INDEX

Explanations

not a fan

The neuron activates on numeric tokens—integers or decimals—i.e. when it sees a number in the text.

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

 they

-1.56

ijnlijk

-1.48

 then

-1.46

-1.35

 that

-1.33

-1.27

นอก

-1.26

kách

-1.23

 extensive

-1.23

コラボ

-1.23

POSITIVE LOGITS

</h2>

1.95

</h1>

1.66

 propone

1.45

breos

1.43

uſ

1.41

gettyimages

1.34

dreamstime

1.34

 wunder

1.33

 novo

1.30

 laim

1.29

Activations Density 0.053%