INDEX

Explanations

months of the year

This neuron detects full month names (e.g., January, February, …, December) in date expressions.

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

 such

-1.89

-1.54

 like

-1.50

 different

-1.41

in

-1.41

-1.36

 many

-1.34

-1.32

 much

-1.28

 some

-1.27

POSITIVE LOGITS

闼

1.40

 jonka

1.39

 doucement

1.37

骓

1.36

of

1.33

痙

1.31

licitations

1.30

كويكب

1.29

ディー

1.29

嘀

1.26

Activations Density 0.034%