INDEX

Explanations

South Asia and Africa

This neuron detects named entities—proper nouns such as people’s names, movie titles, and other capitalized names.

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

or

-2.02

 while

-1.49

).

-1.45

 immediately

-1.43

if

-1.42

but

-1.39

by

-1.37

so

-1.36

 before

-1.35

 always

-1.35

POSITIVE LOGITS

cznym

1.38

johtaja

1.36

 víz

1.30

➀

1.28

 iaitu

1.28

нием

1.27

paikan

1.25

ﺇ

1.25

 spagnolo

1.24

тистика

1.24

Activations Density 0.024%