INDEX

Explanations

underscore separated words and version numbers

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

-0.50

cines

-0.50

 inter

-0.47

 subject

-0.47

 undertaking

-0.45

 part

-0.44

rem

-0.44

 general

-0.44

้ว

-0.44

ANTO

-0.43

POSITIVE LOGITS

 kasarigan

1.10

 betweenstory

1.09

SourceChecksum

1.08

AndEndTag

0.96

AddTagHelper

0.95

expandindo

0.94

 Roskov

0.93

 tartalomajánló

0.89

 سكانية

0.86

RetentionPolicy

0.84

Activations Density 0.087%