INDEX

Explanations

fill in the specifics

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

𝒐

3.20

 égard

2.86

diği

2.79

 getUserBy

2.72

ารณา

2.69

त्रेयी

2.68

dete

2.67

🏻

2.62

 опо

2.59

ೆಯನ್ನು

2.58

POSITIVE LOGITS

wiches

2.49

্ধ্য

2.29

 سان

2.20

iin

2.14

 living

2.09

قص

2.05

{}",

2.05

ׂ

2.02

Fate

2.01

áu

1.94

Activations Density 0.014%