INDEX

Explanations

religious services and gatherings

The neuron detects words referring to church or religious services and gatherings.

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

of

-1.97

т

-1.43

ceeds

-1.37

 Metern

-1.36

欒

-1.35

 tématu

-1.32

 okno

-1.30

而已

-1.30

 stylu

-1.30

 autory

-1.29

POSITIVE LOGITS

おはようございます

1.38

ディズニー

1.35

 same

1.35

あなたは

1.30

ƽ

1.28

隄

1.26

 diamètre

1.23

 equipa

1.23

这家伙

1.22

alty

1.20

Activations Density 0.025%