INDEX

Explanations

opening quote followed by speech

The neuron activates on numeric tokens (integers and decimals) 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

 will

-1.41

给他们

-1.34

of

-1.32

rhosis

-1.31

蔔

-1.27

 этого

-1.23

 даже

-1.23

 другого

-1.22

 другом

-1.21

 always

-1.20

POSITIVE LOGITS

for

1.66



1.58

1.44

咴

1.34

Karena

1.32

鋨

1.30

unno

1.29

 baumwolle

1.28



1.28

1.25

Activations Density 0.025%