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

    Neuronpedia

    INDEX
    Explanations

    descriptions or mentions of physical body parts, specifically shoulders

    oai_token-act-pair · gpt-3.5-turbo

    references to physical features, particularly focusing on shoulders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nom
    -0.78
     Vide
    -0.76
    yrinth
    -0.72
    esters
    -0.70
     Silicon
    -0.65
    href
    -0.65
    secut
    -0.64
    election
    -0.64
    prop
    -0.63
    RAM
    -0.63
    POSITIVE LOGITS
     shoulders
    1.15
     shoulder
    1.01
     neck
    0.85
     ankles
    0.84
     hips
    0.79
     necks
    0.79
     seams
    0.79
    weed
    0.78
     fingertips
    0.77
     waist
    0.77
    Act Density 0.006%

    No Known Activations