INDEX
Explanations
references to various types of diets and dietary practices
New Auto-Interp
Negative Logits
lesi
-0.18
opus
-0.18
hung
-0.17
leo
-0.16
hurst
-0.16
acity
-0.16
hu
-0.15
è¦ĸ
-0.15
anted
-0.15
andon
-0.15
POSITIVE LOGITS
etic
0.34
itian
0.33
icians
0.31
ician
0.28
etics
0.24
ary
0.24
ing
0.23
rich
0.23
ARY
0.21
ting
0.20
Activations Density 0.009%