INDEX
Explanations
culinary ingredients and medical terminology related to substances and health conditions
New Auto-Interp
Negative Logits
SB
-0.82
AB
-0.73
MB
-0.71
sb
-0.69
SB
-0.68
WB
-0.68
RB
-0.68
BB
-0.64
JB
-0.64
WB
-0.63
POSITIVE LOGITS
Personensuche
0.75
boundary
0.71
Built
0.65
Brands
0.64
Bodies
0.64
button
0.64
bygga
0.63
Brand
0.63
Boundaries
0.63
Built
0.63
Activations Density 0.500%