INDEX

Explanations

initial-scale=1

The neuron fires on numeric tokens (digit sequences), in particular the numbers specifying the viewport’s initial-scale in HTML meta tags.

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

verlet

-1.23

merken

-1.23

rechter

-1.21

 srebr

-1.20

kennen

-1.20

wendige

-1.19

standen

-1.16

 SECOND

-1.16

 Sekret

-1.16

 Onze

-1.15

POSITIVE LOGITS

 manifested

1.40

 certainly

1.35

 already

1.34

 obviously

1.30

 different

1.25

 enormously

1.25

 exclusively

1.20

 roughly

1.20

 perfectly

1.18

 comprehensively

1.16

Activations Density 0.064%