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

    Neuronpedia

    INDEX
    Explanations

    phrases and connectors that suggest enumeration or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pouvoirs
    -0.81
     épaules
    -0.81
     vœux
    -0.77
     bienfaits
    -0.76
     jambes
    -0.75
     gouvernements
    -0.73
     navires
    -0.73
     lèvres
    -0.72
     genoux
    -0.70
     bénéfices
    -0.69
    POSITIVE LOGITS
    RenderAtEndOf
    0.99
    zości
    0.86
     cherchés
    0.81
    例句
    0.79
     lenker
    0.76
    ')")
    0.75
    Các
    0.75
    )";
    0.74
     אחרים
    0.74
    '],
    0.73
    Act Density 0.556%

    No Known Activations