INDEX

Explanations

people groups and affiliations

The neuron detects capitalized organization and event names (especially multi‐word titles or acronyms).

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

 üblichen

-1.39

 übrigen

-1.38

出来ました

-1.38

 täglichen

-1.36

 troubled

-1.34

 desemple

-1.32

 magasiner

-1.30

 beantragt

-1.29

 acoged

-1.27

 faltar

-1.26

POSITIVE LOGITS

ViewChild

1.34

1.32

 noong

1.30

and

1.28

љу

1.27

DRC

1.25

ⅼ

1.22

1.20

 then

1.16

OURCES

1.16

Activations Density 0.045%