INDEX

Explanations

italian, cubana, or chinese

The neuron fires on locative language—tokens that mark spatial relations or positions (e.g. prepositions like “in,” “on,” “above,” copular verbs “was,” “be,” and related context words).

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

 then

-1.94

of

-1.63

to

-1.51

cadeau

-1.47

 confirmación

-1.47

 Detalles

-1.45

 salvación

-1.38

 reunião

-1.37

 promoción

-1.35

 Consejos

-1.34

POSITIVE LOGITS

writerow

1.41

 asta

1.26

</h1>

1.23

 cubana

1.23

agrave

1.13

為主

1.11

aka

1.10

 intrigue

1.09

३

1.09

 italian

1.08

Activations Density 0.008%