INDEX

Explanations

questions starting with Q: or help

The neuron fires on tokens that end with the letter “x.”

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

and

-1.66

 esquí

-1.30

 their

-1.24

</h1>

-1.20

in

-1.17

！”

-1.17

 スペシャル

-1.13

IFICACIÓN

-1.13

 most

-1.13

POSITIVE LOGITS

ὺς

1.48

 insides

1.41

دانلود

1.40

锲

1.37

1.35

ोड़

1.34

vantaged

1.34

丸

1.33

blätter

1.30

躥

1.26

Activations Density 0.000%