INDEX
Explanations
phrases related to fire or firefighting
terminology related to fire and emergency services
New Auto-Interp
Negative Logits
士
-0.73
rome
-0.72
lez
-0.70
future
-0.69
urat
-0.67
illac
-0.67
archment
-0.65
uls
-0.65
lace
-0.64
IX
-0.64
POSITIVE LOGITS
extingu
0.75
ÃĥÃĤ
0.71
destro
0.70
dams
0.68
ornia
0.67
fury
0.67
exting
0.67
espresso
0.67
ĪĴ
0.66
cffffcc
0.66
Activations Density 0.191%