INDEX

Explanations

place names ending in ton or boro

The neuron activates on geographic place names, especially town, city, and county names.

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

蹓

-1.63

 damski

-1.61

Would

-1.55

ครื่อง

-1.50

łość

-1.49

僰

-1.48

 diriger

-1.45

𓆏

-1.44

 personer

-1.44

 progetto

-1.44

POSITIVE LOGITS

et

1.62

 should

1.59

↵↵

1.57

is

1.56

How

1.55

For

1.43

 both

1.42

1.41

 need

1.38

 других

1.34

Activations Density 0.167%