INDEX

Explanations

legal and disclaimer language

words related to "disclosure"

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

XmlType

-0.50

chnet

-0.49

gettimeofday

-0.47

SourceChecksum

-0.46

appspot

-0.45

localctx

-0.44

InitVars

-0.43

 asist

-0.43

 Execution

-0.43

ficulties

-0.42

POSITIVE LOGITS

dis

1.00

DIS

0.93

dis

0.91

 disclosure

0.91

Dis

0.90

Dis

0.88

 disclose

0.83

 disclosures

0.78

 disclosing

0.78

DIS

0.75

Activations Density 2.097%