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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating shared knowledge and active contributions in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /autoload
    -0.15
    ÐŁÐļ
    -0.15
    AZE
    -0.14
     Ellison
    -0.14
    hir
    -0.14
    帯
    -0.14
     Stein
    -0.14
    anos
    -0.14
    steen
    -0.13
    EW
    -0.13
    POSITIVE LOGITS
     veget
    0.16
    anel
    0.16
    rava
    0.15
    SAFE
    0.15
     Morav
    0.15
     ãĥ¢
    0.15
    iyon
    0.15
    leigh
    0.15
    .Dto
    0.14
     Cassidy
    0.14
    Act Density 0.375%

    No Known Activations