INDEX
Explanations
locations or activities related to cultural or arts venues
references to theaters and cinematic venues
New Auto-Interp
Negative Logits
doms
-0.84
nir
-0.71
bring
-0.68
ilies
-0.67
vironment
-0.66
ortium
-0.65
pages
-0.65
ever
-0.64
haust
-0.63
agher
-0.62
POSITIVE LOGITS
wright
1.01
theatre
1.01
goers
1.00
theater
0.99
theat
0.93
theaters
0.91
Royale
0.87
marqu
0.87
eers
0.84
Workshop
0.82
Activations Density 0.015%