INDEX

Explanations

long type declarations

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

鶿

-1.58

PasswordEncoder

-1.56

 }}"></

-1.55

絝

-1.48

емым

-1.44

жнарод

-1.41

 商店

-1.41

⚣

-1.39

tirer

-1.38

 体育

-1.37

POSITIVE LOGITS

1.77

an

1.69

1.67

琑

1.55

1.49

cestershire

1.38

1.36

也在

1.35

owę

1.34

<bos>

1.33

Activations Density 0.004%