INDEX
Explanations
occurrences of the term "bo" in various contexts
New Auto-Interp
Negative Logits
y
-0.23
yum
-0.16
ume
-0.16
weight
-0.15
labs
-0.15
lin
-0.15
l
-0.14
upon
-0.14
UTION
-0.14
usa
-0.14
POSITIVE LOGITS
bo
0.24
ogie
0.22
oleans
0.21
hem
0.20
vine
0.20
Bo
0.19
ating
0.19
ister
0.18
obs
0.18
oming
0.18
Activations Density 0.012%