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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical positioning or location

    oai_token-act-pair · gpt-3.5-turbo

    spatial relationships and positioning in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Few
    -0.64
     Offline
    -0.62
     offline
    -0.62
    arcity
    -0.61
    ARS
    -0.61
    Reports
    -0.61
    Attempts
    -0.60
    Introduced
    -0.59
    MQ
    -0.59
    udi
    -0.58
    POSITIVE LOGITS
     the
    0.93
    neath
    0.93
     each
    0.87
     protr
    0.85
     underside
    0.80
     forehead
    0.80
     his
    0.79
     skull
    0.79
     your
    0.79
     hips
    0.78
    Act Density 0.221%

    No Known Activations