INDEX
Explanations
proper nouns related to shopping malls
references to a specific mall
New Auto-Interp
Negative Logits
IBLE
-0.80
SHIP
-0.78
vous
-0.75
vernment
-0.66
Nich
-0.65
İĭ
-0.64
nder
-0.60
dit
-0.60
lished
-0.60
Dame
-0.60
POSITIVE LOGITS
malls
0.96
ocks
0.92
ageddon
0.92
itect
0.91
mall
0.90
enium
0.90
aji
0.89
ieu
0.87
ificent
0.87
adium
0.87
Activations Density 0.012%