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

    Neuronpedia

    INDEX
    Explanations

    topics related to gender issues and social justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.45
    ندی
    -0.41
    into
    -0.39
     Ta
    -0.39
     d
    -0.39
    折
    -0.38
     $
    -0.38
    いため
    -0.38
    面
    -0.37
     
    -0.37
    POSITIVE LOGITS
     resourceCulture
    1.09
    AnchorStyles
    0.98
    AccessorTable
    0.94
    IsMutable
    0.93
    RenderAtEndOf
    0.92
     EconPapers
    0.89
    HostException
    0.88
    BagConstraints
    0.88
     ✭✭
    0.87
    basicConfig
    0.86
    Act Density 0.739%

    No Known Activations