INDEX
Explanations
references to locations or entities associated with Brooklyn
New Auto-Interp
Negative Logits
ye
-0.20
y
-0.17
ÑĪив
-0.16
yen
-0.16
agrant
-0.16
tir
-0.15
si
-0.15
coat
-0.15
yd
-0.15
ãģĹãģı
-0.15
POSITIVE LOGITS
ites
0.27
ite
0.23
-based
0.23
ensis
0.20
ITES
0.19
ights
0.17
-bound
0.17
typings
0.16
ollo
0.16
ourd
0.16
Activations Density 0.013%