INDEX

Explanations

political or union leader

This neuron activates on words naming political entities or roles (e.g., party, leader, chief, politician).

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

 their

-1.70

嗚

-1.59

-1.54

it

-1.52

-1.50

後記

-1.47

 času

-1.46

香水

-1.41

 可愛い

-1.38

眉毛

-1.38

POSITIVE LOGITS

</td>

1.88

1.76

 خدمة

1.72

↵↵↵↵↵↵↵↵↵↵↵

1.70

™

1.69

一直在

1.66

 MIKE

1.64

鹀

1.64

↵↵↵↵↵↵↵↵↵↵↵↵↵

1.63

 ........

1.58

Activations Density 0.019%