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

    Neuronpedia

    INDEX
    Explanations

    references to the anatomy and physical positioning related to the shoulders and neck

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marac
    -0.58
     kysy
    -0.57
    léans
    -0.57
    orteur
    -0.56
     festen
    -0.55
    nthetic
    -0.55
     faith
    -0.55
     quantités
    -0.55
    Morse
    -0.54
    Timmy
    -0.53
    POSITIVE LOGITS
     shoulders
    1.11
    Shoulder
    1.05
     Shoulder
    1.00
     shoulder
    1.00
     Shoulders
    0.97
    shoulder
    0.93
     Neck
    0.91
     neck
    0.85
     Waist
    0.83
    Waist
    0.82
    Act Density 0.276%

    No Known Activations