INDEX

Explanations

parts, episodes, and sections

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

 другую

-1.45

 wichtigsten

-1.43

 другая

-1.34

もありますが

-1.34

igshid

-1.32

 problém

-1.30

koľvek

-1.30

 portavoz

-1.30

 inoltre

-1.29

 EconPapers

-1.28

POSITIVE LOGITS

it

2.19

and

2.09

 from

1.74

or

1.56

for

1.48

 which

1.48

 miliar

1.37

말

1.27

 augusti

1.26

Джере

1.24

Activations Density 0.294%