INDEX

Explanations

numbers and specific codes

The neuron fires whenever it sees a standalone numeric token (i.e. digits making up numbers) in the text.

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

for

-2.09

was

-1.61

are

-1.59

has

-1.44

on

-1.41

 Это

-1.38

if

-1.38

He

-1.38

in

-1.37

 would

-1.34

POSITIVE LOGITS

躥

1.58

你有

1.56

خیلی

1.52

縢

1.50

Actually

1.50

VERY

1.49

夲

1.48

苙

1.48

 vosotros

1.45

 смогли

1.45

Activations Density 0.011%