INDEX
Explanations
words related to anger
instances of anger or frustration
New Auto-Interp
Negative Logits
sites
-0.93
glas
-0.85
uchin
-0.84
fman
-0.82
ajo
-0.82
artifacts
-0.79
icrobial
-0.79
akeru
-0.78
ingen
-0.77
ipeg
-0.76
POSITIVE LOGITS
outburst
0.89
angry
0.86
parting
0.78
Birds
0.78
mobs
0.77
shouts
0.75
Angry
0.75
streak
0.74
indignation
0.71
anger
0.69
Activations Density 0.025%