Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to paragraphs and paragraph numbers within a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Hellen
    -0.87
     Lizzy
    -0.86
     Wur
    -0.82
     SUA
    -0.82
     Showtime
    -0.80
    PropertyChanging
    -0.73
    UpdateCommand
    -0.73
    Ell
    -0.71
     Crete
    -0.70
     Utica
    -0.70
    POSITIVE LOGITS
     paragraphs
    1.38
     paragraph
    1.36
    paragraphs
    1.36
     Paragraph
    1.30
    Paragraph
    1.24
    paragraph
    1.23
    rafo
    0.83
     parag
    0.80
    parag
    0.79
     Margot
    0.74
    Act Density 0.002%

    No Known Activations