INDEX
Explanations
locations within a city
mentions of specific locations or places
New Auto-Interp
Negative Logits
stood
-0.74
forthcoming
-0.69
nascent
-0.65
ajor
-0.63
Andre
-0.61
Parameter
-0.60
inclusion
-0.58
Attribute
-0.57
ongoing
-0.56
unpublished
-0.56
POSITIVE LOGITS
smelling
1.09
expecting
1.01
unnoticed
1.01
undet
0.95
pretending
0.92
wondering
0.91
wearing
0.91
looking
0.91
naked
0.91
screaming
0.90
Activations Density 0.460%