INDEX

Explanations

two worlds together

The neuron primarily activates on mentions of “world” or “worlds” (and closely related terms like “realms”).

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

as

-2.30

-1.80

but

-1.60

 Pristupljeno

-1.44

and

-1.42

in

-1.38

 during

-1.32

an

-1.31

 time

-1.30

.”

-1.30

POSITIVE LOGITS

 другие

1.59

 hybride

1.56

 parfois

1.49

 mixta

1.41

 éstos

1.41

 recupera

1.41

eki

1.38

 چیه

1.36

 facilita

1.34

 charmant

1.34

Activations Density 0.041%