INDEX
Explanations
references to distinct landmarks or historical figures associated with Brooklyn
New Auto-Interp
Negative Logits
yd
-0.17
aff
-0.16
umont
-0.15
ydro
-0.15
appreh
-0.14
Aff
-0.14
éĥ
-0.14
ayo
-0.14
‘
-0.13
_integration
-0.13
POSITIVE LOGITS
ins
0.34
arr
0.31
'est
0.28
arrera
0.27
'a
0.27
'al
0.25
'Ãł
0.25
'es
0.25
'on
0.24
reta
0.24
Activations Density 0.004%