INDEX

Explanations

french determiners

les

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

 Houſe

-0.66

 Shakspeare

-0.64

 Cæsar

-0.64

astify

-0.64

 lèvres

-0.63

ViewImports

-0.62

 pattes

-0.62

 testamento

-0.61

Efq

-0.60

 oreilles

-0.60

POSITIVE LOGITS

Jeografia

0.66

createCanvas

0.57

awtextra

0.56

ۇ

0.53

جغرافيا

0.53

uns

0.51

netinet

0.50

twimg

0.50

blings

0.49

ab

0.48

Activations Density 0.475%