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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the presence of certain items or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.53
    __::
    -0.52
    Tikang
    -0.48
    :✨
    -0.47
    addGroup
    -0.47
     pushes
    -0.46
     paramString
    -0.46
     Introduced
    -0.45
     Introdu
    -0.44
    introdu
    -0.44
    POSITIVE LOGITS
    contains
    1.42
    Contains
    1.41
     contains
    1.36
     Contains
    1.32
     contain
    1.30
     containing
    1.27
     Containing
    1.16
     Contain
    1.09
    Containing
    1.09
    contain
    1.08
    Act Density 0.105%

    No Known Activations