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

    Neuronpedia

    INDEX
    Explanations

    characters with honorific titles or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    honorifics and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jornalista
    -0.44
     aislada
    -0.43
    libatkan
    -0.40
     berlebihan
    -0.40
     mengalir
    -0.40
     Hälfte
    -0.38
     töd
    -0.38
     komunikasi
    -0.37
     quirúrg
    -0.36
     кіль
    -0.36
    POSITIVE LOGITS
    WithIOException
    0.77
     Monfieur
    0.75
     mister
    0.72
     Monsieur
    0.70
    sieur
    0.69
    Mister
    0.68
    mister
    0.68
     Madame
    0.68
     AttributeSet
    0.68
     gentleman
    0.65
    Act Density 0.020%

    No Known Activations