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

    Neuronpedia

    INDEX
    Explanations

    descriptions of inventions or innovations

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    expandindo
    -0.64
    raszamy
    -0.58
     réflex
    -0.58
     république
    -0.57
    Parcelize
    -0.57
    GEBURTSDATUM
    -0.57
     boleto
    -0.56
     carreira
    -0.55
    fml
    -0.54
    ویری
    -0.54
    POSITIVE LOGITS
     devised
    3.08
     devise
    2.70
     devising
    2.52
     devis
    1.73
    devise
    1.28
     придума
    0.96
     conco
    0.96
     coined
    0.90
     invented
    0.80
     formulating
    0.75
    Act Density 0.010%

    No Known Activations