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

    Neuronpedia

    INDEX
    Explanations

    individual characteristics or features describing the appearance or qualities of a person or object

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating characteristics or attributes of people or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ],[
    -0.81
    Cause
    -0.76
    ]"
    -0.71
     alike
    -0.71
    IRC
    -0.70
    cies
    -0.70
    Rs
    -0.69
    IAL
    -0.68
     Became
    -0.67
    oor
    -0.66
    POSITIVE LOGITS
     typical
    0.83
     adulthood
    0.78
     ordinary
    0.71
    liest
    0.71
     royalty
    0.70
     medieval
    0.70
     a
    0.69
     classical
    0.69
     traditional
    0.67
     adolescence
    0.67
    Act Density 0.186%

    No Known Activations