INDEX

Explanations

summation and integral notation

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

-2.52

);

-2.50

捎

-2.48

liseum

-2.45

 sicheren

-2.36

都有

-2.28

begin

-2.27

 speziellen

-2.22

 achieving

-2.20

 gemeinsamen

-2.20

POSITIVE LOGITS

韡

2.67

 från

2.50

 händer

2.42

⦊

2.39

Pemer

2.38

 organik

2.31

轵

2.31

 diki

2.30

 fortsatt

2.27

 kalem

2.27

Activations Density 0.005%