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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal belief and emotional connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sauvages
    -0.57
     opportunità
    -0.54
     coloridas
    -0.54
     douleur
    -0.51
     legyen
    -0.50
     världen
    -0.50
     gând
    -0.50
     betekenis
    -0.50
     alimentazione
    -0.49
     máscara
    -0.49
    POSITIVE LOGITS
    )");
    0.86
    KURZBESCHREIBUNG
    0.79
     AssemblyCompany
    0.79
    )"),
    0.72
    "},
    0.70
    >`;
    0.69
    >");
    0.67
    Numerology
    0.67
    CloseOperation
    0.67
     }}$}
    0.65
    Act Density 0.431%

    No Known Activations