INDEX

Explanations

references to specific product categories or types

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

 Anti

-0.45

<eos>

-0.41

lla

-0.41

-0.40

是一

-0.40

вин

-0.40

di

-0.38

DR

-0.38

 Multi

-0.38

POSITIVE LOGITS

SourceChecksum

1.06

 Destinations

1.05

 Strains

1.04

 Bins

1.00

 Fields

0.99

 Hobbies

0.99

 Formats

0.98

 Viruses

0.98

 Fabrics

0.96

 Devices

0.96

Activations Density 0.183%