INDEX

Explanations

The neuron detects mentions of Internet domain names or top‐level domains (e.g. “.com,” “domain,” “website”).

domain names

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

 works

-1.30

 feltro

-1.30

 evening

-1.27

acked

-1.23

 teaching

-1.22

centerX

-1.20

 gosta

-1.19

 misteriosa

-1.17

 estran

-1.17



-1.16

POSITIVE LOGITS

 your

1.32

for

1.30

 sizi

1.20

衞

1.16

ụy

1.16

спользова

1.15

 vanity

1.13

спользу

1.11

 name

1.10

While

1.10

Activations Density 0.024%