INDEX

Explanations

use statements in code

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

-1.60

 resulting

-1.45

 žád

-1.39

 destined

-1.36

 importância

-1.34

 erstmal

-1.30

Ді

-1.26

Основные

-1.24

情況

-1.23

 будут

-1.23

POSITIVE LOGITS

!!</

1.45

躥

1.41

nós

1.41

受欢迎

1.41

1.38

gió

1.37

knię

1.36

 Kró

1.36

❗

1.34

cours

1.32

Activations Density 0.023%