INDEX

Explanations

adjective descriptors of quality

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

ኵ

-1.70

os

-1.67

ዣ

-1.54

不舒服

-1.48

 biß

-1.45

 diriger

-1.44

芣

-1.44

就好了

-1.44

 jahre

-1.41

蕖

-1.40

POSITIVE LOGITS

in

1.53

 those

1.43

 these

1.41

we

1.36

 they

1.27

 other

1.25

>();

1.25

 with

1.24

 Probes

1.23

جرة

1.21

Activations Density 0.107%