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

    Neuronpedia

    INDEX
    Explanations

    references to structural models and their connections in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -1.04
    存于互联网档案馆
    -0.93
    RenderAtEndOf
    -0.92
     ProtoMessage
    -0.89
    AccessorTable
    -0.88
     Theſe
    -0.84
     Winaray
    -0.83
     Мексичка
    -0.81
    UVWXYZ
    -0.81
     مشين
    -0.80
    POSITIVE LOGITS
    -------------</
    0.64
     saw
    0.47
     met
    0.46
     ser
    0.45
    ,
    0.44
     notare
    0.43
    Turns
    0.42
     turns
    0.42
    Cobra
    0.41
     her
    0.41
    Act Density 7.519%

    No Known Activations