INDEX

Explanations

personal names: Angus, Lucy, Jenny

The neuron selectively fires on specific capitalized proper names (notably “Angus” and “Lucy”).

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

We

-3.67

Because

-3.31

-3.30

To

-3.27

But

-3.20

-3.19

When

-3.17

With

-3.14

After

-3.11

For

-3.09

POSITIVE LOGITS

玙

2.83

).

2.72

咐

2.63

 самая

2.55

++];

2.55

 котором

2.52

oriques

2.47

竺

2.45

was

2.45

is

2.45

Activations Density 0.007%