INDEX

Explanations

document context or type

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dilapidated

-1.13

اء

-1.09

 vorigen

-1.07

大腿

-1.07

 وقتی

-1.02

⻬

-1.01

geführt

-1.00

地点

-1.00

 abject

-1.00

 goddamn

-0.98

POSITIVE LOGITS

 Document

1.73

document

1.58

Document

1.55

 Dokument

1.48

ations

1.47

doc

1.39

ATION

1.39

Doc

1.35

 documents

1.31

 document

1.29

Activations Density 0.039%