INDEX

Explanations

chat and cart

The neuron fires on code identifier tokens like “chat” or “cart” (e.g. HTML id or variable names).

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

-1.66

 infatti

-1.35

 плани

-1.34

 fremden

-1.29

 заявление

-1.29

 çoğu

-1.27

たちに

-1.25

 более

-1.24

 impromptu

-1.24

of

-1.23

POSITIVE LOGITS

-"

1.48

--"

1.47

 almofada

1.46

KeySpec

1.45

1.42

uminense

1.41

pergillus

1.41

 paillettes

1.41

="

1.39

ğlık

1.39

Activations Density 0.024%