INDEX

Explanations

optical writing, converts light

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

-2.03

所有

-1.83

他的

-1.70

so

-1.57

 chodzi

-1.55

is

-1.52

 какие

-1.49

(/^

-1.49

no

-1.46

for

-1.43

POSITIVE LOGITS

 another

1.51

the

1.40

了过来

1.39

を購入

1.39

 evidentemente

1.38

⦁

1.38

 other

1.35

歿

1.32

 adequad

1.31

 that

1.30

Activations Density 0.048%