INDEX

Explanations

with the

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

 también

-1.30

っとり

-1.29

sometimes

-1.23

without

-1.23

 شده

-1.22

WITHOUT

-1.21

 originali

-1.16

})}

-1.16

了起来

-1.13

ferences

-1.13

POSITIVE LOGITS

thodoxy

1.48

 после

1.36

tiest

1.34

nyard

1.30

 after

1.29

any

1.27

URRED

1.27

صبح

1.26

ressee

1.25

antism

1.24

Activations Density 0.066%