INDEX

Explanations

names of languages

The main thing this neuron does is find mentions of natural language names (e.g. English, French, German, etc.).

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

-1.56

-1.30

 veckor

-1.28

 verá

-1.27

new

-1.22

are

-1.22

 große

-1.19

 verläng

-1.18

-1.16

<h2>

-1.16

POSITIVE LOGITS

女

1.32

 núm

1.31

 imagenes

1.29

狁

1.29

 フロア

1.27

ꪔ

1.24

 atencion

1.23

 iconos

1.22

Прият

1.21



1.20

Activations Density 0.038%