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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to physical appearance

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to physical appearance and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forcement
    -0.97
    atos
    -0.82
    prises
    -0.81
    atis
    -0.80
     Readers
    -0.73
    andom
    -0.72
    swers
    -0.72
    nesday
    -0.72
    sers
    -0.71
    conom
    -0.69
    POSITIVE LOGITS
     overweight
    1.09
     frail
    1.08
     unmarried
    1.06
     weighed
    1.03
     inexperienced
    1.03
     weighs
    1.02
     wore
    1.01
     obese
    1.00
     wiser
    0.99
     taller
    0.98
    Act Density 0.223%

    No Known Activations