INDEX
Explanations
sentences that begin or contain punctuation
New Auto-Interp
Negative Logits
.uf
-0.16
less
-0.15
.mc
-0.15
ãģĹãģ®
-0.14
ÑģÑĤанов
-0.14
ÑģпÑĢоÑģил
-0.14
ayla
-0.14
inya
-0.14
ãĥ³ãĤ¬
-0.14
oba
-0.13
POSITIVE LOGITS
ë¡Ģ
0.15
cate
0.15
ãĥ¼ãĤ¹
0.14
ereum
0.14
MOTE
0.14
ebek
0.14
ิà¸ļ
0.13
.Apis
0.13
COPE
0.13
Harm
0.13
Activations Density 0.064%