INDEX
Explanations
mentions of specific individuals, particularly titles and names
New Auto-Interp
Negative Logits
alam
-0.16
ettle
-0.14
burn
-0.14
á»ĭ
-0.14
_Lean
-0.14
ÑģÑı
-0.14
.WinForms
-0.14
kerja
-0.14
utivo
-0.13
alo
-0.13
POSITIVE LOGITS
afari
0.14
olia
0.14
wil
0.14
aze
0.14
esta
0.13
raw
0.13
Ard
0.12
esco
0.12
ocre
0.12
onia
0.12
Activations Density 0.036%