INDEX

Explanations

research

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ProtoMessage

-0.79

CopyWith

-0.77

 AssemblyCompany

-0.77

parsedMessage

-0.74

 "..\..\

-0.71

 calendriers

-0.68

 stands

-0.67

astéroïdes

-0.64

 onOptions

-0.60

Driven

-0.57

POSITIVE LOGITS

woordig

0.50

 lauter

0.47

">*</

0.46

Spoljašnje

0.42

erdings

0.42

 rechter

0.41

Ruff

0.39

утбо

0.39

TestTools

0.39

lamabad

0.39

Activations Density 0.001%