INDEX

Explanations

availability and opening

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

<tr>

-1.28

苼

-1.26

łóż

-1.24

،

-1.23

<th>

-1.22

 поколения

-1.20

卝

-1.20

泐

-1.19

ペン

-1.19

 ajout

-1.18

POSITIVE LOGITS

for

1.65

 dibuka

1.43

tradu

1.32

 opening

1.31

our

1.30

 opened

1.30

ajuste

1.30

its

1.29

 this

1.28

 beroperasi

1.28

Activations Density 0.053%