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

    Neuronpedia

    INDEX
    Explanations

    behaviors that indicate defiance or non-compliance in individuals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.69
    berdayakan
    -0.65
     referrerpolicy
    -0.57
    EndGlobalSection
    -0.57
    ftagPool
    -0.56
    таратура
    -0.56
    GraphicsUnit
    -0.56
    новниш
    -0.54
     disambiguazione
    -0.52
    CppMethod
    -0.52
    POSITIVE LOGITS
     refusal
    0.67
     refusing
    0.66
     obstin
    0.65
     disobedience
    0.62
     refused
    0.61
     refuses
    0.59
     defiance
    0.59
     refus
    0.56
    Portail
    0.53
     resistance
    0.53
    Act Density 0.189%

    No Known Activations