INDEX
Explanations
items or terms related to the Tamil script or language
New Auto-Interp
Negative Logits
oy
-0.17
Tob
-0.17
erd
-0.16
toy
-0.16
cred
-0.15
lobs
-0.15
uy
-0.15
isc
-0.15
som
-0.15
wij
-0.14
POSITIVE LOGITS
¤
0.32
ļ
0.27
©
0.27
±
0.27
ħ
0.24
µ
0.24
ª
0.23
®
0.22
°
0.22
ķ
0.20
Activations Density 0.002%