INDEX
Explanations
specific actions or events related to conflict or struggle
New Auto-Interp
Negative Logits
usercontent
-0.74
conn
-0.71
Bey
-0.67
lords
-0.63
Otherwise
-0.62
leness
-0.62
rone
-0.62
anything
-0.60
riv
-0.60
sooner
-0.60
POSITIVE LOGITS
hirt
0.79
ometimes
0.76
hift
0.72
creen
0.72
ilver
0.69
Shots
0.69
wered
0.64
veland
0.64
POV
0.63
IGHTS
0.63
Activations Density 0.278%