INDEX

Explanations

foreign given names and surnames

The neuron activates on capitalized tokens that are part of named entities (proper nouns), especially personal and place names.

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

ENEFITS

-1.35

 APPELL

-1.34

 rése

-1.34

 retrô

-1.33

 imprimer

-1.33

 nieuwe

-1.30

 Spanyol

-1.30

 caminh

-1.28

 refuser

-1.27

 Você

-1.27

POSITIVE LOGITS

</i>

1.73

</b>

1.72

1.69

1.63

1.60

1.59

1.57

is

1.55

1.52

1.51

Activations Density 0.186%