INDEX

Explanations

importance, need, value, significance

This neuron detects abstract evaluative nouns expressing significance or necessity (e.g. “importance,” “value,” “need”).

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

the

-1.42

 menghubungi

-1.34

 wurden

-1.33

 они

-1.29

⼈

-1.28

you

-1.27

 They

-1.26

arashtra

-1.23

 sprawd

-1.20

POSITIVE LOGITS

and

1.59

of

1.36

andReturn

1.30

 campeão

1.27

:\/\/

1.27

垍

1.27

 Ruß

1.23

 महत्व

1.23

mann

1.20

{\$

1.18

Activations Density 0.036%