INDEX
Explanations
punctuation and common words like conjunctions and prepositions
New Auto-Interp
Negative Logits
pi
-0.42
象
-0.42
med
-0.35
MED
-0.35
MED
-0.34
se
-0.34
b
-0.32
pi
-0.32
vor
-0.32
Med
-0.31
POSITIVE LOGITS
Mr
2.36
Mr
2.16
mr
1.86
Ms
1.78
mr
1.50
Ms
1.50
Mrs
1.43
Mister
1.42
Messrs
1.42
MR
1.32
Activations Density 3.318%