INDEX
Explanations
expressions of anger and dissatisfaction
expressions of anger or frustration
New Auto-Interp
Negative Logits
glas
-0.91
sites
-0.88
uchin
-0.82
nown
-0.82
akeru
-0.82
icrobial
-0.78
fman
-0.77
livest
-0.75
ipeg
-0.74
artifacts
-0.74
POSITIVE LOGITS
mobs
0.94
outburst
0.93
angry
0.86
Birds
0.80
anger
0.77
indignation
0.77
Anger
0.74
Angry
0.73
lash
0.73
storms
0.71
Activations Density 0.065%