INDEX

Explanations

examples of categories

The main thing this neuron does is detect numeric tokens (including integers and decimals) representing measurements or quantities.

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

 there

-1.64

着一个

-1.56

is

-1.55

-1.52

in

-1.50

日発売

-1.48

-1.44

-1.42

doras

-1.41

its

-1.39

POSITIVE LOGITS

 other

2.72

 anderen

2.16

 others

2.03

 various

1.98

 سایر

1.95

and

1.90

 this

1.84

อื่น

1.83

our

1.74

 with

1.69

Activations Density 0.143%