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

    Neuronpedia

    INDEX
    Explanations

    sections or headings indicating specific categories or grouping of information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     everything
    -0.46
    Ate
    -0.43
     factors
    -0.43
    everything
    -0.42
    flags
    -0.40
    :
    -0.40
    lot
    -0.40
    цездатний
    -0.40
     flags
    -0.38
    cmu
    -0.37
    POSITIVE LOGITS
    AndEndTag
    1.04
    ReusableCell
    0.89
    RenderAtEndOf
    0.87
    IBOutlet
    0.81
    InSection
    0.81
    ArgumentParser
    0.79
     estekak
    0.78
    WebServlet
    0.77
    redited
    0.75
     виправивши
    0.73
    Act Density 0.035%

    No Known Activations