INDEX

Explanations

who followed by a verb

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

and

-2.56

and

-1.57

 এবং

-1.49

蓠

-1.34

 ofrece

-1.30

んでも

-1.29

 работа

-1.28

～

-1.27

of

-1.27

llten

-1.27

POSITIVE LOGITS

has

1.55

is

1.44

ﾍ

1.41

after

1.38

 despite

1.34

Več

1.31

 after

1.30

 moldura

1.30

感じです

1.29

 geladeira

1.29

Activations Density 0.066%