INDEX

Explanations

JSON structured data

This neuron primarily activates on multi‐digit numeric tokens (i.e. sequences of digits representing numbers).

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

-2.16

 После

-2.05

 специалисты

-2.00

</h3>

-1.94

-1.93

が

-1.93

-1.90

-1.87

</blockquote>

-1.85

POSITIVE LOGITS

2.27

2.14

様な

2.13

Ꮟ

2.09

’).

2.06

⦊

2.03

 búsquedas

2.03

());

2.00

 transacciones

2.00

もう一度

1.98

Activations Density 0.045%