INDEX
Explanations
names related to politics and film industry, specifically the name "Bach"
New Auto-Interp
Negative Logits
vomit
-0.71
LEASE
-0.70
ODUCT
-0.70
IPCC
-0.65
derog
-0.62
Origin
-0.60
ITY
-0.60
DSL
-0.59
substance
-0.59
Independence
-0.59
POSITIVE LOGITS
mann
1.36
ynski
1.14
ao
1.02
illi
0.94
fried
0.94
isan
0.93
Bach
0.92
alos
0.92
ophon
0.92
lore
0.88
Activations Density 0.022%