INDEX

Explanations

means, class, literature, special

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

 mujeres

-1.34

 fır

-1.32

cting

-1.30

zyms

-1.29

reicher

-1.29

nits

-1.28

titur

-1.27

 extrait

-1.27

⦅

-1.25

ljeno

-1.24

POSITIVE LOGITS

by

1.91

 both

1.57

 there

1.57

 even

1.43

 ścian

1.35

1.32

 should

1.30

 There

1.27

 here

1.26

 will

1.23

Activations Density 0.144%