INDEX

Explanations

jurisdiction and control

The neuron activates on formal legal or governmental policy terminology (e.g. prosecutorial decisions, felonies, military chain-of-command, state subject).

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

 сайті

-1.05

 założ

-0.93

 tatuagem

-0.88

하려

-0.88

 světě

-0.87

ventud

-0.86

ínsula

-0.84

ENODEV

-0.83

Mvh

-0.83

قایناق‌لار

-0.82

POSITIVE LOGITS

 control

1.27

responsibility

1.16

 responsibility

1.16

 jurisdiction

1.02

control

1.01

 ownership

1.01

 portions

0.96

 transferred

0.94

ownership

0.94

 delegated

0.92

Activations Density 0.067%