INDEX
Explanations
image, achievements, feelings, moving objects
New Auto-Interp
Negative Logits
nuage
-0.96
HAIR
-0.85
Lak
-0.84
珧
-0.83
Hickory
-0.83
италья
-0.82
vah
-0.81
ńska
-0.80
procé
-0.80
Показать
-0.80
POSITIVE LOGITS
image
1.09
specifications
1.00
excellent
0.96
characteristics
0.95
feelings
0.94
important
0.93
evaluation
0.91
mysterious
0.91
results
0.91
their
0.89
Activations Density 0.137%