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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly those in entertainment or public life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walsh
    -0.15
    positor
    -0.15
    ieve
    -0.15
    criptors
    -0.14
     sunk
    -0.14
    .chomp
    -0.14
    erge
    -0.14
    vÄĽÅĻ
    -0.14
     Plate
    -0.14
    acco
    -0.13
    POSITIVE LOGITS
     Andrew
    0.17
    465
    0.16
    ::-
    0.15
    Andrew
    0.14
    ackson
    0.14
     imp
    0.14
     stake
    0.14
     Andy
    0.13
     Lowell
    0.13
    adian
    0.13
    Act Density 0.023%

    No Known Activations