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

    Neuronpedia

    INDEX
    Explanations

    references to shoulders and their positioning or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    shoulder and related parts/actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كورة
    -0.47
    хьтан
    -0.40
     toy
    -0.33
    pperware
    -0.33
    TryParse
    -0.33
     memas
    -0.32
     câte
    -0.32
     cardiaque
    -0.32
     disfraz
    -0.31
     messes
    -0.31
    POSITIVE LOGITS
     shoulders
    1.96
     Shoulders
    1.76
     épaules
    1.55
     hombros
    1.34
     shoulder
    1.27
    Shoulder
    1.24
     Shoulder
    1.24
    shoulder
    1.18
     Schulter
    1.13
    肩
    1.04
    Act Density 0.004%

    No Known Activations