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

    Neuronpedia

    INDEX
    Explanations

    references to scientific citations included in the document

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    ofollow
    -0.68
    براير
    -0.60
     UserDao
    -0.60
     UnityEditor
    -0.59
    raseña
    -0.59
    titleMargin
    -0.58
    EndContext
    -0.57
    mètres
    -0.57
    olybdenum
    -0.57
     ویکی‌پدیا
    -0.56
    POSITIVE LOGITS
    cit
    2.64
     cit
    0.83
    Cit
    0.66
     Cit
    0.63
    cita
    0.59
    providedIn
    0.52
    PROTOBUF
    0.52
    icit
    0.51
    citi
    0.50
    RegistryLite
    0.49
    Act Density 0.002%

    No Known Activations