INDEX

Explanations

city names and entities

The neuron fires on the “--” (and similar dashes) that follow news dateline city names (e.g. “DETROIT --”), marking the start of a wire‐style article.

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

 versátil

-1.58

 gekozen

-1.52

 abiye

-1.52

摆手

-1.43

拍了拍

-1.42

jiet

-1.39

 medlemmer

-1.38

ابراین

-1.38

pośred

-1.37

 kontaktu

-1.36

POSITIVE LOGITS

 They

1.98

1.83

1.60

for

1.54

дже

1.48

 deine

1.40

1.38

in

1.38

een

1.37

way

1.34

Activations Density 0.034%