INDEX
Explanations
mentions of the name "Robert" and its variations
New Auto-Interp
Negative Logits
DataAnnotations
-0.80
يتيمه
-0.76
GenerationType
-0.72
DebuggerNonUser
-0.67
Italijanski
-0.67
فريبيس
-0.66
balleur
-0.66
quelize
-0.66
fevere
-0.65
SBATCH
-0.64
POSITIVE LOGITS
Bob
0.71
bie
0.68
Bob
0.67
BOB
0.57
Bobby
0.55
Bobby
0.54
Dylan
0.52
bob
0.50
ziek
0.48
takip
0.48
Activations Density 0.076%