INDEX

Explanations

been followed by wanted

This neuron activates on the phrase “always wanted to” (i.e. expressions of a long-held desire such as “If you’ve always wanted to…”).

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

🕗

-1.38

 persecu

-1.38

 puisqu

-1.37

 controver

-1.37

 excur

-1.37

 ماد

-1.35

不舒服

-1.34

Ĥ

-1.34

 arit

-1.32

 inga

-1.31

POSITIVE LOGITS

eaked

1.39

 this

1.30

any

1.29

！

1.29

 your

1.28

</tfoot>

1.27

 אתם

1.27

mographie

1.24

مكان

1.24

 September

1.23

Activations Density 0.098%