INDEX

Explanations

dates and times

The neuron activates on numeric tokens and measurements, i.e. standalone numbers and figures.

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

(!__

-1.59

 mortes

-1.59

 môžete

-1.58

 můžete

-1.52

Specifically

-1.51

一切都

-1.46

our

-1.45

 требу

-1.43

ві

-1.43

了出来

-1.40

POSITIVE LOGITS

1.78

).

1.48

 ingenious

1.40

 ensuring

1.29

↵

1.27

].

1.26

 zrobić

1.24

}\

1.23

 Einige

1.23

 elettrica

1.23

Activations Density 0.056%