INDEX

Explanations

double preceding other words

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

gol

-0.83

の一覧

-0.77

 रे

-0.75

⌣

-0.75

 зни

-0.75

term

-0.75

uterie

-0.74

وين

-0.74

it

-0.72

多元

-0.72

POSITIVE LOGITS

 double

1.35

double

1.30

 двой

1.28

Double

1.27

 Double

1.23

ToDouble

1.13

 DOUBLE

1.11

DOUBLE

1.02

 doble

0.99

双

0.97

Activations Density 0.043%