INDEX

Explanations

introducing statements with 'that'

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

 який

-1.85

 яка

-1.59

 レザー

-1.56

𝖨

-1.53

yonel

-1.50

◛

-1.50

nischen

-1.48

 イエロー

-1.40

 皇族

-1.39

Siapa

-1.38

POSITIVE LOGITS

 that

13.75

 که

4.59

 rằng

3.48

 bahwa

3.47

 που

3.39

 что

3.33

ว่า

3.23

that

2.95

 שה

2.95

że

2.81

Activations Density 0.870%