INDEX

Explanations

asking for more information

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

вере

1.57

 nations

1.53

 governments

1.51

pilot

1.45

𝒊

1.44

ність

1.39

ってい

1.38

creator

1.37

pil

1.36

्र

1.36

POSITIVE LOGITS

 học

1.76

 Học

1.68

шк

1.62

शास्त्र

1.61

 Shack

1.59

學

1.59

学家

1.57

 Onion

1.55

学的

1.55

 bàn

1.54

Activations Density 0.305%