INDEX

Explanations

describing people and things

The neuron strongly activates on numeric tokens—especially decimal or measurement values—i.e. it detects numbers 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

\\

-1.64

if

-1.39

how

-1.37

</blockquote>

-1.30

</h2>

-1.29

<h2>

-1.27

for

-1.26

if

-1.23

_____

-1.23

 pelas

-1.22

POSITIVE LOGITS

of

1.40

1.37

 vesel

1.32

㄀

1.31

 devrait

1.30

 TÉCNICA

1.30

 adil

1.30

 verir

1.30

 diatas

1.29

＝＝＝＝

1.28

Activations Density 0.084%