INDEX

Explanations

references like [@B] or [@CR]

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

of

-1.41

thang

-1.39

の人に

-1.33

untuk

-1.27

and

-1.22

 También

-1.20

 frança

-1.20

plastik

-1.19

lorn

-1.17

の方に

-1.17

POSITIVE LOGITS

 Innenstadt

1.10

1.08

 differing

1.06

 localObject

1.05

 scrittore

1.04

但这

1.03

但在

1.03

any

1.02

ÁCT

1.02

但却

1.01

Activations Density 0.061%