INDEX
Explanations
references to the name "Ben" or variations of it
New Auto-Interp
Negative Logits
vette
-0.19
eric
-0.17
uction
-0.17
lettes
-0.16
uctor
-0.16
dock
-0.15
NullOrEmpty
-0.14
ανα
-0.14
æijĨ
-0.14
gaard
-0.14
POSITIVE LOGITS
jamin
0.34
oit
0.33
ito
0.29
ign
0.28
utzer
0.27
ning
0.26
itez
0.25
ighted
0.25
éf
0.24
icio
0.24
Activations Density 0.008%