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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     breastfeeding
    -0.07
     furry
    -0.07
    |,↵
    -0.06
    ｛
    -0.06
    /man
    -0.06
     hugged
    -0.06
    ApiResponse
    -0.06
    局
    -0.06
    {}_
    -0.06
    .*↵↵
    -0.06
    POSITIVE LOGITS
    gold
    0.07
     فوق
    0.07
    (hw
    0.07
    (role
    0.06
     validations
    0.06
    fal
    0.06
     výše
    0.06
    โอ
    0.06
     gold
    0.06
     doğal
    0.06
    Act Density 0.009%

    No Known Activations