INDEX

Explanations

men and women

This neuron activates on words that explicitly refer to gender or sex categories (e.g., women, men, male, female, heterosexual).

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

of

-1.77

一楼

-1.57

赊

-1.42

 دیگران

-1.34

']){

-1.34

 possono

-1.33

 Entdecken

-1.30

뽐

-1.27

lusst

-1.27

龊

-1.25

POSITIVE LOGITS

The

1.59

 There

1.48

</i>

1.43

<blockquote>

1.42

 when

1.42

″

1.40

شل

1.38

 обычно

1.34

赵

1.33

変わる

1.31

Activations Density 0.053%