INDEX

Explanations

all and related concepts

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

".

-1.47

⇹

-1.41

."

-1.40

 Uniwers

-1.38

guia

-1.37

</th>

-1.36

"/>

-1.34

 Keto

-1.32

“.

-1.32

”.

-1.32

POSITIVE LOGITS

adone

1.57

 wszystkich

1.53

 cauza

1.50

 스톡

1.49

Minha

1.48

ズニー

1.45

 obicei

1.41

 ネタバレ

1.41

 cadrul

1.40

ทั้งหมด

1.40

Activations Density 0.006%