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

    Neuronpedia

    INDEX
    Explanations

    references to costs or expenditures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ircut
    -0.76
     wigs
    -0.71
    hyrchwyd
    -0.70
    cipar
    -0.70
    hlor
    -0.67
     моро
    -0.67
    vertra
    -0.67
     Atwood
    -0.66
    のカ
    -0.65
     moulds
    -0.65
    POSITIVE LOGITS
     Expenses
    1.45
     expenses
    1.41
    Expenses
    1.38
    expense
    1.36
     Expense
    1.32
    expenses
    1.32
     expense
    1.23
    Expense
    1.20
     gastos
    0.94
     gasto
    0.81
    Act Density 0.003%

    No Known Activations