INDEX

Explanations

limited or restricted scope

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

⃣

-1.46



-1.41

 关于

-1.37

 összefoglaló

-1.32

 fotograf

-1.30

 OGSÅ

-1.28

 dieux

-1.26

<bos>

-1.24

簟

-1.23

輳

-1.22

POSITIVE LOGITS

to

2.30

but

1.74

1.71

1.67

if

1.67

that

1.62

1.58

).

1.56

Anyone

1.54

 operazioni

1.53

Activations Density 0.031%