INDEX

Explanations

mathematical equation

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

ского

-2.91

粂

-2.59

 They

-2.45

，

-2.44

不会

-2.42

這

-2.41

的一

-2.39

یرات

-2.33

-2.30

This

-2.28

POSITIVE LOGITS

 verbess

3.09

↵

2.98

2.70

2.66

 Hinblick

2.52

2.39

焌

2.38

哢

2.31

 besonder

2.25

 Empfehlung

2.20

Activations Density 0.006%