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

    Neuronpedia

    INDEX
    Explanations

    statements of distrust or negativity towards authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.96
     jsPsych
    -0.78
    AccessorTable
    -0.76
    djangoproject
    -0.74
    adaptiveStyles
    -0.72
    fjspx
    -0.69
    ۣ
    -0.68
     referrerpolicy
    -0.65
    Autoritní
    -0.64
     feroit
    -0.64
    POSITIVE LOGITS
    GEBURTSDATUM
    0.72
     also
    0.64
     like
    0.60
     especially
    0.56
     wanted
    0.54
     też
    0.53
    agrave
    0.52
     नहीं
    0.52
     maybe
    0.51
    uccio
    0.49
    Act Density 0.384%

    No Known Activations