INDEX

Explanations

final piece of data

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

owne

0.58

 руках

0.57

 अब्

0.55

Deleting

0.53

 ثاني

0.52

 प्रश्

0.50

lll

0.49

 फस

0.49

yczne

0.49

 아닙

0.49

POSITIVE LOGITS

 robotic

0.46

 robotics

0.45

 vaginal

0.44

 gamb

0.44

 utama

0.44

 linearized

0.42

SIGNAL

0.42

enburg

0.42

AR

0.42

 amounts

0.42

Activations Density 0.000%