INDEX

Explanations

words that describe architectural features of a building

ceilings

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

principalTable

-0.69

 Carab

-0.63

 Shakspeare

-0.62

DJANGO

-0.60

 juſ

-0.60

 Macca

-0.56

uisine

-0.54

￡

-0.54

Carriera

-0.53

 snippetHide

-0.52

POSITIVE LOGITS

Ce

0.66

 vaulted

0.59

 False

0.59

 ciel

0.58

cel

0.56

 пото

0.56

 Пото

0.54

Ce

0.53

ce

0.52

tedrale

0.52

Activations Density 0.438%