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

    Neuronpedia

    INDEX
    Explanations

    expressions related to mathematical notation or syntax

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    digarh
    -0.77
    ScreenState
    -0.75
     печень
    -0.73
     Vaughn
    -0.71
    </h5>
    -0.69
     Vaugh
    -0.69
    <h3>
    -0.69
    <h5>
    -0.69
    mspace
    -0.69
    hoga
    -0.66
    POSITIVE LOGITS
     EB
    1.16
    EB
    0.94
     BOU
    0.91
     ThemeData
    0.89
     Bou
    0.88
     Eb
    0.86
    Bou
    0.82
     eb
    0.77
    ChildScrollView
    0.77
     Amiens
    0.76
    Act Density 0.008%

    No Known Activations