INDEX

Explanations

question, ASCII, code, or scan

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

 stick

-0.81

 Dokumentation

-0.79

正面

-0.78

 briefing

-0.78

 profile

-0.77

통

-0.77

gemene

-0.77

 PLWABN

-0.77

 България

-0.75

kript

-0.75

POSITIVE LOGITS

 scanned

1.71

 digitized

1.71

 scans

1.50

 scan

1.43

 Google

1.38

Scan

1.36

scan

1.34

OCR

1.34

Google

1.31

 scanning

1.27

Activations Density 0.051%