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

    Neuronpedia

    INDEX
    Explanations

    sections related to methodologies and experimental results in research documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    芭
    -0.44
    ya
    -0.43
    ";
    -0.42
    ("/");
    -0.41
    connect
    -0.41
    </i>
    -0.41
     conect
    -0.41
    ga
    -0.39
     also
    -0.39
    ba
    -0.39
    POSITIVE LOGITS
    DeleteBehavior
    0.92
    :✨
    0.91
     дописавши
    0.89
    AndEndTag
    0.81
     "..\..\
    0.78
    RectangleBorder
    0.74
    脚注の使い方
    0.72
     $_"
    0.72
    setVerticalGroup
    0.72
    didSet
    0.71
    Act Density 0.247%

    No Known Activations