INDEX
Explanations
the occurrences of the substring "sn"
New Auto-Interp
Negative Logits
inger
-0.17
otron
-0.16
442
-0.15
Umb
-0.14
534
-0.14
isay
-0.14
aise
-0.14
etr
-0.14
iere
-0.14
vement
-0.14
POSITIVE LOGITS
sn
0.44
Sn
0.35
sn
0.34
(sn
0.31
/sn
0.30
.Sn
0.30
.sn
0.30
-sn
0.29
Sn
0.29
SN
0.27
Activations Density 0.009%