INDEX

Explanations

data access objects, persistence

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

 Hinblick

-1.77

 reveló

-1.69

などが

-1.68

 manifestó

-1.67

 применение

-1.64

 Ensuring

-1.63

 desarrolló

-1.63

 myriad

-1.58

 ajusta

-1.56

 комнаты

-1.53

POSITIVE LOGITS

<bos>

2.36

We

1.84

$.

1.73

مدينة

1.53

er

1.45

❧

1.44

 juga

1.41

 this

1.36

 these

1.34

Activations Density 0.002%