INDEX

Explanations

describing or description

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

PANY

-0.82

ึ้น

-0.79

ష్

-0.78

жением

-0.75

illotine

-0.74

🔚

-0.74

 Portail

-0.73

strijden

-0.73

 leçon

-0.72

Blick

-0.72

POSITIVE LOGITS

 description

7.41

 descriptions

6.72

 describe

6.13

description

5.88

 described

5.69

Description

5.63

 Description

5.53

 describing

5.53

 describes

5.31

 описа

5.16

Activations Density 0.287%