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

    Neuronpedia

    INDEX
    Explanations

    the presence of parentheses in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Referências
    -0.61
     Rys
    -0.60
    RequestOptions
    -0.58
     Eliz
    -0.54
     decode
    -0.53
    Izvori
    -0.53
     doGet
    -0.53
    NewReader
    -0.53
    étranger
    -0.52
     Chwiliwch
    -0.52
    POSITIVE LOGITS
    kegaard
    0.71
    thâu
    0.62
    tığı
    0.59
     MonoBehaviour
    0.59
    rigada
    0.58
     محفوظة
    0.56
    iNdEx
    0.54
     Afric
    0.54
    ModelState
    0.54
    hamcrest
    0.53
    Act Density 0.023%

    No Known Activations