INDEX
Explanations
classifications or distinctions among species
New Auto-Interp
Negative Logits
vrd
-0.20
animal
-0.15
scientific
-0.15
edl
-0.15
Scient
-0.15
Animal
-0.15
Bow
-0.14
Meth
-0.14
linger
-0.14
Scientific
-0.14
POSITIVE LOGITS
morph
0.27
morph
0.23
Morph
0.21
Characters
0.20
morphology
0.20
diagn
0.20
characters
0.20
characters
0.20
Characters
0.20
symp
0.19
Activations Density 0.035%