INDEX

Explanations

places or names

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

 настройки

-1.59

 hacían

-1.54

 probably

-1.41

 methods

-1.38

 soyez

-1.37

 χρησιμοποι

-1.37

 شهرد

-1.34

 techniques

-1.33

 nena

-1.32

 disediakan

-1.30

POSITIVE LOGITS

ּוֹ

1.48

这么多

1.45

 السياس

1.36

 остальных

1.36

 бампер

1.28

icoot

1.26

poe

1.24

颚

1.23

ний

1.23

 остальные

1.21

Activations Density 0.002%