INDEX
Explanations
mentions of composite materials
terms related to composites and specific locations or entities
New Auto-Interp
Negative Logits
Wonderland
-0.75
ertodd
-0.74
į
-0.71
ObamaCare
-0.69
hips
-0.68
Buddha
-0.68
@#&
-0.66
aternity
-0.65
Cortana
-0.64
Ducks
-0.63
POSITIVE LOGITS
cill
0.88
aic
0.85
ply
0.82
ensions
0.78
cil
0.78
pos
0.77
ikuman
0.77
otypes
0.75
tiss
0.74
itent
0.74
Activations Density 0.040%