INDEX

Explanations

human first names

The main thing this neuron does is detect personal names (proper names of people).

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

but

-1.57

もありますが

-1.49

も多い

-1.41

も良い

-1.32

 lauded

-1.27

loginButton

-1.27

のよ

-1.27

hésitez

-1.26

 coopération

-1.25

素敵

-1.23

POSITIVE LOGITS

*)&

1.32

 mengerti

1.26

 }));

1.25

 هستیم

1.24

˃

1.23

Initially

1.22

kių

1.21

esía

1.19

 déc

1.16

相片

1.16

Activations Density 0.011%