INDEX

Explanations

holidays and celebrations

This neuron detects mentions of major holidays or festivals (e.g., “New Year,” “Chinese New Year,” “Eid Al-Fitr,” “Diwali,” “Ramadan”).

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

-1.49

 hebben

-1.46

 minerales

-1.34

 heeft

-1.29

los

-1.29

蟜

-1.28

 zonder

-1.27

-1.26

 dieser

-1.25

POSITIVE LOGITS

 maybe

1.40

ἶ

1.38

ciendo

1.37

Упаковка

1.31

 Конечно

1.27

When

1.26

Rujukan

1.25

 komende

1.25

 their

1.24

жала

1.24

Activations Density 0.010%