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

    Neuronpedia

    INDEX
    Explanations

    instances or phrases indicating automated processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nier
    -0.79
    lihood
    -0.78
    Personensuche
    -0.76
     AssemblyProduct
    -0.73
     TextFormField
    -0.70
    hound
    -0.68
     TZ
    -0.67
    endsection
    -0.67
    DllImport
    -0.65
    PMailer
    -0.64
    POSITIVE LOGITS
     automatic
    2.06
     Automatic
    2.00
     automatically
    1.94
    Automatic
    1.92
    automatic
    1.91
     AUTOMATIC
    1.82
    automatically
    1.66
     Automatically
    1.64
     automat
    1.64
    Automatically
    1.59
    Act Density 0.099%

    No Known Activations