INDEX

Explanations

]

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kloped

-0.63

-0.60

WithMany

-0.59

يميديا

-0.57

 سكانية

-0.57

ectoria

-0.56

The

-0.56

 Wiktionnaire

-0.55

And

-0.53

asantry

-0.52

POSITIVE LOGITS

 Jurí

0.67

 asiático

0.53

parsedMessage

0.52

 Democrá

0.52

[];

0.50

team

0.50

 Jefus

0.49

 myſelf

0.48

 Autónoma

0.48

 himſelf

0.48

Activations Density 0.006%