INDEX

Explanations

function definitions and code blocks

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

ंछ

2.53

ğa

2.46

pars

2.41

ऍ

2.33

 состав

2.32

скопа

2.30

ؤ

2.29

 condicion

2.25

embed

2.24

รส

2.23

POSITIVE LOGITS

ted

3.00

ting

2.50

="_

2.43

sd

2.32

lessly

2.21

ten

2.07

tl

2.02

います

2.00

tan

1.98

nya

1.94

Activations Density 0.555%