INDEX

Explanations

documentation comments

The neuron fires on long runs of space characters (i.e. code indentation).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

توضیحات

-1.29

tembro

-1.28



-1.24

its

-1.20

ίου

-1.19

Trichloroethane

-1.18

geç

-1.13

quelize

-1.13

ㆁ

-1.12

 மற்றும்

-1.11

POSITIVE LOGITS

1.56

1.49

‘

1.39

1.34



1.25

1.23

“

1.23

1.22

’

1.20

”

1.15

Activations Density 0.004%