INDEX

Explanations

adjective + noun

descriptive adjective noun phrases

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

 συγκεκρι

0.55

🏯

0.47

వలం

0.46

 উপলক্ষে

0.45

letion

0.44

 HAVING

0.43

よりも

0.43

operasi

0.42

eningkatan

0.42

一

0.41

POSITIVE LOGITS

0.46

eacute

0.41

0.40

untuk

0.40

ஞான

0.37

 എന്നിവ

0.37

Ve

0.36

yellow

0.36

 retort

0.36

ث

0.35

Activations Density 0.888%