INDEX

Explanations

internet addresses

The neuron fires on URL components (e.g. “http”, “://”, “.com”, “.org”, “.edu” etc.), effectively detecting web addresses.

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

 vorhandenen

-1.16

 què

-1.14

 vorbere

-1.13

 vorhand

-1.11

 wöch

-1.09

 llevará

-1.08

 umfang

-1.05

お部屋

-1.04

 genügend

-1.04

 zusätz

-1.03

POSITIVE LOGITS

1.24

锱

1.13

._

1.10

😲

1.09

😱

1.08

 which

1.08

🎃

1.05

🤯

1.03

ʿ

1.03

🤬

1.02

Activations Density 0.053%