INDEX
Explanations
proper nouns and names, particularly related to familial relationships
New Auto-Interp
Negative Logits
.functional
-0.17
ague
-0.16
n
-0.15
LabelText
-0.15
νÏİ
-0.15
jac
-0.15
andbox
-0.14
baseUrl
-0.14
subtype
-0.14
aved
-0.14
POSITIVE LOGITS
b
0.31
esan
0.19
б
0.17
hti
0.17
)b
0.16
Âłb
0.16
Twin
0.15
RuleContext
0.15
км
0.14
å«
0.14
Activations Density 0.008%