INDEX

Explanations

know what to expect

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

дой

-0.91

'])){

-0.78

strecke

-0.77

°•

-0.75

 '.';

-0.73

 przekon

-0.73

妹

-0.73

棟

-0.72

 mencu

-0.72

 décédé

-0.71

POSITIVE LOGITS

 expected

1.48

 EXPECT

1.42

 Expect

1.39

 expect

1.34

 Expected

1.26

 expects

1.23

 expectation

1.22

Expect

1.22

 expecting

1.14

 esperado

1.13

Activations Density 0.026%