INDEX

Explanations

code blocks and imports

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

⅘

-1.39

ühle

-1.31

 dibujado

-1.29

nischen

-1.28

 llenar

-1.23

sistencia

-1.20

 habia

-1.20

reality

-1.17

 aña

-1.16

切る

-1.16

POSITIVE LOGITS

 this

1.77

–

1.60

to

1.50

 that

1.45

：……

1.34

火的

1.34

это

1.27

;->

1.27

 Schülern

1.22

 られ

1.19

Activations Density 0.024%