INDEX

Explanations

html div elements

This neuron responds to HTML tag tokens (e.g. opening “<div>”, “<p>”, “<span>”, etc.) in code.

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

to

-1.45

 used

-1.40

 many

-1.37

 various

-1.33

を探す

-1.30

 incluyendo

-1.29

 asumi

-1.26

 than

-1.25

 does

-1.21

 then

-1.20

POSITIVE LOGITS

 totiž

1.46

 attente

1.37

</strong>

1.35

=""/>

1.34

 maksi

1.28

밈

1.25

 refroidissement

1.24

"}}

1.24

ſy

1.23

 poitrine

1.23

Activations Density 0.012%