INDEX

Explanations

IB Tutor, Grand Prix, Guys Outfits

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

 która

-1.71

 razu

-1.64

Pokud

-1.63

⠀⠀

-1.60

無論

-1.58

ของ

-1.56

 chargeur

-1.53

昨年

-1.53

 우리

-1.52

 narzęd

-1.50

POSITIVE LOGITS

is

1.80

↵↵

1.77

was

1.66

</h2>

1.59

mes

1.55

Leírás

1.52

in

1.43

ts

1.41

際は

1.41

↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.40

Activations Density 0.126%