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

    Neuronpedia

    INDEX
    Explanations

    code annotations and documentation comments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.72
    twimg
    -0.71
    principalTable
    -0.68
    ]$}
    -0.64
     invokingState
    -0.63
    setObjectName
    -0.63
    ?}",
    -0.63
    RefNanny
    -0.61
    itous
    -0.60
    AsUp
    -0.59
    POSITIVE LOGITS
    PRNewswire
    0.56
     sija
    0.54
    verwijspagina
    0.53
     تانيه
    0.50
    デューサー
    0.48
     dossiers
    0.48
    ீர
    0.46
    devamını
    0.46
     Senado
    0.46
    aimerais
    0.45
    Act Density 0.003%

    No Known Activations