INDEX

Explanations

ago

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

ago

-0.76

 resté

-0.71

 AssemblyCulture

-0.67

`,

-0.63

 myö

-0.61

følgelig

-0.60

 Numerade

-0.59

 später

-0.59

tvguidetime

-0.59

")));

-0.58

POSITIVE LOGITS

0.60

Personendaten

0.57

 للاسماء

0.53

or

0.53

Gemeinsame

0.52

VolleyError

0.50

er

0.47

 Bridget

0.46

 Thrones

0.45

Activations Density 0.026%