INDEX

Explanations

University of

The neuron activates on mentions of “University,” flagging references to academic institutions.

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

-1.63

Kaynakça

-1.47

 preparados

-1.44

獃

-1.43

 eficiente

-1.37

多少钱

-1.30

 wußte

-1.29

 cerrados

-1.28

⽣

-1.28

will

-1.27

POSITIVE LOGITS

to

2.50

 ketika

1.60

Cbd

1.57

 karena

1.57

 También

1.56

⻬

1.52

᩠

1.51

садки

1.50

 عندما

1.50

of

1.50

Activations Density 0.016%