INDEX
Explanations
expressions of sadness and emotional distress
New Auto-Interp
Negative Logits
MTC
-0.52
Clipper
-0.50
clipper
-0.49
ilever
-0.48
RTEX
-0.48
Unite
-0.47
myra
-0.47
berth
-0.45
clippers
-0.45
fuse
-0.44
POSITIVE LOGITS
Sad
0.88
Sad
0.87
sad
0.81
sad
0.79
saddest
0.78
Sadler
0.77
tristes
0.73
SAD
0.71
sedih
0.70
sadness
0.70
Activations Density 0.003%