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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical appearance

    oai_token-act-pair · gpt-3.5-turbo

    attributes and physical characteristics of objects or beings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.79
    chemical
    -0.77
    agents
    -0.76
    EMS
    -0.75
    76561
    -0.75
    relevant
    -0.72
    agent
    -0.72
    soDeliveryDate
    -0.72
    akings
    -0.71
    ItemTracker
    -0.70
    POSITIVE LOGITS
     shoulders
    1.36
     hips
    1.35
     edges
    1.26
     spine
    1.24
     curves
    1.19
     nose
    1.18
     curved
    1.17
     waist
    1.14
     chin
    1.14
     angled
    1.14
    Act Density 0.196%

    No Known Activations