INDEX
Explanations
terms related to the action of pumping and the object being pumped
New Auto-Interp
Negative Logits
зв
-0.16
ials
-0.16
larg
-0.15
inine
-0.15
egers
-0.15
lijke
-0.14
gether
-0.14
POR
-0.14
Ðļод
-0.14
zenie
-0.14
POSITIVE LOGITS
kins
0.37
kin
0.26
jack
0.21
кин
0.21
edReader
0.19
skins
0.17
amentals
0.16
elly
0.16
-action
0.16
lÃŃn
0.15
Activations Density 0.009%