INDEX

Explanations

associative learning and Leviticus

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

殽

-2.75

does

-2.67



-2.66

快要

-2.59

スポンサーリンク

-2.48

部分が

-2.41

緲

-2.41

almost

-2.39

変わらず

-2.30

很不

-2.30

POSITIVE LOGITS

↵↵

2.39

ный

2.36

</strong>

2.34

ות

2.33

ский

2.28

↑↑↑</

2.19

嗵

2.14

鴆

2.14

 What

2.09

<i>

2.06

Activations Density 0.044%