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

    Neuronpedia

    INDEX
    Explanations

    references to movie genres and their corresponding identifiers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.95
     referrerpolicy
    -0.88
    CloseOperation
    -0.87
     الحره
    -0.86
    новништво
    -0.85
    EndGlobalSection
    -0.80
     समीक्षक
    -0.79
     pleaſure
    -0.79
     виправивши
    -0.78
     }}"></
    -0.77
    POSITIVE LOGITS
    fficiency
    0.44
    ونا
    0.44
    achau
    0.43
    さき
    0.40
    Erfolge
    0.39
     OK
    0.39
     skog
    0.38
     pietra
    0.37
    drage
    0.37
    驗
    0.37
    Act Density 0.094%

    No Known Activations