INDEX
Explanations
phrases related to national anthems
mentions of the national anthem
New Auto-Interp
Negative Logits
erm
-0.71
Commerce
-0.70
Sor
-0.69
odge
-0.67
aido
-0.65
fram
-0.64
ulton
-0.64
LD
-0.64
ringe
-0.64
ahn
-0.63
POSITIVE LOGITS
anthem
1.12
Anthem
0.85
lyrics
0.80
salute
0.74
sburg
0.71
brance
0.69
kne
0.69
songs
0.69
mson
0.69
singers
0.68
Activations Density 0.025%