INDEX

Explanations

how to make something

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

we

-2.84

 then

-2.28

 ailing

-2.27

 入っ

-2.17

gefügt

-2.09

一切都

-2.06

 एक

-2.05

 fringes

-2.05

 defunct

-2.05

href

-2.03

POSITIVE LOGITS

ка

2.86

笮

2.50

ஂ

2.48

𓋼

2.44

骓

2.39

髏

2.33

 fahren

2.30

...");

2.30

 cruda

2.23

蹚

2.22

Activations Density 0.007%