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

    Neuronpedia

    INDEX
    Explanations

    occurrences of characters preparing for a party

    oai_token-act-pair · gemini-2.0-flash

    items related to tableware

    np_token-act-pair-logits · gpt-4o-mini

    plates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IBU
    -0.52
    PhysRev
    -0.52
     Grosso
    -0.52
    moiselle
    -0.52
     Gautier
    -0.51
    idão
    -0.49
    -0.49
    belo
    -0.48
    Sucesor
    -0.47
     bey
    -0.47
    POSITIVE LOGITS
     plates
    0.78
    ware
    0.77
     Plates
    0.73
     plate
    0.72
     Plate
    0.70
    Plates
    0.69
     glassware
    0.69
     ware
    0.67
     dishes
    0.66
    plates
    0.65
    Act Density 1.801%

    No Known Activations