INDEX
Explanations
punctuation marks, particularly parentheses and quotation marks
New Auto-Interp
Negative Logits
activex
-0.16
nila
-0.16
ayi
-0.15
fetisch
-0.15
#
-0.15
geh
-0.14
ÐIJÑĢÑħÑĸв
-0.14
Ỽ
-0.14
angler
-0.14
#End
-0.14
POSITIVE LOGITS
s
0.20
com
0.17
g
0.17
ses
0.17
anges
0.16
pro
0.16
j
0.16
rette
0.15
1
0.15
es
0.15
Activations Density 0.070%