INDEX

Explanations

starts of phrases or words

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

-1.71

-1.47

 були

-1.44

可以

-1.42

the

-1.42

-1.30

’

-1.28

 nebst

-1.25

-1.23

现在的

-1.23

POSITIVE LOGITS

 abuelos

1.41

一笑

1.41

⸂

1.41

ALLED

1.40

стреча

1.38

･･

1.36

uesia

1.34

 χρησιμοποι

1.34

 головой

1.30

berfläche

1.29

Activations Density 0.005%