INDEX

Explanations

coordinates and measurements

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

-1.59

ङ

-1.51

but

-1.48

liğini

-1.39

 démoc

-1.39

塒

-1.35

 bisogna

-1.34

moreland

-1.34

😑

-1.34

heureusement

-1.33

POSITIVE LOGITS

of

1.59

for

1.48

her

1.40

свя

1.37

1.34

 with

1.32

cées

1.31

 تھے

1.30

1.26

in

1.24

Activations Density 0.005%