INDEX

Explanations

listing multiple things

The neuron activates on numeric tokens—especially decimal numbers—i.e. it spots numerical measurements or quantities.

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

↵

-2.33

The

-1.88

-1.74

–

-1.71

 Their

-1.66

トッピング

-1.59



-1.58

…………

-1.57

ݮ

-1.54

<strong>

-1.51

POSITIVE LOGITS

埽

2.11

หรือ

2.03

或

1.96

縢

1.89

 that

1.80

 или

1.80

ayaquil

1.79

 everything

1.78

และ

1.76

🩱

1.76

Activations Density 0.048%