INDEX
Explanations
quotations containing family members' names
dialogue and statements from characters within a narrative
New Auto-Interp
Negative Logits
captcha
-0.74
CVE
-0.70
Draft
-0.70
UGC
-0.69
UX
-0.69
uggest
-0.68
Platform
-0.68
iste
-0.65
cham
-0.64
TPP
-0.64
POSITIVE LOGITS
Dad
1.43
Dad
1.41
grandparents
1.41
grandchildren
1.40
dad
1.37
Aunt
1.36
siblings
1.36
aunt
1.34
Mom
1.34
mom
1.29
Activations Density 0.630%