INDEX

Explanations

public followed by code construct

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

by

-1.62

？』

-1.57

as

-1.44

ции

-1.41

at

-1.41

ﾄ

-1.34

があります

-1.33

for

-1.32

 There

-1.32

IANGLES

-1.27

POSITIVE LOGITS

来週

1.47

為に

1.44

 insanely

1.41



1.31

かなりの

1.27

めちゃくちゃ

1.26

thc

1.26

久し

1.25

けっこう

1.25

だいぶ

1.24

Activations Density 0.003%