INDEX

Explanations

platforms

without needing

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

 Archae

0.52

 Empres

0.51

 Optimization

0.50

 Repairs

0.50

 Bakın

0.50

 Antônio

0.50

 Injuries

0.49

 الترب

0.49

 آف

0.49

 Ingers

0.49

POSITIVE LOGITS

bot

0.47

 बारह

0.47

bereit

0.47

by

0.46

 namesake

0.46

at

0.44

robot

0.44

 ਕੀ

0.44

를

0.43

convert

0.42

Activations Density 0.000%