INDEX

Explanations

Text

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 shock

-0.65

 soap

-0.62

 Text

-0.55

Text

-0.54

IST

-0.51

soap

-0.50

Soap

-0.48

iste

-0.48

Un

-0.47

istu

-0.47

POSITIVE LOGITS

 AssemblyCulture

1.23

 OMITBAD

1.12

 ModelExpression

1.09

 pinulongan

1.06

 ainfi

1.06

Autoritní

1.05

enderror

1.04

berdayakan

1.04

 Normdatei

1.03

SBATCH

1.02

Activations Density 0.998%