INDEX
Explanations
characters or words written in a specific script
New Auto-Interp
Negative Logits
Õ
-0.17
stry
-0.16
157
-0.15
ĥĿ
-0.15
ye
-0.15
idi
-0.15
áŀ
-0.15
á
-0.14
ج
-0.14
ай
-0.14
POSITIVE LOGITS
à¥į
0.22
à¥
0.20
म
0.20
स
0.19
à¤ķ
0.19
à¥ĩ
0.19
ा
0.19
द
0.18
प
0.18
à¥įâĢį
0.18
Activations Density 0.017%