INDEX
Explanations
references to governmental or legislative actions and their consequences
New Auto-Interp
Negative Logits
hitheater
-0.65
TagMode
-0.65
color
-0.61
Flavor
-0.60
rumor
-0.59
colorless
-0.58
flavor
-0.58
catalogs
-0.58
UserContext
-0.55
esophagus
-0.55
POSITIVE LOGITS
Irish
1.23
Dublin
1.15
Irish
1.15
Ireland
1.11
Dublin
1.04
Ireland
1.04
irish
1.01
IRELAND
1.00
irish
0.97
Limerick
0.94
Activations Density 0.162%