INDEX
Explanations
names or last names with a certain pattern of vowels and consonants
proper nouns, especially names of individuals and places
New Auto-Interp
Negative Logits
VALUE
-0.72
Manila
-0.66
ADRA
-0.65
Vote
-0.63
Jam
-0.63
Story
-0.63
soDeliveryDate
-0.61
ITION
-0.61
Sabha
-0.60
Showtime
-0.60
POSITIVE LOGITS
enegger
1.33
tein
1.23
enstein
1.16
sson
1.15
ijk
1.14
enburg
1.14
meier
1.14
sen
1.11
ner
1.11
icz
1.11
Activations Density 0.224%