INDEX
Explanations
occurrences of the letters "sch" and related variations
New Auto-Interp
Negative Logits
ensa
-0.17
sez
-0.15
ombok
-0.15
nard
-0.15
ngr
-0.15
ohen
-0.15
och
-0.15
405
-0.15
olerance
-0.15
agine
-0.15
POSITIVE LOGITS
wing
0.20
lag
0.20
rank
0.19
rift
0.18
mer
0.18
loss
0.17
on
0.17
aff
0.16
web
0.16
ikan
0.16
Activations Density 0.013%