INDEX
Explanations
terms related to dominance and control in various contexts
New Auto-Interp
Negative Logits
ago
-0.17
ãĥŀãĥ³
-0.15
ermann
-0.15
ipp
-0.15
atch
-0.14
_primary
-0.14
esus
-0.14
ávÄĽ
-0.14
mong
-0.14
iset
-0.14
POSITIVE LOGITS
545
0.19
597
0.17
Ñģобой
0.17
stay
0.15
amac
0.15
reffen
0.15
/support
0.14
645
0.14
347
0.14
arbonate
0.14
Activations Density 0.038%