INDEX

Explanations

idiomatic phrases and common sayings

The neuron detects repeated function or discourse words appearing in parallel structures (e.g. “like … like,” “here ye, here ye,” “twinkle twinkle,” “go … go”).

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

you

-1.36

-1.27

 این

-1.27

FFFFFF

-1.27

who

-1.24

and

-1.23

 estas

-1.23

limus

-1.22

-1.20

-1.17

POSITIVE LOGITS

 weihnachts

1.39

 クッキー

1.35

ୂ

1.33

imee

1.29

Tarjeta

1.27

aise

1.27

ejemplo

1.22

 moks

1.21

estudiante

1.21

 detaljer

1.21

Activations Density 0.021%