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

    Neuronpedia

    INDEX
    Explanations

    references to body measurements, particularly focusing on waist and hips

    oai_token-act-pair · gpt-3.5-turbo

    references to body measurements and physical attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utics
    -0.69
    kson
    -0.67
    20439
    -0.66
    ogical
    -0.66
    utic
    -0.66
     Suc
    -0.65
    UE
    -0.64
     Mub
    -0.62
    itsch
    -0.62
     Bhar
    -0.61
    POSITIVE LOGITS
     circumference
    1.10
     waist
    0.98
    coat
    0.86
     jeans
    0.86
     torso
    0.86
     neck
    0.82
    lift
    0.80
     width
    0.76
     strap
    0.76
    Width
    0.76
    Act Density 0.030%

    No Known Activations