INDEX

Explanations

because of the

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igel

-0.08

 blamed

-0.08

 tale

-0.08

 tallest

-0.08

 guts

-0.08

 erst

-0.08

 sophistic

-0.08

 fray

-0.07

Bes

-0.07

 weakest

-0.07

POSITIVE LOGITS

 fact

0.37

fact

0.30

 lack

0.24

Fact

0.23

 absence

0.23

 nature

0.23

 Fact

0.22

 rarity

0.21

 presence

0.21

nature

0.19

Activations Density 0.242%