INDEX

Explanations

connector words like 'and'

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

in

-1.72

çou

-1.68

 memutus

-1.63

わけで

-1.52

 notare

-1.39

 eikä

-1.38

 aumentare

-1.37

 lalu

-1.35

at

-1.35

 merusak

-1.34

POSITIVE LOGITS

and

9.38

และ

4.00

и

3.06

和

2.83

\&

2.63

 και

2.59

및

2.53

2.47

 மற்றும்

2.44

și

2.34

Activations Density 1.064%