INDEX
Explanations
instances of strong emotions or emphatic expressions in dialogue
New Auto-Interp
Negative Logits
ahren
-0.18
Ì£
-0.16
Guaranteed
-0.14
smoker
-0.14
zi
-0.14
Brend
-0.13
FN
-0.13
ÙĪØ±Ø¯
-0.13
Realty
-0.13
darker
-0.13
POSITIVE LOGITS
odesk
0.15
ocht
0.15
chte
0.14
év
0.14
933
0.14
GOT
0.14
ystate
0.13
inely
0.13
ÏĨεÏģ
0.13
IVO
0.13
Activations Density 0.000%