INDEX

Explanations

founders

The neuron fires on mentions of “founders” (e.g. in bios or articles noting who founded something).

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

Sejarah

-2.02

umahan

-2.00

 две

-1.84

整个人

-1.79

tempat

-1.76

民眾

-1.73

ESTY

-1.73

sepatu

-1.73

 einheit

-1.72

тельности

-1.70

POSITIVE LOGITS

ྂ

2.20

2.16

1.98

℣

1.88

be

1.88

</h2>

1.85

You

1.82

はお

1.79

瀘

1.75

phère

1.74

Activations Density 0.005%