INDEX

Explanations

fax number

The main thing this neuron does is detect numeric tokens (digits and 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

chae

-0.79

ttps

-0.75

 checker

-0.74

 Philharmonic

-0.73

wala

-0.73

getUid

-0.73

iffion

-0.73

》

-0.72

 trachea

-0.72

 Spotify

-0.72

POSITIVE LOGITS

fax

5.22

Fax

4.34

Fax

4.16

fax

4.03

FAX

3.52

FAX

3.48

fa

1.88

 facsimile

1.84

 фак

1.56

фак

1.55

Activations Density 0.070%