INDEX
Explanations
references to individuals named John
New Auto-Interp
Negative Logits
ſche
-0.89
ſind
-0.86
//=
-0.86
Anſ
-0.82
Theſe
-0.81
themſelves
-0.80
whoſe
-0.79
Rache
-0.79
poffible
-0.78
Reſ
-0.77
POSITIVE LOGITS
John
1.81
John
1.56
john
1.39
JOHN
1.39
JOHN
1.38
john
1.25
Johns
1.16
Джон
1.08
Johns
1.02
johns
0.98
Activations Density 0.035%