INDEX

Explanations

label, introduction, or Supreme Court

The neuron is picking out numeric literals.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

you

-1.73

 their

-1.71

↵↵

-1.71

in

-1.64

or

-1.46

if

-1.45

 from

-1.39

on

-1.29

and

-1.26

 begin

-1.24

POSITIVE LOGITS

 seçenek

1.58

Ecco

1.50

了一個

1.31

Ingredienti

1.30

 ailing

1.30

各種

1.29

 revamped

1.27

噓

1.27

 Fucking

1.27

Sì

1.27

Activations Density 0.000%