INDEX
Explanations
occurrences of the word "Bar" in various contexts
New Auto-Interp
Negative Logits
nid
-0.17
io
-0.16
kul
-0.16
ying
-0.16
ene
-0.16
gor
-0.15
çį
-0.15
empo
-0.15
ese
-0.14
ent
-0.14
POSITIVE LOGITS
bara
0.28
riers
0.28
celona
0.24
oque
0.23
becue
0.23
coded
0.22
rios
0.22
rio
0.21
neys
0.21
rient
0.21
Activations Density 0.015%