INDEX

Explanations

published on dates

certain words and following punctuation

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

0.44

 were

0.44

CA

0.43

Smith

0.43

Were

0.43

▂

0.43

CO

0.42

were

0.41

Ever

0.41

••••

0.40

POSITIVE LOGITS

awać

0.51

 تیاری

0.50

 প্রয়োজনীয়

0.48

 तैयारी

0.48

䛶

0.47

绑

0.47

 bağ

0.47

 ضروری

0.47

 ሂደ

0.46

<unused98>

0.46

Activations Density 0.001%