INDEX
Explanations
occurrences of the substring "ca"
New Auto-Interp
Negative Logits
rshire
-0.43
Kath
-0.39
kata
-0.38
ogly
-0.38
Eins
-0.36
kata
-0.36
Kata
-0.36
Kata
-0.36
yardımcı
-0.35
נד
-0.35
POSITIVE LOGITS
ca
2.89
ca
2.42
CA
2.05
Ca
1.87
CA
1.87
Ca
1.82
caul
1.02
ça
1.00
cae
0.98
Cahill
0.93
Activations Density 0.282%