INDEX
Explanations
references to Brooklyn and its neighborhoods or features
New Auto-Interp
Negative Logits
tir
-0.18
erver
-0.16
ÑĪив
-0.16
geber
-0.16
yen
-0.15
agrant
-0.15
yr
-0.15
sam
-0.15
utm
-0.15
si
-0.15
POSITIVE LOGITS
ites
0.25
ite
0.21
å°¼äºļ
0.20
-based
0.19
ights
0.17
äs
0.17
-area
0.16
ourd
0.15
iegel
0.15
oney
0.15
Activations Density 0.012%