INDEX
Explanations
mentions of the name "Ben" or its variations
New Auto-Interp
Negative Logits
Reſ
-1.08
myſelf
-1.02
Eſ
-1.00
itſelf
-0.99
greateſt
-0.97
ſelf
-0.96
Inſ
-0.94
houſe
-0.93
ſeveral
-0.93
Monfieur
-0.93
POSITIVE LOGITS
Ben
3.96
Ben
3.62
ben
3.01
BEN
2.74
ben
2.70
BEN
2.59
Бен
1.90
Benjamin
1.81
Benjamin
1.61
Bén
1.57
Activations Density 0.020%