INDEX

Explanations

universities and cities

The neuron detects mentions of academic institutions and their locations (e.g. “University of X,” city names like Chicago or Albany in that context).

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

 Ilustra

-1.48

 dipinto

-1.38

НЫЕ

-1.37

人們

-1.33

 ayam

-1.33

 Ahnung

-1.33

 akin

-1.32

那

-1.32

 Opiniones

-1.31

 berapa

-1.30

POSITIVE LOGITS

For

1.61

you

1.52

to

1.52

To

1.50

unpublished

1.42

 your

1.41

 Here

1.36

 somit

1.33

1.31

 After

1.30

Activations Density 0.034%