INDEX

Explanations

stories, comics, and novels

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

for

-1.88

in

-1.42

 importante

-1.35

 activ

-1.35

 افغان

-1.30

+#+

-1.24

 Formel

-1.20

୩

-1.20

}));

-1.19

⫽

-1.18

POSITIVE LOGITS

 häufiger

1.47

 détru

1.47

вів

1.46

 verbess

1.46

Če

1.29

 élar

1.28

 rafra

1.27

 obé

1.27

 soportar

1.23

 zusätz

1.23

Activations Density 0.073%