INDEX
Explanations
mentions of the name "Jean" and its variations
New Auto-Interp
Negative Logits
gor
-0.17
xor
-0.16
ght
-0.15
udic
-0.15
ãĥ³ãĤ°
-0.15
_RST
-0.14
abit
-0.14
ursor
-0.14
iland
-0.14
lej
-0.14
POSITIVE LOGITS
ette
0.30
ne
0.30
Bapt
0.23
ie
0.22
ettes
0.21
ine
0.20
Claude
0.19
inne
0.18
ene
0.18
etten
0.17
Activations Density 0.006%