INDEX
Explanations
instances of the word "born" and its variations
New Auto-Interp
Negative Logits
ctor
-0.17
unas
-0.16
Emb
-0.16
oley
-0.15
emi
-0.14
ppard
-0.14
itti
-0.14
uria
-0.14
antar
-0.14
iban
-0.14
POSITIVE LOGITS
avirus
0.20
into
0.17
holm
0.16
åij½åij¨æľŁ
0.16
éo
0.15
place
0.15
raised
0.14
ãģ¾ãĤĮ
0.14
_into
0.14
raised
0.14
Activations Density 0.024%