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

    Neuronpedia

    INDEX
    Explanations

    content related to surprise or unexpected events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nev
    -0.15
    IDGE
    -0.14
     ký
    -0.14
     Prod
    -0.14
    uC
    -0.14
    rens
    -0.13
    bol
    -0.13
    ibre
    -0.13
    idge
    -0.13
    ìĪ
    -0.13
    POSITIVE LOGITS
    Categories
    0.18
    lient
    0.18
    lash
    0.16
    رات
    0.15
    977
    0.15
     ден
    0.14
     Categories
    0.14
    .uni
    0.14
    άλ
    0.14
    _tac
    0.14
    Act Density 0.003%

    No Known Activations