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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical body parts, specifically knees

    oai_token-act-pair · gpt-3.5-turbo

    references to knee injuries and related medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aires
    -0.86
    ource
    -0.82
    ADRA
    -0.78
    actionDate
    -0.75
    hips
    -0.74
    NRS
    -0.72
    rational
    -0.70
    ourke
    -0.69
     Vide
    -0.69
    afety
    -0.68
    POSITIVE LOGITS
     knee
    1.07
     joints
    1.05
     jerk
    1.01
     ankle
    0.91
     knees
    0.90
     injury
    0.88
     shoulder
    0.88
     kne
    0.85
     braces
    0.84
    bone
    0.84
    Act Density 0.015%

    No Known Activations