INDEX

Explanations

custom-fitted, custom-built, customization

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

<bos>

3.09

е

2.23

রোপ

2.21

 décret

2.21

iminary

2.15

𝙧

2.12

க்கோ

2.12

▂

2.11

ι

2.11

ሢ

2.09

POSITIVE LOGITS

Dims

2.40

вайте

2.16

 Intelig

2.16

des

2.11

 بالله

2.09

 дыха

2.08

 atop

2.08

 دلچ

2.04

Oops

2.04

жливо

2.04

Activations Density 0.011%