INDEX

Explanations

year digits

The neuron detects standalone multi-digit numeric sequences (e.g. three-digit page or citation numbers) in legal citation contexts.

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

of

-2.45

and

-1.84

 with

-1.72

at

-1.59

 before

-1.48

 vernis

-1.42

 händer

-1.42

or

-1.40

Putting

-1.40

 memen

-1.39

POSITIVE LOGITS

1.78

 myriad

1.62

 extremely

1.60

1.57

st

1.55

 exceptional

1.53

 exceptionally

1.51

..........

1.47

1.44

Activations Density 0.004%