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

    Neuronpedia

    INDEX
    Explanations

    words related to body parts, specifically shoulders

    oai_token-act-pair · gpt-3.5-turbo

    references to the shoulder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esis
    -0.82
    eer
    -0.82
    icative
    -0.81
    esters
    -0.80
    yrinth
    -0.79
    âĸĪâĸĪ
    -0.79
     Vide
    -0.77
    ovych
    -0.76
    gom
    -0.76
    icate
    -0.76
    POSITIVE LOGITS
     shoulder
    1.15
     blades
    1.14
    bone
    0.88
     blade
    0.86
     shrug
    0.86
     straps
    0.86
     pads
    0.82
     joints
    0.77
     shoulders
    0.77
     lobe
    0.77
    Act Density 0.017%

    No Known Activations