INDEX

Explanations

eleven

The neuron fires strongly on the numeral “11” (e.g. day‐of‐month tokens in dates).

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

When

-1.79

er

-1.78

 with

-1.78

“

-1.76

two

-1.76

 four

-1.68

-1.66

Since

-1.64

 забезпе

-1.63

<!--

-1.62

POSITIVE LOGITS

antaine

2.05

茕

1.94

镚

1.75

⑊

1.75

ться

1.70

TODOS

1.65

潆

1.61

 другого

1.60

鈊

1.54

ਂ

1.53

Activations Density 0.025%