INDEX
Explanations
greetings or welcoming phrases
New Auto-Interp
Negative Logits
ftagPool
-0.70
LookAnd
-0.68
fillType
-0.59
imgur
-0.59
tagHelper
-0.58
unhofer
-0.56
uyasha
-0.56
ImageContext
-0.55
Kaynakça
-0.54
})}$
-0.54
POSITIVE LOGITS
welcome
1.10
aboard
0.99
welcome
0.96
Welcome
0.94
WELCOME
0.94
Welcome
0.94
elcome
0.94
welcomed
0.92
welcomes
0.88
WELCOME
0.88
Activations Density 0.052%