INDEX

Explanations

numbers and quantities

The neuron primarily detects numeric tokens and numerical expressions (e.g. digits, quantities, and measurements).

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

optString

-1.02

漚

-0.97

 Söder

-0.95

Fußball

-0.92

 excellente

-0.92

ΡΟ

-0.92

Теперь

-0.91

】：

-0.91

forderungen

-0.90

 optimale

-0.90

POSITIVE LOGITS

 that

1.54

of

1.37

 from

1.29

 last

1.23

 previous

1.22

 earlier

1.17

 recent

1.13

 leading

1.09

 preceding

1.08

 later

1.00

Activations Density 0.064%