INDEX

Explanations

Numbers in different languages

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

 prochaines

-0.59

GEBURTSDATUM

-0.54

 laikā

-0.49

 lèvres

-0.48

 helft

-0.47

 idées

-0.47

UnusedPrivate

-0.46

 frattempo

-0.46

각주

-0.46

true

-0.45

POSITIVE LOGITS

two

1.30

 three

1.22

 four

1.00

 several

0.97

 five

0.90

 deux

0.88

two

0.84

 trois

0.82

six

0.78

 zwei

0.77

Activations Density 0.001%