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

    Neuronpedia

    INDEX
    Explanations

    words related to physical attributes or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical attributes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.78
    atis
    -0.78
     Trend
    -0.76
    hof
    -0.75
    mong
    -0.73
    adas
    -0.72
    imar
    -0.69
    oops
    -0.68
    makers
    -0.68
    andum
    -0.67
    POSITIVE LOGITS
     physical
    3.58
    physical
    3.03
    Physical
    2.64
     Physical
    2.50
     physically
    2.29
     phys
    1.59
     bodily
    1.46
     physiological
    1.39
     psychological
    1.36
    phys
    1.32
    Act Density 0.031%

    No Known Activations