INDEX
Explanations
mentions of the name "Ben" and its variations
New Auto-Interp
Negative Logits
eric
-0.15
CHAIN
-0.15
uction
-0.15
ahat
-0.15
ulaire
-0.15
uctor
-0.14
lettes
-0.14
/Instruction
-0.14
a
-0.14
letic
-0.14
POSITIVE LOGITS
jamin
0.32
icio
0.28
oit
0.28
ito
0.25
ji
0.23
ighted
0.23
Franklin
0.22
ign
0.21
ning
0.21
jam
0.21
Activations Density 0.007%