INDEX
Explanations
occurrences of the substring "ent"
New Auto-Interp
Negative Logits
ing
-0.17
flt
-0.15
thems
-0.15
Sheila
-0.14
ERO
-0.14
impulse
-0.14
eto
-0.14
oc
-0.14
ARB
-0.14
iple
-0.13
POSITIVE LOGITS
idot
0.16
UGE
0.15
ENO
0.15
acas
0.14
hare
0.14
otal
0.14
.nih
0.14
doma
0.14
.EventArgs
0.14
ieten
0.14
Activations Density 0.022%