INDEX
Explanations
mentions of specific nationalities or regions, particularly Welsh and Catalan
references to Welsh identity
New Auto-Interp
Negative Logits
nels
-0.81
ocr
-0.78
eus
-0.78
cean
-0.75
awaru
-0.72
eering
-0.71
ramid
-0.71
ographed
-0.71
FactoryReloaded
-0.70
aundering
-0.69
POSITIVE LOGITS
Welsh
1.00
Nadu
0.96
Wales
0.79
Instruments
0.77
Lions
0.73
Cardiff
0.72
humour
0.69
MEP
0.69
istani
0.68
Hots
0.67
Activations Density 0.004%