INDEX
Explanations
names, specifically "Pratt" and "Whitney."
mentions of specific individuals and the concept of fins in various contexts
New Auto-Interp
Negative Logits
bold
-0.72
oked
-0.71
bane
-0.69
oup
-0.68
kered
-0.66
pres
-0.65
Pradesh
-0.61
blo
-0.61
jaws
-0.61
âĶĢ
-0.60
POSITIVE LOGITS
Pratt
0.95
etry
0.84
vernment
0.81
etsk
0.74
uit
0.71
CLUD
0.68
nell
0.67
itives
0.66
Reviewer
0.65
amental
0.64
Activations Density 0.047%