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

    Neuronpedia

    INDEX
    Explanations

    technical terms and statistics related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onavir
    -0.16
    олÑİ
    -0.16
    ornings
    -0.16
    essim
    -0.16
    adge
    -0.15
    ibur
    -0.15
    getattr
    -0.14
    ype
    -0.14
    kud
    -0.14
    mars
    -0.13
    POSITIVE LOGITS
    wi
    0.17
    pany
    0.15
    _pagination
    0.15
    qd
    0.14
    erli
    0.14
     automáticamente
    0.14
    .Automation
    0.14
    æĶ¿
    0.14
     Ulus
    0.14
     Hd
    0.13
    Act Density 1.020%

    No Known Activations