INDEX
Explanations
terms related to food and refreshment
New Auto-Interp
Negative Logits
lier
-0.17
yro
-0.17
fall
-0.17
lify
-0.16
erna
-0.15
ileo
-0.15
.freeze
-0.15
loid
-0.15
pais
-0.14
aque
-0.14
POSITIVE LOGITS
ingly
0.20
ossil
0.17
xes
0.17
owl
0.16
/free
0.15
es
0.15
utable
0.15
ÑĮко
0.15
oose
0.15
resher
0.14
Activations Density 0.032%