INDEX
Explanations
the presence of the name "Ben" in various contexts
names starting with Ben
New Auto-Interp
Negative Logits
itulah
-0.52
amarillas
-0.50
kasarigan
-0.50
ovunque
-0.48
"/";
-0.47
moeite
-0.47
zabaw
-0.46
'/';
-0.46
iertamente
-0.46
smaak
-0.46
POSITIVE LOGITS
Ben
1.84
Ben
1.75
BEN
1.14
ben
1.02
Бен
0.97
BEN
0.95
Bens
0.88
Benjamin
0.86
Benjamin
0.86
Bennet
0.85
Activations Density 0.002%