g |
Token ID | 70 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
fetal | +3.424 |
touch | +3.125 |
primates | +3.097 |
hail | +3.074 |
presume | +3.073 |
Neg logit contributions | |
)=( | -2.992 |
Conserv | -2.985 |
glers | -2.944 |
oros | -2.918 |
� | -2.906 |
Token | azz |
Token ID | 8101 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Conserv | +0.375 |
oros | +0.367 |
Hoo | +0.364 |
� | +0.361 |
Relief | +0.358 |
Neg logit contributions | |
fetal | -0.499 |
touch | -0.455 |
hail | -0.451 |
packages | -0.444 |
STATE | -0.444 |
Token | ar |
Token ID | 283 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
fetal | +0.994 |
touch | +0.893 |
hail | +0.883 |
packages | +0.868 |
STATE | +0.864 |
Neg logit contributions | |
Conserv | -1.018 |
oros | -0.994 |
Hoo | -0.994 |
� | -0.982 |
Relief | -0.978 |
Token | ) |
Token ID | 8 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
fetal | +1.063 |
touch | +0.957 |
hail | +0.948 |
STATE | +0.935 |
packages | +0.932 |
Neg logit contributions | |
Conserv | -0.998 |
oros | -0.981 |
Hoo | -0.973 |
� | -0.965 |
Relief | -0.962 |
Token | , |
Token ID | 11 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
fetal | +0.220 |
touch | +0.194 |
hail | +0.193 |
packages | +0.191 |
STATE | +0.191 |
Neg logit contributions | |
Conserv | -0.291 |
oros | -0.284 |
Hoo | -0.283 |
� | -0.280 |
Relief | -0.279 |
Token | earth |
Token ID | 4534 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
fetal | +1.878 |
touch | +1.655 |
hail | +1.626 |
primates | +1.602 |
STATE | +1.572 |
Neg logit contributions | |
Conserv | -2.481 |
oros | -2.456 |
Hoo | -2.451 |
� | -2.433 |
Relief | -2.418 |
Token | , |
Token ID | 11 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
fetal | +1.484 |
touch | +1.340 |
hail | +1.320 |
primates | +1.302 |
STATE | +1.295 |
Neg logit contributions | |
Conserv | -1.405 |
oros | -1.387 |
Hoo | -1.382 |
� | -1.372 |
Relief | -1.358 |
Token | and |
Token ID | 290 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
fetal | +4.253 |
touch | +3.845 |
hail | +3.741 |
primates | +3.735 |
blast | +3.623 |
Neg logit contributions | |
oros | -4.077 |
Hoo | -4.065 |
Conserv | -4.061 |
glers | -4.038 |
� | -4.037 |
Token | atmospheric |
Token ID | 20938 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
fetal | +2.691 |
touch | +2.365 |
hail | +2.295 |
primates | +2.277 |
smarter | +2.204 |
Neg logit contributions | |
Conserv | -3.807 |
oros | -3.784 |
Hoo | -3.783 |
� | -3.754 |
Relief | -3.734 |
Token | sciences |
Token ID | 19838 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
fetal | +1.169 |
touch | +1.017 |
hail | +0.993 |
primates | +0.975 |
presume | +0.956 |
Neg logit contributions | |
Conserv | -1.861 |
oros | -1.848 |
Hoo | -1.834 |
� | -1.828 |
glers | -1.816 |
Token | at |
Token ID | 379 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
fetal | +4.644 |
touch | +4.141 |
hail | +4.044 |
primates | +3.947 |
smarter | +3.899 |
Neg logit contributions | |
oros | -6.239 |
glers | -6.155 |
Conserv | -6.123 |
Hoo | -6.097 |
� | -6.096 |
Token | North |
Token ID | 2258 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
fetal | +2.172 |
touch | +1.960 |
hail | +1.934 |
primates | +1.893 |
STATE | +1.885 |
Neg logit contributions | |
oros | -2.102 |
Conserv | -2.078 |
� | -2.049 |
Hoo | -2.043 |
Relief | -2.031 |
Token | Carolina |
Token ID | 5913 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
fetal | +2.281 |
touch | +2.076 |
hail | +2.049 |
STATE | +2.022 |
packages | +2.020 |
Neg logit contributions | |
Conserv | -1.838 |
oros | -1.831 |
� | -1.823 |
Hoo | -1.812 |
glers | -1.781 |
Token | State |
Token ID | 1812 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Conserv | +0.535 |
oros | +0.522 |
Hoo | +0.519 |
� | +0.513 |
Relief | +0.509 |
Neg logit contributions | |
fetal | -0.800 |
touch | -0.733 |
hail | -0.727 |
packages | -0.717 |
STATE | -0.717 |
Token | University |
Token ID | 2059 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
Conserv | +0.780 |
Hoo | +0.750 |
oros | +0.750 |
� | +0.739 |
Relief | +0.733 |
Neg logit contributions | |
fetal | -1.359 |
touch | -1.249 |
hail | -1.244 |
packages | -1.233 |
STATE | -1.228 |
Token | saw |
Token ID | 2497 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
fetal | +0.791 |
touch | +0.712 |
hail | +0.706 |
STATE | +0.692 |
packages | +0.692 |
Neg logit contributions | |
Conserv | -0.756 |
oros | -0.743 |
Hoo | -0.738 |
� | -0.731 |
Relief | -0.727 |
Token | it |
Token ID | 340 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Conserv | +0.363 |
oros | +0.355 |
Hoo | +0.354 |
� | +0.350 |
Relief | +0.349 |
Neg logit contributions | |
fetal | -0.368 |
touch | -0.332 |
hail | -0.330 |
packages | -0.325 |
STATE | -0.325 |
Token | as |
Token ID | 355 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
fetal | +2.251 |
touch | +2.041 |
hail | +2.003 |
smarter | +1.955 |
presume | +1.948 |
Neg logit contributions | |
Conserv | -2.132 |
oros | -2.124 |
Hoo | -2.091 |
)=( | -2.067 |
� | -2.061 |
Token | anti |
Token ID | 3098 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
fetal | +1.631 |
touch | +1.457 |
hail | +1.439 |
STATE | +1.411 |
packages | +1.408 |
Neg logit contributions | |
Conserv | -1.798 |
oros | -1.774 |
Hoo | -1.760 |
� | -1.747 |
Relief | -1.736 |
Token | - |
Token ID | 12 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
fetal | +1.046 |
touch | +0.927 |
STATE | +0.904 |
hail | +0.902 |
packages | +0.900 |
Neg logit contributions | |
Conserv | -1.234 |
Hoo | -1.230 |
oros | -1.220 |
� | -1.213 |
Relief | -1.211 |
Token | gay |
Token ID | 22744 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
fetal | +2.486 |
touch | +2.193 |
packages | +2.145 |
STATE | +2.142 |
WHERE | +2.136 |
Neg logit contributions | |
Conserv | -2.975 |
Hoo | -2.934 |
oros | -2.922 |
� | -2.903 |
Relief | -2.902 |
Token | bigotry |
Token ID | 28849 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
fetal | +5.285 |
touch | +4.742 |
hail | +4.520 |
swipe | +4.462 |
primates | +4.447 |
Neg logit contributions | |
oros | -5.753 |
Conserv | -5.689 |
� | -5.679 |
Hoo | -5.673 |
)=( | -5.648 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
fetal | +2.789 |
touch | +2.500 |
hail | +2.470 |
presume | +2.404 |
smarter | +2.403 |
Neg logit contributions | |
Conserv | -2.924 |
oros | -2.887 |
Hoo | -2.857 |
� | -2.826 |
Relief | -2.806 |
Token |
|
Token ID | 198 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
fetal | +0.753 |
touch | +0.677 |
hail | +0.672 |
STATE | +0.668 |
WHERE | +0.662 |
Neg logit contributions | |
Conserv | -0.672 |
oros | -0.669 |
Hoo | -0.658 |
� | -0.653 |
avy | -0.647 |
Token |
|
Token ID | 198 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
fetal | +0.152 |
touch | +0.137 |
hail | +0.135 |
STATE | +0.134 |
WHERE | +0.133 |
Neg logit contributions | |
Conserv | -0.152 |
oros | -0.151 |
Hoo | -0.149 |
� | -0.147 |
Relief | -0.147 |
Token | But |
Token ID | 1537 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
fetal | +0.317 |
touch | +0.288 |
hail | +0.286 |
packages | +0.281 |
STATE | +0.281 |
Neg logit contributions | |
Conserv | -0.245 |
oros | -0.240 |
Hoo | -0.239 |
� | -0.236 |
Relief | -0.235 |
Token | . |
Token ID | 764 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
fetal | +3.011 |
touch | +2.701 |
hail | +2.662 |
primates | +2.595 |
presume | +2.578 |
Neg logit contributions | |
Conserv | -3.262 |
oros | -3.239 |
Hoo | -3.201 |
� | -3.140 |
)=( | -3.137 |
Token | Child |
Token ID | 5932 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
fetal | +2.317 |
touch | +2.113 |
hail | +2.084 |
STATE | +2.083 |
primates | +2.068 |
Neg logit contributions | |
oros | -1.418 |
Conserv | -1.382 |
� | -1.377 |
glers | -1.372 |
avy | -1.364 |
Token | Development |
Token ID | 7712 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
Conserv | +0.637 |
oros | +0.625 |
Hoo | +0.621 |
� | +0.617 |
Relief | +0.609 |
Neg logit contributions | |
fetal | -0.738 |
touch | -0.668 |
hail | -0.660 |
primates | -0.650 |
packages | -0.649 |
Token | , |
Token ID | 11 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
fetal | +1.688 |
touch | +1.518 |
hail | +1.496 |
STATE | +1.478 |
primates | +1.477 |
Neg logit contributions | |
Conserv | -1.649 |
Hoo | -1.614 |
oros | -1.613 |
� | -1.602 |
Relief | -1.582 |
Token | 68 |
Token ID | 8257 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
fetal | +3.448 |
touch | +3.063 |
RESP | +2.996 |
hail | +2.988 |
STATE | +2.965 |
Neg logit contributions | |
oros | -3.860 |
glers | -3.818 |
avy | -3.772 |
� | -3.705 |
� | -3.688 |
Token | , |
Token ID | 11 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
fetal | +3.376 |
WHERE | +2.933 |
STATE | +2.930 |
touch | +2.913 |
hail | +2.882 |
Neg logit contributions | |
oros | -4.676 |
Conserv | -4.560 |
Hoo | -4.560 |
arrang | -4.544 |
glers | -4.525 |
Token | 6 |
Token ID | 718 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
fetal | +5.080 |
touch | +4.642 |
hail | +4.532 |
STATE | +4.461 |
swipe | +4.382 |
Neg logit contributions | |
oros | -5.629 |
glers | -5.540 |
Conserv | -5.446 |
avy | -5.421 |
)=( | -5.373 |
Token | 65 |
Token ID | 2996 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
fetal | +3.329 |
touch | +3.049 |
STATE | +2.998 |
WHERE | +2.975 |
hail | +2.974 |
Neg logit contributions | |
oros | -3.336 |
Conserv | -3.332 |
Hoo | -3.277 |
glers | -3.225 |
)=( | -3.224 |
Token | - |
Token ID | 532 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
fetal | +3.715 |
touch | +3.401 |
hail | +3.271 |
STATE | +3.264 |
WHERE | +3.250 |
Neg logit contributions | |
arrang | -4.612 |
oros | -4.590 |
)=( | -4.586 |
glers | -4.559 |
Conserv | -4.527 |
Token | 6 |
Token ID | 718 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
fetal | +2.895 |
hail | +2.590 |
touch | +2.583 |
presume | +2.524 |
smarter | +2.498 |
Neg logit contributions | |
oros | -3.000 |
Conserv | -2.955 |
Hoo | -2.860 |
avy | -2.853 |
glers | -2.838 |
Token | 75 |
Token ID | 2425 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
fetal | +1.251 |
WHERE | +1.155 |
touch | +1.150 |
STATE | +1.138 |
hail | +1.119 |
Neg logit contributions | |
Conserv | -1.229 |
oros | -1.223 |
Hoo | -1.204 |
Relief | -1.187 |
glers | -1.176 |
Token | т |
Token ID | 20375 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
fetal | +0.035 |
touch | +0.033 |
hail | +0.032 |
packages | +0.032 |
STATE | +0.032 |
Neg logit contributions | |
Conserv | -0.016 |
oros | -0.015 |
Hoo | -0.015 |
� | -0.015 |
Relief | -0.015 |
Token | ь |
Token ID | 45367 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Conserv | +0.769 |
oros | +0.760 |
Hoo | +0.749 |
� | +0.743 |
Relief | +0.731 |
Neg logit contributions | |
fetal | -1.222 |
hail | -1.112 |
touch | -1.112 |
primates | -1.099 |
STATE | -1.097 |
Token | � |
Token ID | 12466 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Conserv | +0.461 |
oros | +0.449 |
Hoo | +0.447 |
� | +0.444 |
Relief | +0.437 |
Neg logit contributions | |
fetal | -0.825 |
touch | -0.758 |
hail | -0.755 |
packages | -0.746 |
primates | -0.745 |
Token | � |
Token ID | 111 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Conserv | +0.312 |
oros | +0.304 |
Hoo | +0.301 |
� | +0.297 |
Relief | +0.295 |
Neg logit contributions | |
fetal | -0.562 |
touch | -0.517 |
hail | -0.514 |
packages | -0.507 |
STATE | -0.507 |
Token | и |
Token ID | 18849 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Conserv | +0.779 |
oros | +0.763 |
Hoo | +0.750 |
� | +0.744 |
avy | +0.726 |
Neg logit contributions | |
fetal | -1.682 |
touch | -1.550 |
hail | -1.543 |
primates | -1.526 |
packages | -1.525 |
Token | � |
Token ID | 140 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
fetal | +2.220 |
touch | +2.075 |
hail | +2.057 |
STATE | +2.038 |
WHERE | +2.038 |
Neg logit contributions | |
Conserv | -0.706 |
oros | -0.674 |
Hoo | -0.670 |
Relief | -0.654 |
� | -0.649 |
Token | � |
Token ID | 109 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
Conserv | +2.108 |
oros | +2.056 |
Hoo | +1.981 |
� | +1.975 |
avy | +1.963 |
Neg logit contributions | |
fetal | -5.757 |
primates | -5.306 |
touch | -5.295 |
hail | -5.285 |
WHERE | -5.254 |
Token | е |
Token ID | 16843 |
Feature activation | +6.71e-03 |
Pos logit contributions | |
Conserv | +1.085 |
oros | +1.065 |
� | +1.051 |
Hoo | +1.050 |
Relief | +1.028 |
Neg logit contributions | |
fetal | -1.732 |
touch | -1.585 |
hail | -1.578 |
packages | -1.563 |
primates | -1.559 |
Token | л |
Token ID | 30143 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
Conserv | +0.017 |
oros | +0.016 |
Hoo | +0.016 |
� | +0.016 |
Relief | +0.015 |
Neg logit contributions | |
fetal | -0.042 |
touch | -0.038 |
hail | -0.038 |
primates | -0.038 |
packages | -0.038 |
Token | ь |
Token ID | 45367 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Conserv | +0.049 |
oros | +0.048 |
Hoo | +0.048 |
� | +0.047 |
Relief | +0.047 |
Neg logit contributions | |
fetal | -0.057 |
touch | -0.052 |
hail | -0.052 |
packages | -0.051 |
primates | -0.051 |
Token | � |
Token ID | 12466 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Conserv | +1.779 |
oros | +1.740 |
� | +1.738 |
Hoo | +1.736 |
Relief | +1.708 |
Neg logit contributions | |
fetal | -2.245 |
touch | -2.028 |
hail | -2.022 |
packages | -2.001 |
primates | -2.001 |
Token | ) |
Token ID | 8 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
fetal | +0.465 |
touch | +0.418 |
hail | +0.415 |
STATE | +0.410 |
primates | +0.410 |
Neg logit contributions | |
Conserv | -0.425 |
oros | -0.415 |
Hoo | -0.413 |
� | -0.410 |
Relief | -0.409 |
Token |
|
Token ID | 198 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
fetal | +0.255 |
touch | +0.231 |
hail | +0.231 |
primates | +0.226 |
presume | +0.226 |
Neg logit contributions | |
Conserv | -0.215 |
oros | -0.209 |
Hoo | -0.208 |
Relief | -0.207 |
� | -0.206 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Conserv | +0.317 |
oros | +0.314 |
Hoo | +0.312 |
� | +0.307 |
Relief | +0.306 |
Neg logit contributions | |
fetal | -0.329 |
touch | -0.297 |
hail | -0.292 |
STATE | -0.290 |
WHERE | -0.290 |
Token | The |
Token ID | 464 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
fetal | +1.027 |
touch | +0.937 |
STATE | +0.927 |
hail | +0.926 |
WHERE | +0.924 |
Neg logit contributions | |
Conserv | -0.779 |
oros | -0.762 |
Hoo | -0.759 |
� | -0.748 |
Relief | -0.744 |
Token | Washington |
Token ID | 2669 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
fetal | +0.364 |
touch | +0.328 |
hail | +0.325 |
packages | +0.319 |
STATE | +0.318 |
Neg logit contributions | |
Conserv | -0.353 |
oros | -0.347 |
Hoo | -0.344 |
� | -0.341 |
Relief | -0.339 |
Token | Redskins |
Token ID | 22038 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
fetal | +2.157 |
touch | +1.985 |
hail | +1.957 |
packages | +1.922 |
primates | +1.910 |
Neg logit contributions | |
oros | -1.701 |
Conserv | -1.691 |
Hoo | -1.644 |
� | -1.644 |
)=( | -1.620 |
Token | on |
Token ID | 319 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Conserv | +2.770 |
Hoo | +2.705 |
Relief | +2.698 |
� | +2.681 |
oros | +2.654 |
Neg logit contributions | |
fetal | -2.766 |
STATE | -2.453 |
packages | -2.445 |
WHERE | -2.443 |
touch | -2.442 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Conserv | +0.442 |
Hoo | +0.431 |
oros | +0.429 |
� | +0.423 |
Relief | +0.423 |
Neg logit contributions | |
fetal | -0.654 |
touch | -0.596 |
hail | -0.594 |
STATE | -0.589 |
packages | -0.587 |
Token | held |
Token ID | 2714 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
fetal | +0.830 |
touch | +0.752 |
hail | +0.746 |
presume | +0.725 |
primates | +0.723 |
Neg logit contributions | |
Conserv | -0.811 |
oros | -0.801 |
Hoo | -0.790 |
� | -0.781 |
Relief | -0.777 |
Token | their |
Token ID | 511 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
fetal | +0.187 |
touch | +0.167 |
hail | +0.166 |
STATE | +0.164 |
packages | +0.163 |
Neg logit contributions | |
Conserv | -0.197 |
Hoo | -0.193 |
oros | -0.193 |
� | -0.190 |
Relief | -0.190 |
Token | second |
Token ID | 1218 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
fetal | +1.433 |
touch | +1.292 |
hail | +1.275 |
primates | +1.249 |
STATE | +1.246 |
Neg logit contributions | |
Conserv | -1.432 |
oros | -1.419 |
Hoo | -1.399 |
� | -1.390 |
Relief | -1.376 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
Conserv | +0.098 |
oros | +0.096 |
Hoo | +0.096 |
� | +0.095 |
Relief | +0.094 |
Neg logit contributions | |
fetal | -0.105 |
touch | -0.095 |
hail | -0.094 |
packages | -0.093 |
STATE | -0.093 |
Token | latest |
Token ID | 3452 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Conserv | +0.086 |
oros | +0.084 |
Hoo | +0.084 |
� | +0.083 |
Relief | +0.082 |
Neg logit contributions | |
fetal | -0.080 |
touch | -0.071 |
hail | -0.071 |
STATE | -0.070 |
packages | -0.070 |
Token | proposal |
Token ID | 6961 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
fetal | +1.243 |
touch | +1.127 |
hail | +1.118 |
presume | +1.080 |
primates | +1.078 |
Neg logit contributions | |
Conserv | -1.258 |
oros | -1.252 |
� | -1.224 |
Hoo | -1.224 |
Relief | -1.207 |
Token | for |
Token ID | 329 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
fetal | +1.281 |
touch | +1.148 |
hail | +1.140 |
packages | +1.110 |
STATE | +1.109 |
Neg logit contributions | |
Conserv | -1.405 |
oros | -1.385 |
Hoo | -1.370 |
� | -1.361 |
Relief | -1.351 |
Token | financial |
Token ID | 3176 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
fetal | +2.070 |
touch | +1.882 |
hail | +1.858 |
smarter | +1.804 |
primates | +1.796 |
Neg logit contributions | |
oros | -2.116 |
Conserv | -2.103 |
� | -2.051 |
Hoo | -2.045 |
avy | -2.032 |
Token | fair |
Token ID | 3148 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
fetal | +0.453 |
touch | +0.403 |
hail | +0.400 |
packages | +0.393 |
STATE | +0.393 |
Neg logit contributions | |
Conserv | -0.505 |
oros | -0.495 |
Hoo | -0.493 |
� | -0.489 |
Relief | -0.487 |
Token | play |
Token ID | 711 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Conserv | +3.498 |
Hoo | +3.432 |
Relief | +3.391 |
Cream | +3.356 |
� | +3.349 |
Neg logit contributions | |
fetal | -2.296 |
WHERE | -1.967 |
STATE | -1.954 |
packages | -1.934 |
auna | -1.918 |
Token | in |
Token ID | 287 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
fetal | +0.652 |
touch | +0.587 |
hail | +0.581 |
packages | +0.570 |
STATE | +0.569 |
Neg logit contributions | |
Conserv | -0.656 |
oros | -0.646 |
Hoo | -0.640 |
� | -0.635 |
Relief | -0.630 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
fetal | +1.319 |
touch | +1.191 |
hail | +1.176 |
primates | +1.147 |
STATE | +1.146 |
Neg logit contributions | |
Conserv | -1.376 |
oros | -1.362 |
Hoo | -1.343 |
� | -1.338 |
Relief | -1.324 |
Token | Premier |
Token ID | 9952 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
fetal | +0.599 |
touch | +0.533 |
hail | +0.527 |
STATE | +0.514 |
primates | +0.514 |
Neg logit contributions | |
Conserv | -0.719 |
oros | -0.710 |
Hoo | -0.704 |
� | -0.699 |
Relief | -0.694 |
Token | League |
Token ID | 4041 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
fetal | +0.597 |
touch | +0.560 |
hail | +0.549 |
smarter | +0.538 |
WHERE | +0.538 |
Neg logit contributions | |
oros | -0.358 |
� | -0.349 |
Conserv | -0.343 |
avy | -0.340 |
Hoo | -0.338 |
Token | ifully |
Token ID | 17049 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
fetal | +0.360 |
touch | +0.326 |
hail | +0.323 |
packages | +0.317 |
STATE | +0.317 |
Neg logit contributions | |
Conserv | -0.323 |
oros | -0.317 |
Hoo | -0.315 |
� | -0.312 |
Relief | -0.310 |
Token | Paid |
Token ID | 47355 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
Conserv | +0.138 |
oros | +0.135 |
Hoo | +0.134 |
� | +0.133 |
Relief | +0.132 |
Neg logit contributions | |
fetal | -0.171 |
touch | -0.155 |
hail | -0.154 |
packages | -0.151 |
STATE | -0.151 |
Token | Hom |
Token ID | 8074 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
fetal | +0.345 |
touch | +0.304 |
hail | +0.301 |
STATE | +0.295 |
packages | +0.295 |
Neg logit contributions | |
Conserv | -0.458 |
oros | -0.449 |
Hoo | -0.448 |
� | -0.445 |
Relief | -0.443 |
Token | age |
Token ID | 496 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
fetal | +0.555 |
touch | +0.509 |
hail | +0.504 |
packages | +0.497 |
STATE | +0.497 |
Neg logit contributions | |
Conserv | -0.378 |
oros | -0.370 |
Hoo | -0.367 |
� | -0.363 |
Relief | -0.360 |
Token | To |
Token ID | 1675 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Conserv | +1.173 |
� | +1.138 |
Hoo | +1.138 |
Relief | +1.135 |
oros | +1.131 |
Neg logit contributions | |
fetal | -1.231 |
touch | -1.100 |
hail | -1.096 |
STATE | -1.089 |
primates | -1.081 |
Token | Lost |
Token ID | 9164 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
fetal | +0.609 |
touch | +0.554 |
hail | +0.549 |
WHERE | +0.539 |
packages | +0.538 |
Neg logit contributions | |
Conserv | -0.477 |
oros | -0.475 |
Hoo | -0.466 |
avy | -0.461 |
� | -0.459 |
Token | Leader |
Token ID | 10540 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
Conserv | +2.512 |
Hoo | +2.419 |
� | +2.393 |
Relief | +2.379 |
oros | +2.370 |
Neg logit contributions | |
fetal | -3.234 |
hail | -2.960 |
touch | -2.929 |
STATE | -2.925 |
packages | -2.917 |
Token | O |
Token ID | 440 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Conserv | +1.770 |
Hoo | +1.725 |
oros | +1.718 |
� | +1.712 |
Relief | +1.691 |
Neg logit contributions | |
fetal | -2.228 |
touch | -2.022 |
STATE | -2.007 |
hail | -2.003 |
packages | -1.990 |
Token | der |
Token ID | 1082 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
fetal | +0.570 |
touch | +0.482 |
hail | +0.478 |
packages | +0.465 |
STATE | +0.464 |
Neg logit contributions | |
Conserv | -1.158 |
Hoo | -1.133 |
oros | -1.132 |
Relief | -1.125 |
� | -1.125 |
Token | us |
Token ID | 385 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
fetal | +0.156 |
touch | +0.139 |
hail | +0.137 |
STATE | +0.134 |
auna | +0.134 |
Neg logit contributions | |
Conserv | -0.237 |
Hoo | -0.234 |
� | -0.232 |
oros | -0.232 |
Relief | -0.231 |
Token | Ur |
Token ID | 8799 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
Conserv | +0.860 |
Hoo | +0.840 |
oros | +0.837 |
� | +0.834 |
Relief | +0.829 |
Neg logit contributions | |
fetal | -1.067 |
touch | -0.968 |
hail | -0.958 |
STATE | -0.951 |
packages | -0.950 |
Token | would |
Token ID | 561 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Conserv | +0.287 |
oros | +0.282 |
Hoo | +0.280 |
� | +0.277 |
Relief | +0.276 |
Neg logit contributions | |
fetal | -0.313 |
touch | -0.282 |
hail | -0.280 |
packages | -0.275 |
STATE | -0.275 |
Token | write |
Token ID | 3551 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
fetal | +0.779 |
touch | +0.699 |
hail | +0.688 |
presume | +0.666 |
primates | +0.657 |
Neg logit contributions | |
Conserv | -1.119 |
oros | -1.103 |
Hoo | -1.095 |
� | -1.088 |
Relief | -1.085 |
Token | a |
Token ID | 257 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
fetal | +2.123 |
touch | +1.931 |
hail | +1.898 |
smarter | +1.857 |
presume | +1.847 |
Neg logit contributions | |
oros | -2.085 |
Conserv | -2.071 |
� | -2.040 |
Hoo | -2.007 |
)=( | -2.005 |
Token | half |
Token ID | 2063 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Conserv | +1.006 |
Hoo | +0.983 |
oros | +0.980 |
� | +0.970 |
Relief | +0.968 |
Neg logit contributions | |
fetal | -0.945 |
touch | -0.843 |
hail | -0.836 |
packages | -0.833 |
STATE | -0.831 |
Token | dozen |
Token ID | 8667 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
Conserv | +0.806 |
oros | +0.790 |
Hoo | +0.788 |
Relief | +0.779 |
� | +0.776 |
Neg logit contributions | |
fetal | -0.825 |
touch | -0.734 |
hail | -0.732 |
packages | -0.728 |
WHERE | -0.727 |
Token | of |
Token ID | 286 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
Conserv | +2.438 |
Hoo | +2.372 |
Relief | +2.330 |
Cream | +2.314 |
oros | +2.300 |
Neg logit contributions | |
fetal | -2.929 |
STATE | -2.682 |
WHERE | -2.650 |
auna | -2.636 |
packages | -2.634 |
Token | his |
Token ID | 465 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Conserv | +3.035 |
Hoo | +3.012 |
Cream | +2.927 |
Relief | +2.914 |
oros | +2.876 |
Neg logit contributions | |
fetal | -3.627 |
WHERE | -3.262 |
hail | -3.259 |
STATE | -3.258 |
touch | -3.245 |
Token | most |
Token ID | 749 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Conserv | +0.929 |
Hoo | +0.910 |
oros | +0.908 |
Relief | +0.898 |
� | +0.896 |
Neg logit contributions | |
fetal | -0.901 |
touch | -0.805 |
hail | -0.801 |
STATE | -0.794 |
packages | -0.791 |
Token | memorable |
Token ID | 18078 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
fetal | +0.596 |
touch | +0.527 |
hail | +0.520 |
STATE | +0.508 |
packages | +0.507 |
Neg logit contributions | |
Conserv | -0.781 |
oros | -0.770 |
Hoo | -0.765 |
� | -0.759 |
Relief | -0.755 |
Token | songs |
Token ID | 7259 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
fetal | +0.616 |
touch | +0.562 |
hail | +0.555 |
packages | +0.544 |
primates | +0.543 |
Neg logit contributions | |
Conserv | -0.481 |
oros | -0.475 |
Hoo | -0.467 |
� | -0.466 |
Relief | -0.459 |
Token | , |
Token ID | 11 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
Conserv | +0.246 |
oros | +0.240 |
Hoo | +0.240 |
� | +0.237 |
Relief | +0.237 |
Neg logit contributions | |
fetal | -0.254 |
touch | -0.228 |
hail | -0.226 |
STATE | -0.224 |
packages | -0.224 |
Token | look |
Token ID | 804 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
fetal | +1.878 |
touch | +1.704 |
hail | +1.687 |
primates | +1.642 |
presume | +1.637 |
Neg logit contributions | |
Conserv | -1.860 |
oros | -1.850 |
Hoo | -1.818 |
avy | -1.803 |
Relief | -1.801 |
Token | at |
Token ID | 379 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
fetal | +1.362 |
touch | +1.223 |
hail | +1.210 |
packages | +1.187 |
STATE | +1.187 |
Neg logit contributions | |
Conserv | -1.390 |
oros | -1.366 |
Hoo | -1.357 |
� | -1.344 |
Relief | -1.338 |
Token | these |
Token ID | 777 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
fetal | +0.425 |
touch | +0.383 |
hail | +0.379 |
primates | +0.372 |
packages | +0.372 |
Neg logit contributions | |
Conserv | -0.406 |
oros | -0.400 |
Hoo | -0.397 |
� | -0.393 |
Relief | -0.391 |
Token | Asians |
Token ID | 30852 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Conserv | +1.005 |
oros | +0.983 |
Hoo | +0.980 |
� | +0.972 |
Relief | +0.967 |
Neg logit contributions | |
fetal | -0.870 |
touch | -0.772 |
hail | -0.766 |
STATE | -0.760 |
packages | -0.759 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-03 |
Pos logit contributions | |
fetal | +0.503 |
touch | +0.454 |
hail | +0.450 |
STATE | +0.440 |
packages | +0.440 |
Neg logit contributions | |
Conserv | -0.488 |
oros | -0.480 |
Hoo | -0.477 |
� | -0.471 |
Relief | -0.470 |
Token | They |
Token ID | 1119 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
Conserv | +0.010 |
oros | +0.009 |
Hoo | +0.009 |
� | +0.009 |
Relief | +0.009 |
Neg logit contributions | |
fetal | -0.011 |
touch | -0.010 |
hail | -0.010 |
STATE | -0.010 |
packages | -0.010 |
Token | can |
Token ID | 460 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
Conserv | +0.158 |
oros | +0.155 |
Hoo | +0.154 |
� | +0.152 |
Relief | +0.152 |
Neg logit contributions | |
fetal | -0.167 |
touch | -0.151 |
hail | -0.150 |
STATE | -0.147 |
packages | -0.147 |
Token | � |
Token ID | 447 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
fetal | +0.265 |
touch | +0.230 |
hail | +0.229 |
packages | +0.226 |
WHERE | +0.226 |
Neg logit contributions | |
Conserv | -0.380 |
oros | -0.374 |
Hoo | -0.371 |
� | -0.370 |
Relief | -0.366 |
Token | � |
Token ID | 247 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
Conserv | +0.840 |
oros | +0.819 |
Hoo | +0.814 |
� | +0.803 |
Relief | +0.796 |
Neg logit contributions | |
fetal | -1.558 |
touch | -1.436 |
hail | -1.430 |
packages | -1.409 |
STATE | -1.408 |
Token | t |
Token ID | 83 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Conserv | +0.007 |
oros | +0.007 |
Hoo | +0.007 |
� | +0.007 |
Relief | +0.007 |
Neg logit contributions | |
fetal | -0.006 |
touch | -0.006 |
hail | -0.006 |
STATE | -0.006 |
packages | -0.006 |
Token | take |
Token ID | 1011 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Conserv | +1.186 |
oros | +1.160 |
� | +1.156 |
Hoo | +1.153 |
Relief | +1.135 |
Neg logit contributions | |
fetal | -0.881 |
WHERE | -0.767 |
packages | -0.765 |
STATE | -0.764 |
hail | -0.761 |
Token | occur |
Token ID | 3051 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
Conserv | +1.880 |
� | +1.828 |
oros | +1.820 |
Hoo | +1.815 |
Relief | +1.797 |
Neg logit contributions | |
fetal | -1.771 |
packages | -1.594 |
WHERE | -1.587 |
STATE | -1.586 |
hail | -1.567 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Conserv | +1.211 |
oros | +1.182 |
� | +1.173 |
Hoo | +1.173 |
Relief | +1.160 |
Neg logit contributions | |
fetal | -1.285 |
hail | -1.152 |
touch | -1.152 |
STATE | -1.138 |
packages | -1.135 |
Token | Brief |
Token ID | 22821 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Conserv | +0.528 |
oros | +0.524 |
Hoo | +0.516 |
� | +0.511 |
Relief | +0.508 |
Neg logit contributions | |
fetal | -0.651 |
touch | -0.592 |
hail | -0.585 |
STATE | -0.578 |
WHERE | -0.577 |
Token | ly |
Token ID | 306 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
fetal | +0.498 |
touch | +0.426 |
hail | +0.417 |
primates | +0.405 |
packages | +0.404 |
Neg logit contributions | |
Conserv | -0.948 |
oros | -0.938 |
Hoo | -0.933 |
� | -0.927 |
Relief | -0.921 |
Token | , |
Token ID | 11 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Conserv | +1.428 |
oros | +1.391 |
� | +1.387 |
Hoo | +1.384 |
Relief | +1.358 |
Neg logit contributions | |
fetal | -1.582 |
hail | -1.420 |
packages | -1.417 |
touch | -1.414 |
STATE | -1.410 |
Token | his |
Token ID | 465 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
Conserv | +1.955 |
oros | +1.895 |
Hoo | +1.893 |
� | +1.883 |
Relief | +1.859 |
Neg logit contributions | |
fetal | -2.072 |
hail | -1.860 |
packages | -1.855 |
touch | -1.854 |
STATE | -1.851 |
Token | claim |
Token ID | 1624 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
fetal | +0.155 |
touch | +0.137 |
hail | +0.136 |
packages | +0.133 |
STATE | +0.133 |
Neg logit contributions | |
Conserv | -0.197 |
oros | -0.194 |
Hoo | -0.193 |
� | -0.191 |
Relief | -0.190 |
Token | is |
Token ID | 318 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Conserv | +0.690 |
oros | +0.677 |
� | +0.671 |
Hoo | +0.668 |
Relief | +0.662 |
Neg logit contributions | |
fetal | -0.708 |
touch | -0.633 |
hail | -0.630 |
STATE | -0.624 |
packages | -0.622 |
Token | this |
Token ID | 428 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
fetal | +0.652 |
touch | +0.589 |
hail | +0.582 |
STATE | +0.572 |
packages | +0.571 |
Neg logit contributions | |
Conserv | -0.598 |
oros | -0.588 |
Hoo | -0.585 |
� | -0.577 |
Relief | -0.575 |
Token | : |
Token ID | 25 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
fetal | +1.438 |
touch | +1.304 |
hail | +1.289 |
STATE | +1.267 |
packages | +1.265 |
Neg logit contributions | |
Conserv | -1.252 |
oros | -1.231 |
Hoo | -1.224 |
� | -1.207 |
Relief | -1.202 |
Token | modern |
Token ID | 3660 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
Conserv | +0.306 |
oros | +0.300 |
Hoo | +0.298 |
� | +0.296 |
Relief | +0.294 |
Neg logit contributions | |
fetal | -0.333 |
touch | -0.300 |
hail | -0.298 |
packages | -0.293 |
STATE | -0.293 |
Token | Soccer |
Token ID | 15872 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
Conserv | +1.611 |
Hoo | +1.555 |
Relief | +1.541 |
oros | +1.539 |
� | +1.530 |
Neg logit contributions | |
fetal | -2.346 |
touch | -2.125 |
hail | -2.118 |
WHERE | -2.114 |
STATE | -2.109 |
Token | until |
Token ID | 1566 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
fetal | +0.315 |
touch | +0.286 |
hail | +0.282 |
primates | +0.275 |
STATE | +0.274 |
Neg logit contributions | |
Conserv | -0.318 |
oros | -0.316 |
Hoo | -0.312 |
� | -0.311 |
Relief | -0.305 |
Token | 35 |
Token ID | 3439 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
fetal | +1.032 |
touch | +0.936 |
hail | +0.922 |
primates | +0.898 |
smarter | +0.896 |
Neg logit contributions | |
Conserv | -1.018 |
oros | -1.016 |
Hoo | -0.997 |
� | -0.995 |
)=( | -0.988 |
Token | , |
Token ID | 11 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
fetal | +0.109 |
touch | +0.097 |
hail | +0.096 |
STATE | +0.094 |
packages | +0.094 |
Neg logit contributions | |
Conserv | -0.121 |
oros | -0.119 |
Hoo | -0.119 |
� | -0.118 |
Relief | -0.117 |
Token | an |
Token ID | 281 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
fetal | +0.200 |
touch | +0.179 |
hail | +0.177 |
STATE | +0.175 |
packages | +0.174 |
Neg logit contributions | |
Conserv | -0.216 |
oros | -0.211 |
Hoo | -0.211 |
� | -0.209 |
Relief | -0.208 |
Token | age |
Token ID | 2479 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
Conserv | +0.305 |
oros | +0.300 |
Hoo | +0.299 |
Relief | +0.298 |
� | +0.297 |
Neg logit contributions | |
fetal | -0.224 |
touch | -0.194 |
hail | -0.194 |
packages | -0.194 |
STATE | -0.193 |
Token | that |
Token ID | 326 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Conserv | +2.660 |
Hoo | +2.594 |
Relief | +2.567 |
� | +2.541 |
oros | +2.538 |
Neg logit contributions | |
fetal | -2.667 |
packages | -2.404 |
STATE | -2.380 |
auna | -2.359 |
presume | -2.359 |
Token | usually |
Token ID | 3221 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
Conserv | +0.781 |
Hoo | +0.764 |
oros | +0.760 |
� | +0.754 |
Relief | +0.750 |
Neg logit contributions | |
fetal | -0.773 |
touch | -0.692 |
hail | -0.688 |
STATE | -0.683 |
packages | -0.683 |
Token | signals |
Token ID | 10425 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Conserv | +0.182 |
oros | +0.179 |
Hoo | +0.178 |
� | +0.176 |
Relief | +0.175 |
Neg logit contributions | |
fetal | -0.179 |
touch | -0.161 |
hail | -0.159 |
primates | -0.156 |
packages | -0.156 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Conserv | +0.483 |
Hoo | +0.472 |
oros | +0.466 |
Relief | +0.464 |
� | +0.464 |
Neg logit contributions | |
fetal | -0.455 |
STATE | -0.406 |
packages | -0.405 |
touch | -0.405 |
hail | -0.404 |
Token | end |
Token ID | 886 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
Conserv | +0.987 |
Hoo | +0.966 |
oros | +0.957 |
Relief | +0.955 |
� | +0.954 |
Neg logit contributions | |
fetal | -0.689 |
packages | -0.599 |
STATE | -0.599 |
touch | -0.598 |
hail | -0.597 |
Token | on |
Token ID | 319 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
fetal | +1.586 |
touch | +1.439 |
hail | +1.425 |
primates | +1.396 |
packages | +1.395 |
Neg logit contributions | |
Conserv | -1.447 |
oros | -1.423 |
Hoo | -1.402 |
� | -1.397 |
Relief | -1.393 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Conserv | +2.002 |
Hoo | +1.956 |
oros | +1.929 |
� | +1.929 |
Relief | +1.924 |
Neg logit contributions | |
fetal | -2.218 |
STATE | -1.996 |
hail | -1.994 |
touch | -1.990 |
packages | -1.977 |
Token |
|
Token ID | 198 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
Conserv | +0.894 |
oros | +0.874 |
Hoo | +0.872 |
� | +0.865 |
Relief | +0.859 |
Neg logit contributions | |
fetal | -1.108 |
touch | -1.001 |
hail | -0.997 |
packages | -0.986 |
STATE | -0.986 |
Token |
|
Token ID | 198 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
fetal | +0.356 |
touch | +0.322 |
hail | +0.316 |
STATE | +0.314 |
WHERE | +0.313 |
Neg logit contributions | |
Conserv | -0.354 |
oros | -0.351 |
Hoo | -0.348 |
� | -0.343 |
Relief | -0.342 |
Token | Stephen |
Token ID | 24920 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
fetal | +0.120 |
touch | +0.109 |
hail | +0.108 |
primates | +0.106 |
presume | +0.106 |
Neg logit contributions | |
Conserv | -0.091 |
oros | -0.090 |
Hoo | -0.089 |
� | -0.088 |
Relief | -0.087 |
Token | on |
Token ID | 319 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
fetal | +0.791 |
touch | +0.705 |
hail | +0.698 |
packages | +0.684 |
STATE | +0.684 |
Neg logit contributions | |
Conserv | -0.903 |
oros | -0.888 |
Hoo | -0.884 |
� | -0.876 |
Relief | -0.872 |
Token | Google |
Token ID | 3012 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Conserv | +1.679 |
Hoo | +1.637 |
� | +1.605 |
oros | +1.604 |
Relief | +1.602 |
Neg logit contributions | |
fetal | -2.706 |
hail | -2.461 |
touch | -2.458 |
STATE | -2.447 |
packages | -2.445 |
Token | + |
Token ID | 10 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Conserv | +1.650 |
Hoo | +1.637 |
� | +1.596 |
oros | +1.594 |
Relief | +1.592 |
Neg logit contributions | |
fetal | -2.014 |
hail | -1.808 |
packages | -1.797 |
touch | -1.796 |
primates | -1.788 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Conserv | +0.545 |
Hoo | +0.527 |
oros | +0.526 |
� | +0.525 |
Relief | +0.520 |
Neg logit contributions | |
fetal | -0.730 |
hail | -0.657 |
touch | -0.657 |
packages | -0.654 |
primates | -0.651 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
fetal | +0.555 |
touch | +0.502 |
hail | +0.493 |
STATE | +0.489 |
WHERE | +0.488 |
Neg logit contributions | |
Conserv | -0.562 |
oros | -0.559 |
Hoo | -0.553 |
� | -0.546 |
Relief | -0.544 |
Token | Follow |
Token ID | 7155 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
fetal | +0.136 |
touch | +0.122 |
hail | +0.122 |
primates | +0.119 |
presume | +0.119 |
Neg logit contributions | |
Conserv | -0.124 |
oros | -0.122 |
Hoo | -0.121 |
� | -0.121 |
Relief | -0.120 |
Token | you |
Token ID | 345 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
Conserv | +0.195 |
oros | +0.191 |
Hoo | +0.190 |
� | +0.189 |
Relief | +0.188 |
Neg logit contributions | |
fetal | -0.162 |
touch | -0.143 |
hail | -0.142 |
STATE | -0.140 |
packages | -0.140 |
Token | ? |
Token ID | 30 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Conserv | +0.063 |
oros | +0.062 |
Hoo | +0.062 |
� | +0.061 |
Relief | +0.061 |
Neg logit contributions | |
fetal | -0.056 |
touch | -0.050 |
hail | -0.049 |
packages | -0.048 |
STATE | -0.048 |
Token | � |
Token ID | 447 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
fetal | +0.729 |
touch | +0.659 |
hail | +0.655 |
STATE | +0.643 |
packages | +0.643 |
Neg logit contributions | |
Conserv | -0.662 |
oros | -0.648 |
Hoo | -0.644 |
� | -0.641 |
Relief | -0.638 |
Token | � |
Token ID | 251 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
Conserv | +0.403 |
oros | +0.392 |
Hoo | +0.388 |
� | +0.382 |
Relief | +0.378 |
Neg logit contributions | |
fetal | -0.906 |
touch | -0.839 |
hail | -0.833 |
STATE | -0.823 |
packages | -0.823 |
Token | � |
Token ID | 564 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
fetal | +0.187 |
touch | +0.170 |
hail | +0.169 |
STATE | +0.166 |
packages | +0.166 |
Neg logit contributions | |
Conserv | -0.158 |
oros | -0.154 |
Hoo | -0.154 |
� | -0.153 |
Relief | -0.152 |
Token | � |
Token ID | 250 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Conserv | +1.102 |
oros | +1.073 |
Hoo | +1.065 |
� | +1.056 |
Relief | +1.045 |
Neg logit contributions | |
fetal | -2.321 |
touch | -2.145 |
hail | -2.142 |
packages | -2.108 |
primates | -2.105 |
Token | Is |
Token ID | 3792 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Conserv | +1.271 |
oros | +1.241 |
Hoo | +1.233 |
� | +1.229 |
Relief | +1.216 |
Neg logit contributions | |
fetal | -1.725 |
hail | -1.568 |
touch | -1.568 |
primates | -1.543 |
packages | -1.535 |
Token | it |
Token ID | 340 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
Conserv | +0.710 |
� | +0.698 |
oros | +0.697 |
Hoo | +0.691 |
Relief | +0.680 |
Neg logit contributions | |
fetal | -0.956 |
STATE | -0.876 |
hail | -0.875 |
packages | -0.873 |
WHERE | -0.864 |
Token | okay |
Token ID | 8788 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Conserv | +0.168 |
oros | +0.164 |
Hoo | +0.163 |
� | +0.161 |
Relief | +0.160 |
Neg logit contributions | |
fetal | -0.322 |
hail | -0.297 |
touch | -0.296 |
packages | -0.295 |
STATE | -0.294 |
Token | if |
Token ID | 611 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Conserv | +1.079 |
oros | +1.064 |
� | +1.062 |
Relief | +1.046 |
Hoo | +1.043 |
Neg logit contributions | |
fetal | -1.043 |
hail | -0.941 |
STATE | -0.940 |
packages | -0.935 |
primates | -0.920 |
Token | I |
Token ID | 314 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Conserv | +0.635 |
� | +0.618 |
oros | +0.617 |
Hoo | +0.616 |
Relief | +0.607 |
Neg logit contributions | |
fetal | -0.812 |
hail | -0.738 |
STATE | -0.738 |
packages | -0.734 |
WHERE | -0.730 |
Token | a |
Token ID | 257 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
fetal | +0.629 |
touch | +0.571 |
hail | +0.565 |
primates | +0.554 |
packages | +0.554 |
Neg logit contributions | |
Conserv | -0.548 |
oros | -0.541 |
Hoo | -0.535 |
� | -0.530 |
Relief | -0.526 |
Token | week |
Token ID | 1285 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
fetal | +0.314 |
touch | +0.280 |
hail | +0.276 |
STATE | +0.270 |
primates | +0.269 |
Neg logit contributions | |
Conserv | -0.379 |
oros | -0.374 |
Hoo | -0.371 |
� | -0.368 |
Relief | -0.365 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Conserv | +0.698 |
oros | +0.685 |
Hoo | +0.681 |
� | +0.676 |
Relief | +0.671 |
Neg logit contributions | |
fetal | -0.728 |
touch | -0.655 |
hail | -0.649 |
STATE | -0.640 |
packages | -0.639 |
Token | and |
Token ID | 290 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
fetal | +0.504 |
touch | +0.457 |
hail | +0.452 |
packages | +0.442 |
primates | +0.442 |
Neg logit contributions | |
Conserv | -0.459 |
oros | -0.452 |
Hoo | -0.448 |
� | -0.443 |
Relief | -0.441 |
Token | said |
Token ID | 531 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
fetal | +0.493 |
touch | +0.445 |
hail | +0.442 |
primates | +0.432 |
packages | +0.431 |
Neg logit contributions | |
Conserv | -0.476 |
oros | -0.469 |
Hoo | -0.465 |
� | -0.460 |
Relief | -0.457 |
Token | in |
Token ID | 287 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Conserv | +1.001 |
oros | +0.979 |
Hoo | +0.975 |
� | +0.970 |
Relief | +0.963 |
Neg logit contributions | |
fetal | -1.082 |
touch | -0.972 |
hail | -0.964 |
STATE | -0.955 |
packages | -0.952 |
Token | most |
Token ID | 749 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
fetal | +0.953 |
touch | +0.856 |
hail | +0.847 |
packages | +0.831 |
STATE | +0.829 |
Neg logit contributions | |
Conserv | -0.992 |
oros | -0.975 |
Hoo | -0.969 |
� | -0.961 |
Relief | -0.955 |
Token | cases |
Token ID | 2663 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
fetal | +0.527 |
touch | +0.479 |
hail | +0.475 |
primates | +0.465 |
packages | +0.465 |
Neg logit contributions | |
Conserv | -0.458 |
oros | -0.451 |
Hoo | -0.447 |
� | -0.442 |
Relief | -0.439 |
Token | he |
Token ID | 339 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
Conserv | +0.555 |
oros | +0.544 |
Hoo | +0.542 |
� | +0.538 |
Relief | +0.534 |
Neg logit contributions | |
fetal | -0.572 |
touch | -0.514 |
hail | -0.509 |
STATE | -0.502 |
packages | -0.501 |
Token | got |
Token ID | 1392 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
fetal | +0.084 |
touch | +0.076 |
hail | +0.075 |
packages | +0.073 |
primates | +0.073 |
Neg logit contributions | |
Conserv | -0.089 |
oros | -0.087 |
Hoo | -0.087 |
� | -0.085 |
Relief | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
fetal | +0.508 |
touch | +0.459 |
hail | +0.454 |
smarter | +0.442 |
primates | +0.441 |
Neg logit contributions | |
Conserv | -0.542 |
oros | -0.533 |
Hoo | -0.528 |
� | -0.518 |
avy | -0.516 |
Token | states |
Token ID | 2585 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
Conserv | +0.290 |
oros | +0.284 |
Hoo | +0.283 |
� | +0.280 |
Relief | +0.279 |
Neg logit contributions | |
fetal | -0.310 |
touch | -0.279 |
hail | -0.277 |
packages | -0.273 |
STATE | -0.273 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
Conserv | +0.408 |
oros | +0.400 |
Hoo | +0.398 |
� | +0.394 |
Relief | +0.392 |
Neg logit contributions | |
fetal | -0.429 |
touch | -0.386 |
hail | -0.382 |
packages | -0.378 |
STATE | -0.377 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
fetal | +0.130 |
touch | +0.118 |
hail | +0.117 |
STATE | +0.116 |
packages | +0.115 |
Neg logit contributions | |
Conserv | -0.113 |
oros | -0.112 |
Hoo | -0.111 |
� | -0.110 |
Relief | -0.109 |
Token | ' |
Token ID | 6 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
fetal | +0.603 |
touch | +0.546 |
hail | +0.540 |
primates | +0.525 |
packages | +0.525 |
Neg logit contributions | |
Conserv | -0.604 |
oros | -0.598 |
Hoo | -0.592 |
� | -0.588 |
Relief | -0.583 |
Token | staff |
Token ID | 3085 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
fetal | +0.189 |
touch | +0.169 |
hail | +0.167 |
packages | +0.163 |
STATE | +0.163 |
Neg logit contributions | |
Conserv | -0.219 |
oros | -0.216 |
Hoo | -0.214 |
� | -0.213 |
Relief | -0.211 |
Token | can |
Token ID | 460 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
fetal | +0.108 |
touch | +0.097 |
hail | +0.097 |
packages | +0.095 |
STATE | +0.095 |
Neg logit contributions | |
Conserv | -0.107 |
oros | -0.105 |
Hoo | -0.104 |
� | -0.103 |
Relief | -0.103 |
Token | tap |
Token ID | 9814 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
fetal | +0.700 |
touch | +0.613 |
hail | +0.605 |
packages | +0.590 |
STATE | +0.590 |
Neg logit contributions | |
Conserv | -1.044 |
oros | -1.029 |
Hoo | -1.024 |
� | -1.016 |
Relief | -1.012 |
Token | into |
Token ID | 656 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
fetal | +2.371 |
touch | +2.144 |
hail | +2.104 |
smarter | +2.061 |
primates | +2.055 |
Neg logit contributions | |
Conserv | -2.380 |
oros | -2.349 |
� | -2.321 |
Hoo | -2.318 |
Relief | -2.296 |
Token | a |
Token ID | 257 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
fetal | +0.660 |
touch | +0.593 |
hail | +0.586 |
STATE | +0.575 |
packages | +0.575 |
Neg logit contributions | |
Conserv | -0.659 |
oros | -0.649 |
Hoo | -0.643 |
� | -0.639 |
Relief | -0.634 |
Token | massive |
Token ID | 4858 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
fetal | +0.141 |
touch | +0.125 |
hail | +0.124 |
packages | +0.122 |
STATE | +0.122 |
Neg logit contributions | |
Conserv | -0.167 |
oros | -0.165 |
Hoo | -0.164 |
� | -0.162 |
Relief | -0.162 |
Token | voter |
Token ID | 10765 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
fetal | +0.530 |
touch | +0.469 |
hail | +0.464 |
packages | +0.454 |
STATE | +0.454 |
Neg logit contributions | |
Conserv | -0.671 |
oros | -0.661 |
Hoo | -0.657 |
� | -0.652 |
Relief | -0.649 |
Token | . |
Token ID | 13 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Conserv | +0.221 |
oros | +0.216 |
Hoo | +0.215 |
� | +0.214 |
Relief | +0.212 |
Neg logit contributions | |
fetal | -0.224 |
touch | -0.201 |
hail | -0.199 |
STATE | -0.198 |
packages | -0.198 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Conserv | +0.995 |
Hoo | +0.969 |
� | +0.961 |
Relief | +0.960 |
oros | +0.957 |
Neg logit contributions | |
fetal | -1.222 |
touch | -1.111 |
hail | -1.103 |
primates | -1.090 |
presume | -1.088 |
Token |
|
Token ID | 198 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
Conserv | +0.550 |
oros | +0.542 |
Hoo | +0.539 |
� | +0.531 |
Relief | +0.529 |
Neg logit contributions | |
fetal | -0.580 |
touch | -0.524 |
hail | -0.518 |
STATE | -0.511 |
WHERE | -0.510 |
Token | Another |
Token ID | 6610 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
Conserv | +0.207 |
oros | +0.204 |
Hoo | +0.202 |
� | +0.202 |
Relief | +0.199 |
Neg logit contributions | |
fetal | -0.290 |
touch | -0.265 |
hail | -0.264 |
primates | -0.259 |
presume | -0.258 |
Token | photo |
Token ID | 4590 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Conserv | +0.335 |
oros | +0.329 |
Hoo | +0.328 |
� | +0.325 |
Relief | +0.325 |
Neg logit contributions | |
fetal | -0.313 |
touch | -0.280 |
packages | -0.278 |
hail | -0.278 |
STATE | -0.276 |
Token | uploaded |
Token ID | 19144 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Conserv | +0.522 |
Hoo | +0.509 |
oros | +0.509 |
� | +0.505 |
Relief | +0.502 |
Neg logit contributions | |
fetal | -0.531 |
touch | -0.475 |
hail | -0.472 |
packages | -0.470 |
STATE | -0.469 |
Token | to |
Token ID | 284 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
fetal | +0.433 |
touch | +0.385 |
hail | +0.381 |
packages | +0.373 |
STATE | +0.373 |
Neg logit contributions | |
Conserv | -0.521 |
oros | -0.512 |
Hoo | -0.510 |
� | -0.506 |
Relief | -0.503 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
fetal | +1.044 |
touch | +0.954 |
hail | +0.941 |
primates | +0.921 |
packages | +0.921 |
Neg logit contributions | |
Conserv | -0.764 |
oros | -0.758 |
Hoo | -0.742 |
� | -0.737 |
avy | -0.730 |
Token | by |
Token ID | 416 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
fetal | +0.194 |
touch | +0.174 |
hail | +0.172 |
STATE | +0.169 |
packages | +0.169 |
Neg logit contributions | |
Conserv | -0.206 |
oros | -0.203 |
Hoo | -0.201 |
� | -0.200 |
Relief | -0.199 |
Token | Ma |
Token ID | 6669 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
fetal | +0.067 |
touch | +0.061 |
hail | +0.060 |
packages | +0.060 |
STATE | +0.060 |
Neg logit contributions | |
Conserv | -0.056 |
Hoo | -0.054 |
oros | -0.054 |
� | -0.054 |
Relief | -0.054 |
Token | iss |
Token ID | 747 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Conserv | +1.489 |
Hoo | +1.464 |
oros | +1.461 |
avy | +1.443 |
Relief | +1.431 |
Neg logit contributions | |
fetal | -1.679 |
touch | -1.507 |
STATE | -1.489 |
primates | -1.488 |
hail | -1.488 |
Token | photograph |
Token ID | 8408 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
Conserv | +0.002 |
oros | +0.002 |
Hoo | +0.002 |
� | +0.002 |
Relief | +0.002 |
Neg logit contributions | |
fetal | -0.002 |
touch | -0.002 |
hail | -0.002 |
packages | -0.002 |
STATE | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
Conserv | +0.050 |
oros | +0.049 |
Hoo | +0.049 |
� | +0.048 |
Relief | +0.048 |
Neg logit contributions | |
fetal | -0.050 |
touch | -0.045 |
hail | -0.045 |
STATE | -0.044 |
packages | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
fetal | +0.377 |
touch | +0.341 |
hail | +0.338 |
packages | +0.333 |
STATE | +0.333 |
Neg logit contributions | |
Conserv | -0.326 |
oros | -0.320 |
Hoo | -0.318 |
� | -0.315 |
Relief | -0.313 |
Token | cover |
Token ID | 3002 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
Conserv | +0.386 |
Hoo | +0.375 |
oros | +0.375 |
� | +0.370 |
Relief | +0.370 |
Neg logit contributions | |
fetal | -0.384 |
touch | -0.344 |
hail | -0.342 |
STATE | -0.339 |
packages | -0.338 |
Token | of |
Token ID | 286 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Conserv | +1.889 |
Hoo | +1.817 |
oros | +1.816 |
� | +1.816 |
Relief | +1.805 |
Neg logit contributions | |
fetal | -2.031 |
STATE | -1.817 |
hail | -1.801 |
touch | -1.800 |
packages | -1.800 |
Token | 72 |
Token ID | 7724 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
fetal | +1.584 |
touch | +1.431 |
hail | +1.412 |
primates | +1.390 |
STATE | +1.389 |
Neg logit contributions | |
Conserv | -1.372 |
oros | -1.366 |
Hoo | -1.342 |
� | -1.335 |
Relief | -1.324 |
Token | - |
Token ID | 12 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
fetal | +0.874 |
touch | +0.792 |
hail | +0.784 |
packages | +0.772 |
STATE | +0.772 |
Neg logit contributions | |
Conserv | -0.757 |
oros | -0.742 |
Hoo | -0.738 |
� | -0.731 |
Relief | -0.726 |
Token | year |
Token ID | 1941 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
fetal | +1.050 |
touch | +0.942 |
hail | +0.932 |
STATE | +0.917 |
packages | +0.917 |
Neg logit contributions | |
Conserv | -1.086 |
oros | -1.066 |
Hoo | -1.061 |
� | -1.051 |
Relief | -1.045 |
Token | - |
Token ID | 12 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
fetal | +2.226 |
touch | +1.994 |
hail | +1.966 |
primates | +1.920 |
STATE | +1.920 |
Neg logit contributions | |
Conserv | -2.473 |
oros | -2.438 |
Hoo | -2.421 |
� | -2.400 |
Relief | -2.391 |
Token | old |
Token ID | 727 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
Conserv | +0.268 |
Hoo | +0.262 |
oros | +0.261 |
� | +0.257 |
Relief | +0.257 |
Neg logit contributions | |
fetal | -0.311 |
touch | -0.282 |
hail | -0.278 |
packages | -0.277 |
STATE | -0.277 |
Token | Lab |
Token ID | 3498 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
fetal | +0.259 |
touch | +0.237 |
hail | +0.235 |
STATE | +0.232 |
packages | +0.232 |
Neg logit contributions | |
Conserv | -0.180 |
oros | -0.176 |
Hoo | -0.175 |
� | -0.173 |
Relief | -0.172 |
Token | you |
Token ID | 345 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
fetal | +0.600 |
touch | +0.530 |
hail | +0.525 |
packages | +0.514 |
STATE | +0.514 |
Neg logit contributions | |
Conserv | -0.766 |
oros | -0.754 |
Hoo | -0.750 |
� | -0.744 |
Relief | -0.740 |
Token | keep |
Token ID | 1394 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
fetal | +0.768 |
touch | +0.683 |
hail | +0.672 |
presume | +0.654 |
primates | +0.648 |
Neg logit contributions | |
Conserv | -1.075 |
oros | -1.062 |
Hoo | -1.056 |
� | -1.047 |
Relief | -1.042 |
Token | an |
Token ID | 281 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
Conserv | +1.354 |
Hoo | +1.319 |
oros | +1.306 |
� | +1.296 |
Relief | +1.292 |
Neg logit contributions | |
fetal | -1.284 |
STATE | -1.152 |
packages | -1.141 |
WHERE | -1.140 |
touch | -1.140 |
Token | even |
Token ID | 772 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
fetal | +0.253 |
touch | +0.210 |
hail | +0.209 |
packages | +0.204 |
STATE | +0.204 |
Neg logit contributions | |
Conserv | -0.562 |
oros | -0.554 |
Hoo | -0.552 |
� | -0.548 |
Relief | -0.547 |
Token | ke |
Token ID | 885 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Conserv | +2.037 |
Hoo | +1.975 |
oros | +1.959 |
Relief | +1.951 |
� | +1.943 |
Neg logit contributions | |
fetal | -1.805 |
packages | -1.642 |
STATE | -1.625 |
WHERE | -1.611 |
hail | -1.610 |
Token | el |
Token ID | 417 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
fetal | +0.944 |
touch | +0.874 |
hail | +0.846 |
packages | +0.837 |
auna | +0.834 |
Neg logit contributions | |
Conserv | -0.697 |
Hoo | -0.692 |
oros | -0.678 |
� | -0.674 |
)=( | -0.669 |
Token | ? |
Token ID | 30 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
fetal | +0.789 |
touch | +0.706 |
hail | +0.694 |
packages | +0.679 |
STATE | +0.679 |
Neg logit contributions | |
Conserv | -0.907 |
oros | -0.894 |
Hoo | -0.890 |
� | -0.880 |
Relief | -0.877 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Conserv | +0.126 |
oros | +0.123 |
Hoo | +0.122 |
� | +0.121 |
Relief | +0.121 |
Neg logit contributions | |
fetal | -0.146 |
touch | -0.132 |
hail | -0.131 |
STATE | -0.129 |
packages | -0.128 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Conserv | +1.238 |
oros | +1.216 |
Hoo | +1.208 |
� | +1.196 |
Relief | +1.189 |
Neg logit contributions | |
fetal | -1.376 |
touch | -1.244 |
hail | -1.232 |
STATE | -1.212 |
packages | -1.212 |
Token | I |
Token ID | 40 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Conserv | +0.604 |
oros | +0.589 |
Hoo | +0.587 |
� | +0.579 |
Relief | +0.576 |
Neg logit contributions | |
fetal | -0.972 |
touch | -0.890 |
hail | -0.886 |
primates | -0.871 |
presume | -0.869 |
Token | think |
Token ID | 892 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Conserv | +0.450 |
oros | +0.442 |
Hoo | +0.440 |
� | +0.436 |
Relief | +0.434 |
Neg logit contributions | |
fetal | -0.414 |
touch | -0.370 |
hail | -0.367 |
packages | -0.360 |
STATE | -0.360 |
Token | , |
Token ID | 11 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Conserv | +0.011 |
Hoo | +0.011 |
oros | +0.011 |
Relief | +0.011 |
� | +0.011 |
Neg logit contributions | |
fetal | -0.014 |
touch | -0.013 |
hail | -0.013 |
STATE | -0.013 |
packages | -0.013 |
Token | Ocean |
Token ID | 10692 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Conserv | +0.809 |
oros | +0.786 |
Hoo | +0.782 |
� | +0.771 |
Relief | +0.770 |
Neg logit contributions | |
fetal | -1.303 |
touch | -1.196 |
hail | -1.187 |
packages | -1.175 |
STATE | -1.172 |
Token | ic |
Token ID | 291 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Conserv | +0.812 |
oros | +0.790 |
Hoo | +0.782 |
Relief | +0.771 |
� | +0.770 |
Neg logit contributions | |
fetal | -0.969 |
touch | -0.876 |
hail | -0.870 |
WHERE | -0.862 |
packages | -0.861 |
Token | and |
Token ID | 290 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
fetal | +0.708 |
touch | +0.642 |
hail | +0.637 |
STATE | +0.628 |
packages | +0.628 |
Neg logit contributions | |
Conserv | -0.587 |
oros | -0.573 |
Hoo | -0.570 |
� | -0.563 |
Relief | -0.562 |
Token | Space |
Token ID | 4687 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
Conserv | +1.871 |
Hoo | +1.791 |
oros | +1.782 |
Relief | +1.779 |
� | +1.761 |
Neg logit contributions | |
fetal | -1.942 |
touch | -1.749 |
hail | -1.739 |
WHERE | -1.739 |
STATE | -1.731 |
Token | Sciences |
Token ID | 13473 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
Conserv | +1.957 |
Hoo | +1.871 |
oros | +1.863 |
Relief | +1.844 |
avy | +1.829 |
Neg logit contributions | |
fetal | -2.827 |
touch | -2.575 |
hail | -2.564 |
WHERE | -2.540 |
packages | -2.529 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
fetal | +3.186 |
touch | +2.872 |
hail | +2.805 |
primates | +2.750 |
packages | +2.741 |
Neg logit contributions | |
oros | -3.465 |
Hoo | -3.392 |
� | -3.389 |
glers | -3.384 |
Conserv | -3.384 |
Token | The |
Token ID | 383 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
fetal | +0.185 |
touch | +0.167 |
hail | +0.166 |
STATE | +0.163 |
packages | +0.163 |
Neg logit contributions | |
Conserv | -0.164 |
oros | -0.160 |
Hoo | -0.159 |
� | -0.158 |
Relief | -0.157 |
Token | students |
Token ID | 2444 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
fetal | +0.145 |
touch | +0.129 |
hail | +0.128 |
STATE | +0.126 |
packages | +0.126 |
Neg logit contributions | |
Conserv | -0.166 |
oros | -0.162 |
Hoo | -0.162 |
� | -0.160 |
Relief | -0.160 |
Token | undertook |
Token ID | 45730 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
fetal | +0.572 |
touch | +0.515 |
hail | +0.511 |
presume | +0.497 |
packages | +0.496 |
Neg logit contributions | |
Conserv | -0.625 |
oros | -0.617 |
Hoo | -0.612 |
� | -0.606 |
Relief | -0.604 |
Token | this |
Token ID | 428 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Conserv | +0.778 |
Hoo | +0.763 |
oros | +0.758 |
� | +0.747 |
Relief | +0.747 |
Neg logit contributions | |
fetal | -0.741 |
touch | -0.663 |
hail | -0.657 |
STATE | -0.656 |
WHERE | -0.652 |
Token | 4 |
Token ID | 604 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
fetal | +1.605 |
touch | +1.441 |
hail | +1.417 |
STATE | +1.390 |
packages | +1.389 |
Neg logit contributions | |
Conserv | -1.729 |
oros | -1.702 |
Hoo | -1.691 |
� | -1.674 |
Relief | -1.666 |
Token | 5 |
Token ID | 642 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
fetal | +1.432 |
touch | +1.272 |
hail | +1.267 |
packages | +1.243 |
STATE | +1.242 |
Neg logit contributions | |
Conserv | -1.647 |
oros | -1.615 |
Hoo | -1.609 |
� | -1.598 |
Relief | -1.590 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
fetal | +1.873 |
touch | +1.687 |
hail | +1.659 |
STATE | +1.632 |
packages | +1.624 |
Neg logit contributions | |
Conserv | -1.959 |
oros | -1.930 |
Hoo | -1.915 |
� | -1.895 |
Relief | -1.888 |
Token | 7 |
Token ID | 767 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
fetal | +1.620 |
touch | +1.469 |
hail | +1.455 |
STATE | +1.432 |
packages | +1.431 |
Neg logit contributions | |
Conserv | -1.373 |
oros | -1.347 |
Hoo | -1.338 |
� | -1.325 |
Relief | -1.316 |
Token | 8 |
Token ID | 807 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
fetal | +2.268 |
touch | +2.077 |
hail | +2.041 |
WHERE | +2.002 |
STATE | +2.001 |
Neg logit contributions | |
Conserv | -1.849 |
oros | -1.821 |
Hoo | -1.794 |
� | -1.776 |
glers | -1.769 |
Token | void |
Token ID | 7951 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
fetal | +2.418 |
touch | +2.191 |
hail | +2.165 |
STATE | +2.129 |
packages | +2.127 |
Neg logit contributions | |
Conserv | -2.122 |
oros | -2.088 |
Hoo | -2.071 |
� | -2.049 |
Relief | -2.035 |
Token | vert |
Token ID | 9421 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
fetal | +1.934 |
touch | +1.766 |
presume | +1.569 |
simulate | +1.554 |
hail | +1.542 |
Neg logit contributions | |
Conserv | -4.914 |
Hoo | -4.880 |
oros | -4.874 |
Relief | -4.807 |
glers | -4.806 |
Token | ( |
Token ID | 357 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
fetal | +1.822 |
touch | +1.666 |
hail | +1.633 |
WHERE | +1.598 |
swipe | +1.583 |
Neg logit contributions | |
oros | -1.875 |
Conserv | -1.863 |
Hoo | -1.850 |
)=( | -1.834 |
Relief | -1.827 |
Token | in |
Token ID | 287 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
fetal | +3.175 |
touch | +2.878 |
hail | +2.782 |
presume | +2.688 |
blast | +2.681 |
Neg logit contributions | |
oros | -3.905 |
glers | -3.885 |
Conserv | -3.871 |
Hoo | -3.865 |
KK | -3.865 |
Token | out |
Token ID | 448 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
fetal | +1.150 |
touch | +0.963 |
hail | +0.944 |
packages | +0.913 |
swipe | +0.884 |
Neg logit contributions | |
Conserv | -3.152 |
Hoo | -3.128 |
� | -3.125 |
Relief | -3.091 |
glers | -3.075 |
Token | app |
Token ID | 598 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
fetal | +1.801 |
touch | +1.569 |
hail | +1.368 |
swipe | +1.324 |
blast | +1.292 |
Neg logit contributions | |
oros | -6.388 |
glers | -6.372 |
Conserv | -6.329 |
Relief | -6.328 |
KK | -6.316 |
Token | list |
Token ID | 1351 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
fetal | +0.478 |
touch | +0.431 |
hail | +0.426 |
packages | +0.418 |
primates | +0.416 |
Neg logit contributions | |
Conserv | -0.499 |
oros | -0.492 |
Hoo | -0.487 |
� | -0.484 |
Relief | -0.480 |
Token | . |
Token ID | 13 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
fetal | +2.418 |
touch | +2.192 |
hail | +2.180 |
WHERE | +2.104 |
primates | +2.098 |
Neg logit contributions | |
Conserv | -2.604 |
oros | -2.569 |
Hoo | -2.534 |
� | -2.517 |
)=( | -2.513 |
Token |
|
Token ID | 198 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
fetal | +0.880 |
touch | +0.797 |
hail | +0.790 |
STATE | +0.778 |
packages | +0.778 |
Neg logit contributions | |
Conserv | -0.765 |
oros | -0.751 |
Hoo | -0.745 |
� | -0.740 |
Relief | -0.734 |
Token |
|
Token ID | 198 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
fetal | +1.338 |
touch | +1.210 |
STATE | +1.183 |
WHERE | +1.179 |
hail | +1.178 |
Neg logit contributions | |
oros | -1.497 |
Conserv | -1.492 |
Hoo | -1.477 |
Relief | -1.453 |
� | -1.448 |
Token | Here |
Token ID | 4342 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
fetal | +1.231 |
touch | +1.124 |
STATE | +1.112 |
hail | +1.112 |
WHERE | +1.107 |
Neg logit contributions | |
Conserv | -0.930 |
oros | -0.907 |
Hoo | -0.904 |
� | -0.894 |
Relief | -0.890 |
Token | 's |
Token ID | 338 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
fetal | +3.484 |
touch | +3.194 |
hail | +3.157 |
presume | +3.069 |
STATE | +3.068 |
Neg logit contributions | |
Conserv | -3.111 |
oros | -3.065 |
� | -3.034 |
Hoo | -3.018 |
Relief | -2.983 |
Token | a |
Token ID | 257 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
fetal | +3.239 |
touch | +2.989 |
hail | +2.889 |
presume | +2.830 |
smarter | +2.824 |
Neg logit contributions | |
oros | -3.598 |
Conserv | -3.564 |
� | -3.541 |
glers | -3.487 |
Hoo | -3.479 |
Token | breakdown |
Token ID | 14608 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
fetal | +1.632 |
touch | +1.416 |
hail | +1.360 |
smarter | +1.307 |
swipe | +1.298 |
Neg logit contributions | |
oros | -3.588 |
Conserv | -3.582 |
� | -3.529 |
Hoo | -3.519 |
)=( | -3.517 |
Token | who |
Token ID | 508 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
fetal | +2.537 |
touch | +2.293 |
hail | +2.246 |
smarter | +2.173 |
presume | +2.171 |
Neg logit contributions | |
Conserv | -3.028 |
oros | -2.990 |
Hoo | -2.970 |
� | -2.942 |
Relief | -2.931 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Conserv | +0.464 |
oros | +0.454 |
Hoo | +0.452 |
� | +0.446 |
Relief | +0.445 |
Neg logit contributions | |
fetal | -0.462 |
touch | -0.413 |
hail | -0.409 |
packages | -0.404 |
STATE | -0.403 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Conserv | +0.566 |
Hoo | +0.553 |
oros | +0.553 |
� | +0.546 |
Relief | +0.545 |
Neg logit contributions | |
fetal | -0.539 |
touch | -0.478 |
hail | -0.475 |
STATE | -0.471 |
WHERE | -0.468 |
Token | anniversary |
Token ID | 11162 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
fetal | +0.677 |
touch | +0.611 |
hail | +0.606 |
STATE | +0.596 |
packages | +0.596 |
Neg logit contributions | |
Conserv | -0.609 |
oros | -0.598 |
Hoo | -0.594 |
� | -0.588 |
Relief | -0.584 |
Token | of |
Token ID | 286 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
fetal | +1.920 |
touch | +1.717 |
hail | +1.705 |
STATE | +1.677 |
packages | +1.676 |
Neg logit contributions | |
Conserv | -2.016 |
oros | -1.969 |
Hoo | -1.963 |
� | -1.948 |
Relief | -1.939 |
Token | her |
Token ID | 607 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
Conserv | +0.041 |
Hoo | +0.040 |
oros | +0.040 |
Relief | +0.039 |
� | +0.039 |
Neg logit contributions | |
fetal | -0.059 |
touch | -0.055 |
hail | -0.054 |
packages | -0.054 |
STATE | -0.054 |
Token | 99 |
Token ID | 7388 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
fetal | +0.205 |
touch | +0.181 |
hail | +0.180 |
packages | +0.178 |
STATE | +0.178 |
Neg logit contributions | |
Conserv | -0.259 |
Hoo | -0.254 |
oros | -0.253 |
� | -0.251 |
Relief | -0.250 |
Token | th |
Token ID | 400 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
fetal | +0.554 |
touch | +0.481 |
hail | +0.477 |
packages | +0.467 |
STATE | +0.465 |
Neg logit contributions | |
Conserv | -0.870 |
oros | -0.856 |
Hoo | -0.855 |
� | -0.848 |
Relief | -0.847 |
Token | birthday |
Token ID | 10955 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
fetal | +2.201 |
touch | +1.995 |
hail | +1.970 |
STATE | +1.931 |
primates | +1.930 |
Neg logit contributions | |
Conserv | -1.798 |
oros | -1.775 |
Hoo | -1.748 |
� | -1.743 |
)=( | -1.728 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
fetal | +3.460 |
touch | +3.113 |
hail | +3.075 |
packages | +3.009 |
STATE | +3.008 |
Neg logit contributions | |
Conserv | -3.484 |
oros | -3.442 |
Hoo | -3.409 |
� | -3.378 |
Relief | -3.348 |
Token | the |
Token ID | 262 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
fetal | +0.571 |
touch | +0.516 |
hail | +0.513 |
packages | +0.507 |
STATE | +0.506 |
Neg logit contributions | |
Conserv | -0.498 |
Hoo | -0.485 |
oros | -0.483 |
� | -0.478 |
Relief | -0.478 |
Token | Mary |
Token ID | 5335 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
fetal | +0.283 |
touch | +0.255 |
hail | +0.253 |
packages | +0.251 |
STATE | +0.250 |
Neg logit contributions | |
Conserv | -0.257 |
Hoo | -0.250 |
oros | -0.249 |
� | -0.247 |
Relief | -0.246 |
Token | Mc |
Token ID | 1982 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
fetal | +0.886 |
touch | +0.804 |
hail | +0.797 |
packages | +0.784 |
STATE | +0.783 |
Neg logit contributions | |
Conserv | -0.750 |
oros | -0.735 |
Hoo | -0.730 |
� | -0.724 |
Relief | -0.719 |
Token | Leod |
Token ID | 44559 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
fetal | +1.471 |
touch | +1.346 |
hail | +1.333 |
STATE | +1.316 |
packages | +1.315 |
Neg logit contributions | |
Conserv | -1.145 |
oros | -1.121 |
Hoo | -1.104 |
� | -1.097 |
Relief | -1.092 |
Token | tools |
Token ID | 4899 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Conserv | +1.640 |
Hoo | +1.592 |
oros | +1.588 |
� | +1.587 |
Relief | +1.570 |
Neg logit contributions | |
fetal | -1.285 |
WHERE | -1.145 |
STATE | -1.139 |
packages | -1.123 |
hail | -1.120 |
Token | . |
Token ID | 764 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
fetal | +0.895 |
touch | +0.819 |
hail | +0.814 |
STATE | +0.804 |
WHERE | +0.803 |
Neg logit contributions | |
Conserv | -0.569 |
oros | -0.556 |
Hoo | -0.551 |
� | -0.547 |
Relief | -0.541 |
Token | logging |
Token ID | 18931 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
fetal | +1.754 |
touch | +1.577 |
hail | +1.552 |
primates | +1.506 |
smarter | +1.505 |
Neg logit contributions | |
Conserv | -2.036 |
oros | -2.019 |
Hoo | -1.997 |
� | -1.981 |
Relief | -1.973 |
Token | | |
Token ID | 930 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
fetal | +2.780 |
touch | +2.582 |
hail | +2.564 |
packages | +2.534 |
STATE | +2.531 |
Neg logit contributions | |
Conserv | -1.205 |
oros | -1.168 |
Hoo | -1.158 |
� | -1.139 |
Relief | -1.128 |
Token | 15 |
Token ID | 1315 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
fetal | +1.405 |
touch | +1.271 |
hail | +1.256 |
STATE | +1.232 |
packages | +1.220 |
Neg logit contributions | |
Conserv | -1.431 |
oros | -1.430 |
Hoo | -1.404 |
glers | -1.381 |
� | -1.380 |
Token | 79 |
Token ID | 3720 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
fetal | +0.362 |
touch | +0.328 |
hail | +0.325 |
packages | +0.320 |
STATE | +0.319 |
Neg logit contributions | |
Conserv | -0.315 |
oros | -0.309 |
Hoo | -0.307 |
� | -0.305 |
Relief | -0.303 |
Token | | |
Token ID | 930 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
fetal | +4.288 |
touch | +4.032 |
WHERE | +4.027 |
STATE | +4.012 |
hail | +3.932 |
Neg logit contributions | |
Conserv | -2.383 |
oros | -2.382 |
Hoo | -2.318 |
glers | -2.313 |
)=( | -2.299 |
Token | | |
Token ID | 930 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
fetal | +1.826 |
touch | +1.692 |
hail | +1.684 |
packages | +1.664 |
primates | +1.662 |
Neg logit contributions | |
Conserv | -0.728 |
Hoo | -0.701 |
oros | -0.700 |
� | -0.693 |
Relief | -0.687 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
fetal | +0.775 |
hail | +0.691 |
touch | +0.689 |
STATE | +0.676 |
presume | +0.675 |
Neg logit contributions | |
Conserv | -0.848 |
� | -0.824 |
Hoo | -0.823 |
oros | -0.823 |
Relief | -0.819 |
Token | | |
Token ID | 930 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
fetal | +1.238 |
touch | +1.157 |
STATE | +1.143 |
WHERE | +1.140 |
hail | +1.137 |
Neg logit contributions | |
Conserv | -0.610 |
oros | -0.596 |
Hoo | -0.595 |
Relief | -0.584 |
)=( | -0.572 |
Token | org |
Token ID | 8745 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
fetal | +0.140 |
touch | +0.128 |
hail | +0.127 |
STATE | +0.127 |
WHERE | +0.126 |
Neg logit contributions | |
Conserv | -0.084 |
Hoo | -0.081 |
oros | -0.081 |
� | -0.081 |
Relief | -0.080 |