INDEX

Explanations

surface or container parts

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

企业的

-1.45

:</

-1.31

th

-1.27

 могла

-1.24

 accounting

-1.22

org

-1.22

难过

-1.20

璎

-1.20

 Ecuador

-1.19

 kartą

-1.18

POSITIVE LOGITS

we

1.44

 motivadoras

1.37

 τρό

1.31

 digno

1.29

 rodilla

1.29

 Fuerzas

1.26

 buscar

1.21

 connue

1.19

 costado

1.18

of

1.16

Activations Density 0.007%