INDEX

Explanations

severity

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

Hochspringen

-0.62

okkal

-0.52

‍♂️

-0.51

 propOrder

-0.49

Revenir

-0.48

statuses

-0.47

 Whitman

-0.47

 everyone

-0.47

 Wayback

-0.46

POSITIVE LOGITS

BeginContext

0.54

 injuries

0.52

ICOLON

0.49

GraphicsUnit

0.49

rawDesc

0.49

Rptr

0.49

 drafted

0.48

ضات

0.48

 defaultstate

0.48

PreExecute

0.47

Activations Density 0.076%