INDEX

Explanations

part of

The neuron activates on verbs and phrases that indicate taking part in or participating in an event (e.g. “took part,” “participated,” “competed”).

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

 their

-1.69

 people

-1.24

しておく

-1.16

 comprometido

-1.16

Saf

-1.16

不断的

-1.16

джан

-1.13

ibatis

-1.13

 Festival

-1.11

มี

-1.10

POSITIVE LOGITS

 among

1.42

but

1.29

and

1.29

 thus

1.23

нік

1.22

 zonder

1.20

 seguintes

1.19

 along

1.19

 quella

1.16

')

1.14

Activations Density 0.049%