INDEX
Explanations
in followed by a country or language
New Auto-Interp
Negative Logits
irish
1.20
egyptian
1.18
Scottish
1.16
afric
1.14
Sicilian
1.14
canadian
1.14
Belarusian
1.12
scottish
1.10
Egyptian
1.10
django
1.10
POSITIVE LOGITS
Greater
0.80
ichever
0.71
ganske
0.70
றிந்த
0.70
仅
0.68
这座
0.66
рід
0.66
ומ
0.66
what
0.66
convincingly
0.64
Activations Density 0.570%