INDEX
Explanations
mentions of the pronoun "you"
addressing the reader directly
New Auto-Interp
Negative Logits
msgTypes
-0.51
TagMode
-0.47
rungsseite
-0.44
nahilalakip
-0.42
merawat
-0.41
Parcelize
-0.40
Aholisi
-0.40
脚注の使い方
-0.39
expandindo
-0.39
practices
-0.37
POSITIVE LOGITS
AssemblyProduct
0.55
mirth
0.50
CanadaChoose
0.47
laugh
0.46
canine
0.44
Wikimedijinoj
0.44
dafx
0.44
Италијани
0.44
blitz
0.44
giggle
0.43
Activations Density 0.001%