INDEX
Explanations
mentions of art and its associated concepts and terms
New Auto-Interp
Negative Logits
themſelves
-1.01
Monfieur
-1.00
myſelf
-0.97
Diſ
-0.97
pleaſure
-0.95
ſever
-0.94
LabelTagHelper
-0.93
ſmall
-0.92
FailureListener
-0.91
Theſe
-0.87
POSITIVE LOGITS
art
3.27
Art
3.00
Art
2.85
art
2.62
ART
2.61
ART
2.29
arts
2.12
Arts
1.86
artwork
1.79
arts
1.70
Activations Density 0.040%