INDEX
Explanations
terms related to industrial processes and materials
New Auto-Interp
Negative Logits
iola
-0.15
latex
-0.15
Blur
-0.14
_Print
-0.14
Whe
-0.14
darwin
-0.14
mil
-0.14
@WebServlet
-0.14
PointSize
-0.13
velt
-0.13
POSITIVE LOGITS
kil
0.38
refr
0.35
furnace
0.33
Kil
0.33
furn
0.29
kil
0.29
firing
0.29
burner
0.29
Furn
0.27
fired
0.27
Activations Density 0.022%