INDEX

Explanations

fall, failing, or error

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

чил

2.92

කාශ

2.52

 khớp

2.49

ૃત

2.45

िज्या

2.43

 Fhir

2.42

்

2.40

 caixa

2.36

搅拌

2.36

angular

2.35

POSITIVE LOGITS

”“

2.36

.”[

2.33

𝒊

2.33

<bos>

2.29

]);}

2.27

.”—

2.18

yu

2.16

loss

2.12

ಯಲ್ಲಿ

2.09

.”

2.08

Activations Density 0.308%