INDEX

Explanations

lookup tables and policies

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

esercito

-0.93

SUITE

-0.91

นี้

-0.91

怎麼

-0.90

 liel

-0.88

hilterra

-0.88

Associazione

-0.87

臊

-0.86

 rapist

-0.84

 décisions

-0.83

POSITIVE LOGITS

 Look

1.32

look

1.30

 👀

1.15

 LOOK

1.14

Look

1.13

LOOK

0.91

 Lookout

0.90

 intend

0.88

ups

0.86

 Into

0.85

Activations Density 0.011%