INDEX

Explanations

titles and honorifics

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

-1.37

 this

-1.27

 these

-1.21

to

-1.16

an

-1.12

 tuyo

-1.09

 those

-1.05

 ditem

-1.02

 around

-1.01

 locations

-1.00

POSITIVE LOGITS

owanie

1.19

rhosis

1.19

 Quận

1.09

 Năm

1.09

ntilde

1.09

AYA

1.08

 charisma

1.05

來到

1.04

hidupan

1.04

 cheveux

1.04

Activations Density 0.004%