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

    Neuronpedia

    INDEX
    Explanations

    items or tasks in a list preceded by the abbreviation "etc."

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms or categories of items or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bond
    -0.67
     Kab
    -0.66
     Chow
    -0.66
     Cup
    -0.65
     cap
    -0.63
     Ud
    -0.63
     Cook
    -0.63
     lash
    -0.61
     Lad
    -0.61
     light
    -0.61
    POSITIVE LOGITS
    ÃĥÃĤ
    1.07
    ĸļ士
    1.05
    ÃĥÃĤÃĥÃĤ
    1.03
    Orderable
    0.99
    DeliveryDate
    0.99
    ñ
    0.82
    ò
    0.81
    milo
    0.79
    atem
    0.79
    ¥ŀ
    0.79
    Act Density 0.510%

    No Known Activations