INDEX

Explanations

countries and regions

The neuron primarily detects numerical expressions (digits, durations, percentages, prices) 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

of

-1.92

-1.42

毉

-1.28

OOTDTY

-1.27

曏

-1.27

就

-1.25

⎘

-1.24

と呼ばれる

-1.23

 queria

-1.23

Sábado

-1.22

POSITIVE LOGITS

or

2.33

 this

2.23

涑

1.73

ďte

1.70

 твои

1.61

ってください

1.59

 этом

1.55

 your

1.54

 ataupun

1.52

You

1.48

Activations Density 0.100%