INDEX
Explanations
occurrences of the name "John" and its variations
New Auto-Interp
Negative Logits
itious
-0.19
apk
-0.18
lect
-0.15
oce
-0.15
lication
-0.14
ilma
-0.14
cae
-0.14
_MPI
-0.14
orget
-0.14
lector
-0.14
POSITIVE LOGITS
athan
0.35
nie
0.26
athon
0.23
son
0.21
ston
0.21
atan
0.20
sWith
0.20
sen
0.19
stone
0.19
sons
0.18
Activations Density 0.032%