INDEX
Explanations
names or terms related to Central Asian countries or regions
proper nouns, specifically names of people or places
New Auto-Interp
Negative Logits
kefeller
-0.84
STER
-0.75
plane
-0.65
cess
-0.62
restling
-0.60
Deadpool
-0.59
chambers
-0.59
wcsstore
-0.59
ruary
-0.58
theless
-0.57
POSITIVE LOGITS
nen
0.85
uku
0.83
atsu
0.79
arya
0.79
Pradesh
0.79
ikuman
0.77
OTO
0.76
akra
0.76
aten
0.76
hai
0.76
Activations Density 0.178%