INDEX

Explanations

specific items and sensory descriptions

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

 complètement

-1.55

 derselben

-1.42

 regering

-1.40

 appeler

-1.39

籀

-1.35

 penser

-1.34

幛

-1.34

 apporter

-1.34

 adesivos

-1.30

眎

-1.30

POSITIVE LOGITS

and

2.06

but

1.78

in

1.43

as

1.41

all

1.34

 through

1.27

 first

1.20

 nestled

1.19

if

1.19

 epitom

1.18

Activations Density 0.013%