INDEX

Explanations

through other languages

The neuron strongly activates on numeric tokens (i.e. sequences of digits), marking where numbers occur 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

had

-1.12

٥

-1.11

 nếu

-1.07

なども

-1.06

אם

-1.05

 кото

-1.05

íté

-1.05

比较好

-1.05

if

-1.03

 océano

-1.03

POSITIVE LOGITS

 through

2.30

by

2.27

 durch

1.72

 above

1.64

 each

1.64

 this

1.62

 attraverso

1.58

 poprzez

1.56

 через

1.52

 melalui

1.49

Activations Density 0.075%