INDEX
Explanations
was/is/has followed by description
New Auto-Interp
Negative Logits
อื่น
-0.92
after
-0.89
不再
-0.87
f
-0.85
링
-0.85
frattempo
-0.85
sấy
-0.83
rah
-0.83
This
-0.82
What
-0.82
POSITIVE LOGITS
rám
1.21
ternos
0.98
adorno
0.96
gorro
0.91
silhouette
0.91
Türk
0.91
dél
0.90
'",
0.90
juſ
0.90
obrázek
0.89
Activations Density 0.098%