INDEX
Explanations
mentions of the name "Adam"
New Auto-Interp
Negative Logits
icers
-0.17
lix
-0.17
erta
-0.16
eken
-0.16
ochen
-0.14
pst
-0.14
evin
-0.14
(*)(
-0.14
çŃĴ
-0.14
eking
-0.14
POSITIVE LOGITS
antine
0.26
antium
0.24
antly
0.24
antino
0.20
sville
0.18
son
0.18
u
0.17
ant
0.17
.Adam
0.17
sonian
0.17
Activations Density 0.006%