INDEX
Explanations
references to political scandals and related accusations
New Auto-Interp
Negative Logits
beginnetje
-0.60
DoubleQuotes
-0.59
fjspx
-0.55
BeginContext
-0.54
Mum
-0.53
tigung
-0.51
oprot
-0.49
وتسجيلات
-0.47
역사
-0.46
MetaType
-0.46
POSITIVE LOGITS
UserScript
0.60
interp
0.56
WebVitals
0.56
prefect
0.55
indeer
0.54
lious
0.54
indignant
0.51
hooded
0.51
denounced
0.50
GenerationType
0.49
Activations Density 0.279%