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

    Neuronpedia

    INDEX
    Explanations

    references to a specific individual or entity named "Brown."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     McGuire
    -0.86
    Kiri
    -0.83
    Ciri
    -0.83
     Gators
    -0.79
     Kira
    -0.78
    Kira
    -0.76
     Betts
    -0.75
     Kiri
    -0.73
     McClure
    -0.73
    KIR
    -0.73
    POSITIVE LOGITS
     Brown
    1.52
    BROWN
    1.41
     BROWN
    1.37
    Brown
    1.35
     Browns
    1.35
     browns
    1.23
     brown
    1.22
    brown
    1.10
    Brow
    1.07
     browned
    1.02
    Act Density 0.008%

    No Known Activations