INDEX

Explanations

references to a specific proper noun, likely a name or title

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

 ModelExpression

-0.62

 trajets

-0.58

READY

-0.55

Portály

-0.52

Ready

-0.50

StructEnd

-0.50

IANGLES

-0.50

 DataTypes

-0.49

spaceBetween

-0.48

もちゃ

-0.48

POSITIVE LOGITS

mir

2.75

Mir

2.50

Mir

2.44

MIR

2.28

mir

2.22

MIR

1.95

 Mira

1.09

 mira

1.09

Mira

1.08

 Miranda

1.05

Activations Density 0.002%