INDEX

Explanations

globalisation, blockers, predators, Wrigley Field

The neuron strongly activates on named entities—proper nouns such as people’s names, place names, titles of works, and other capitalized 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

=“

-1.83

 with

-1.75

 when

-1.67

 after

-1.55

װ

-1.52

følgelig

-1.49

 rodillas

-1.45

 sitten

-1.44

 fredag

-1.44

)$,

-1.42

POSITIVE LOGITS

1.54

 их

1.40

 они

1.39

 он

1.37

If

1.35

他们

1.32

Its

1.29

其

1.29

1.25

ной

1.23

Activations Density 0.358%