INDEX
Explanations
names and terms related to people or items ending in "ay" or "ray"
New Auto-Interp
Negative Logits
inia
-0.18
sy
-0.18
iate
-0.18
iams
-0.18
iy
-0.17
s
-0.17
erable
-0.16
su
-0.16
bih
-0.16
Riley
-0.16
POSITIVE LOGITS
ward
0.29
yyyy
0.23
theon
0.21
eb
0.21
enne
0.21
yyy
0.20
ÌĪ
0.20
urved
0.20
den
0.20
alnız
0.20
Activations Density 0.142%