INDEX

Explanations

shock, attack, fear

The neuron fires on words that denote sudden shock or surprise reactions (e.g. startled, shock, heart attack, scared, surprise).

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

to

-1.34

end

-1.29

-1.27

type

-1.24

-1.21

 Need

-1.16

lab

-1.16

-1.14

 Both

-1.12

new

-1.11

POSITIVE LOGITS

😱

1.61

нении

1.46

 különböz

1.34

änemark

1.32

likler

1.31

取决

1.30

лтемелер

1.28

biť

1.27

镦

1.24

timme

1.23

Activations Density 0.031%