INDEX

Explanations

states of being or outcomes

The neuron fires on the main content words (especially the principal nouns and verbs) in a sentence, i.e. the core semantic “subjects” and “predicates.”

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

 regalar

-1.48

 indépendante

-1.34

 durer

-1.31

 aérienne

-1.31

賀状

-1.30

 spécialisée

-1.30

 przecież

-1.29

訁

-1.24

 conster

-1.24

 éditoriale

-1.21

POSITIVE LOGITS

 also

1.56

 some

1.41

 earlier

1.36

as

1.31

saw

1.27

for

1.24

all

1.23

 much

1.22

ционного

1.20

 różnych

1.17

Activations Density 0.049%