INDEX

Explanations

groups of people involved

The neuron strongly fires on collective-group nouns (e.g. gang, staff, cast, crew, team) referring to a group of people.

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

and

-1.02

(""));

-0.96

 himself

-0.92

 hört

-0.92

も行

-0.90

 Familienname

-0.88

 whereas

-0.87

ism

-0.86

ன்

-0.86

POSITIVE LOGITS

of

2.13

 consisting

1.86

 members

1.85

members

1.72

mitglieder

1.66

 MEMBERS

1.58

 consists

1.50

 incluyendo

1.40

成员

1.40

 consisted

1.40

Activations Density 0.089%