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

    Neuronpedia

    INDEX
    Explanations

    specific references to privacy-related terms and concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tinyos
    -1.00
    extAlignment
    -0.87
     bezeichneter
    -0.84
    MetaType
    -0.82
    WindowConstants
    -0.81
     propOrder
    -0.81
     AGA
    -0.80
    WithIOException
    -0.80
     Lombard
    -0.79
     ExecuteAsync
    -0.78
    POSITIVE LOGITS
     bij
    1.03
     Bij
    1.02
    Bij
    0.99
     Bei
    0.94
     bei
    0.93
     при
    0.90
    При
    0.88
     При
    0.83
    при
    0.79
    bij
    0.78
    Act Density 0.004%

    No Known Activations