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

    Neuronpedia

    INDEX
    Explanations

    references to a specific film director

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.85
    thâu
    -0.68
     GenerationType
    -0.65
     Buchen
    -0.65
     Middles
    -0.62
     Administrativna
    -0.60
     propOrder
    -0.60
    zewod
    -0.57
     lamella
    -0.57
    MethodManager
    -0.57
    POSITIVE LOGITS
     Mann
    3.28
    Mann
    2.63
     mann
    1.44
     Manns
    0.81
     lenker
    0.61
     Mannheim
    0.57
    createCanvas
    0.55
    нрави
    0.51
     للمعارف
    0.51
    териалы
    0.50
    Act Density 0.001%

    No Known Activations