INDEX
Explanations
terms related to concussions and their effects
New Auto-Interp
Negative Logits
AtPath
-0.16
tte
-0.15
868
-0.14
OMPI
-0.14
rado
-0.14
bourg
-0.14
emas
-0.14
leans
-0.13
pread
-0.13
Ñĩа
-0.13
POSITIVE LOGITS
conc
0.42
concussion
0.41
conc
0.41
Conc
0.39
brain
0.32
Brain
0.31
helmets
0.29
helmet
0.29
brain
0.28
Brain
0.28
Activations Density 0.049%