INDEX
Explanations
instances of the letter 'z' in various contexts
New Auto-Interp
Negative Logits
olicit
-0.16
zcze
-0.15
indow
-0.15
oles
-0.14
ä»ģ
-0.14
ading
-0.14
/*č↵
-0.14
ifest
-0.14
íĸī
-0.14
ilo
-0.13
POSITIVE LOGITS
eh
0.20
entral
0.18
irk
0.18
ivil
0.18
uck
0.18
yper
0.17
itat
0.16
Scaler
0.16
yk
0.16
udem
0.16
Activations Density 0.012%