INDEX
Explanations
references to the concept of "body."
New Auto-Interp
Negative Logits
Gennaio
-0.69
餐廳
-0.66
revenus
-0.66
shingles
-0.64
binoculars
-0.64
mezzanine
-0.61
simile
-0.61
Caw
-0.61
glaucoma
-0.60
gneiss
-0.60
POSITIVE LOGITS
body
3.87
Body
3.59
BODY
3.38
body
3.38
Body
3.32
bodies
3.12
Bodies
2.89
BODY
2.75
bodys
2.56
bodies
2.52
Activations Density 0.059%