INDEX
Explanations
terms related to moisture or wetness in various contexts
New Auto-Interp
Negative Logits
opers
-0.20
mekte
-0.17
ials
-0.17
ially
-0.16
azi
-0.16
ots
-0.15
oted
-0.15
yx
-0.15
esteem
-0.15
erable
-0.15
POSITIVE LOGITS
ted
0.31
lands
0.28
ting
0.28
zel
0.27
ters
0.25
ter
0.25
ten
0.23
ensch
0.22
land
0.22
test
0.21
Activations Density 0.010%