INDEX

Explanations

providing information

This neuron activates on occurrences of the word “information.”

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

1.60

ه

1.50

er

1.27

이자

1.24

1.23

ে

1.23

IT

1.21

ができ

1.20

RO

1.16

Dopo

1.15

POSITIVE LOGITS

ℹ

1.29

 अबाउट

1.27

 about

1.25

 información

1.23

 renseignements

1.16

 informace

1.16

 информация

1.15

 информацию

1.13

 Brochure

1.13

ോഷ

1.09

Activations Density 0.067%