INDEX
Explanations
expressions of strong emotional reactions or sentiments, particularly those indicating curiosity or horror
sooo, hmm, or horrific
New Auto-Interp
Negative Logits
SourceChecksum
-0.52
ftagPool
-0.44
DoubleQuotes
-0.43
enfans
-0.41
GOTREF
-0.40
ActivatedRoute
-0.40
auguri
-0.40
/*
-0.38
AnchorTagHelper
-0.38
Parti
-0.38
POSITIVE LOGITS
sooo
0.75
soo
0.73
soo
0.70
Soo
0.65
Soo
0.63
Hmm
0.60
horrific
0.59
soooo
0.59
Hmm
0.57
hmm
0.57
Activations Density 0.011%