INDEX
Explanations
mentions of food and its various aspects or categories
New Auto-Interp
Negative Logits
ept
-0.18
ors
-0.17
-builder
-0.16
letal
-0.15
eping
-0.15
opus
-0.14
unto
-0.14
ORS
-0.14
ension
-0.14
(es
-0.13
POSITIVE LOGITS
stuff
0.38
ie
0.26
st
0.25
borne
0.24
stu
0.22
chain
0.21
service
0.20
ies
0.20
zie
0.19
gie
0.19
Activations Density 0.042%