INDEX

Explanations

depth and profoundness

This neuron responds to words that express magnitude or depth—terms conveying scale, measurement, or grand abstract qualities (e.g. depth, fathomed, wonders, great, mystery).

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

在这里

-1.45

 مثل

-1.34

particularly

-1.29

 tutaj

-1.28

𐬹

-1.27

像是

-1.26

 leña

-1.26

犼

-1.26

 gänzlich

-1.24

 craz

-1.23

POSITIVE LOGITS

People

1.48

and

1.48

how

1.42

 although

1.39

 workings

1.36

 first

1.34

 řešení

1.33

 uses

1.30

One

1.29

baguna

1.27

Activations Density 0.030%