INDEX

Explanations

return to navigation

The neuron detects navigation or “go back” style link or button labels (e.g. “Back to,” “Return to,” “Go back to,” “Home,” “Previous”).

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

-1.70

-1.55

ඇ

-1.41

ыр

-1.34

devils

-1.33

its

-1.30

васто

-1.28

ٞ

-1.25

いしい

-1.25

 उसने

-1.23

POSITIVE LOGITS

begin

1.63

𔘓

1.48

CHREIBUNG

1.41

 Họ

1.41

 शुरु

1.39

 mußte

1.34

end

1.33

 etmeye

1.33

放入

1.30

 juzgar

1.30

Activations Density 0.032%