INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 صوتيه

-0.91

ArrowToggle

-0.88

 سكانية

-0.87

 GenerationType

-0.85

 ویکی‌پدی

-0.82

 referenties

-0.80

 chi̍t

-0.77

oredCriteria

-0.77

 '\\;'

-0.76

 nahilalakip

-0.75

POSITIVE LOGITS

 strong

0.43

帖最后由

0.41

 long

0.39

 Архивировано

0.36

е

0.34

 Post

0.34

Post

0.33

 fortes

0.32

лов

0.32

Activations Density 0.000%

No Known Activations