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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ownership and control

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating levels or degrees of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reperto
    -0.71
    WARE
    -0.70
    ertodd
    -0.67
    NetMessage
    -0.61
    ATURES
    -0.60
     partName
    -0.59
    ©¶æ¥µ
    -0.55
    chwitz
    -0.54
    ashtra
    -0.54
    pots
    -0.54
    POSITIVE LOGITS
     course
    1.05
     sorts
    0.86
    icial
    0.83
    course
    0.76
     Nanto
    0.64
    rium
    0.56
     those
    0.56
     ours
    0.56
     Nations
    0.54
     the
    0.54
    Act Density 0.906%

    No Known Activations