INDEX
Explanations
names and pronouns followed by speech verbs
New Auto-Interp
Negative Logits
доба
0.59
enquire
0.56
exclaimed
0.54
adicion
0.54
questioned
0.51
breathed
0.50
exclamation
0.49
дода
0.48
finalised
0.48
detalhes
0.47
POSITIVE LOGITS
".
0.43
"":
0.42
करीत
0.39
ня
0.38
""
0.38
bio
0.38
okit
0.38
lately
0.38
Noting
0.38
Bio
0.37
Activations Density 0.001%