INDEX

Explanations

gun control, possession, violence, laws, rights

This neuron strongly activates on words referring to firearms or weapons (especially “gun” and its variants, plus related terms like “arms” and “firearms”).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

-2.11

-1.96

 ellen

-1.94

　　……

-1.85

 dormitórios

-1.76

彀

-1.71

骓

-1.70

 palha

-1.62

埙

-1.60

多年的

-1.59

POSITIVE LOGITS

 erfolgreichen

1.81

将

1.79

 δύο

1.73

 начинают

1.71

 hört

1.70

 ['./

1.68

 Behörden

1.66

纐

1.66

ぅ

1.66

僱

1.63

Activations Density 0.009%