INDEX

Explanations

apologies and excitement

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 buzz

-0.83

Seems

-0.64

buzz

-0.64

 Seems

-0.61

seems

-0.60

 seems

-0.59

basically

-0.53

 basically

-0.52

 sorry

-0.51

Buzz

-0.51

POSITIVE LOGITS

ed

0.83

0.71

protoimpl

0.69

pires

0.68

_;

0.63

edale

0.63

utnik

0.63

ivably

0.63

/**

0.63

Personendaten

0.63

Activations Density 1.747%