INDEX

Explanations

look followed by descriptors

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

of

-1.69

 Fantastic

-1.61

 Fifteen

-1.59

することが

-1.58

 juſ

-1.54

脔

-1.53

躰

-1.53

 fantastic

-1.51

Ꮚ

-1.48

の中では

-1.47

POSITIVE LOGITS

 hasten

1.45

 aids

1.32

 parallels

1.30

⚜

1.30

'}

1.27

 nearing

1.25

 zvíř

1.23

 sinte

1.20

由

1.20

 alın

1.18

Activations Density 0.012%