INDEX

Explanations

Gmail, omni, Camille Norment

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

 sólida

-2.47

あれば

-2.42

-2.36

踽

-2.25

 obicei

-2.23

 rígida

-2.23

 were

-2.23

 buscas

-2.20



-2.19

说的

-2.16

POSITIVE LOGITS

 When

2.66

 What

2.63

_);

2.38

 THERE

2.33

ziert

2.31

 While

2.30

佧

2.28

}\}$

2.23

 eine

2.23

 There

2.23

Activations Density 0.004%