INDEX
Explanations
references to various aspects of culture
references to "culture."
New Auto-Interp
Negative Logits
iary
-0.76
agher
-0.74
ieth
-0.72
issan
-0.72
fman
-0.71
IELD
-0.71
oug
-0.71
inosaur
-0.70
heed
-0.69
deen
-0.69
POSITIVE LOGITS
culture
0.95
Culture
0.95
lia
0.76
ulture
0.76
indo
0.76
clash
0.74
Appropri
0.72
cultures
0.71
ogy
0.70
diversity
0.70
Activations Density 0.016%