INDEX

Explanations

government actions and statements

The neuron activates on mentions of government bodies, offices, and officials (e.g., “government,” “President,” “Embassy,” “officials”).

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

 czerwca

-1.89

in

-1.70

']

-1.61

 września

-1.58

</h3>

-1.45

年に

-1.44

Ꮗ

-1.40

 grudnia

-1.37

̣c

-1.35

ICIONES

-1.34

POSITIVE LOGITS

is

1.66

of

1.55

 itself

1.48

 Abgerufen

1.36

瘸

1.34

its

1.30

Endereco

1.28

Descubre

1.28

 then

1.27



1.24

Activations Density 0.012%