INDEX

Explanations

punctuation and 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

mappings

-0.76

🥈

-0.75

 Suez

-0.75

Uso

-0.70

 Zweifel

-0.69

ATTN

-0.67

 capuche

-0.66

 Peggy

-0.66

ATT

-0.66

OBJ

-0.66

POSITIVE LOGITS

 được

0.68

ordon

0.66

Const

0.63

機構

0.63

ilas

0.63

art

0.63

 Amritsar

0.63

subsubsection

0.60

zám

0.60

enc

0.60

Activations Density 0.037%