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

    Neuronpedia

    INDEX
    Explanations

    code related to functions and argument comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungan
    -0.18
    ообÑĢаз
    -0.15
    otte
    -0.15
    ellar
    -0.15
    antha
    -0.15
    odable
    -0.15
    hangi
    -0.14
    uda
    -0.14
    omb
    -0.14
    uitka
    -0.14
    POSITIVE LOGITS
    InView
    0.15
    aft
    0.15
     Ley
    0.15
     Cair
    0.15
    EIF
    0.14
    клад
    0.14
    leigh
    0.14
    ptrdiff
    0.13
    ERA
    0.13
     -*-č↵
    0.13
    Act Density 0.081%

    No Known Activations