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

    Neuronpedia

    INDEX
    Explanations

    legal or contractual terms related to employment agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĥn
    -0.17
    ypy
    -0.16
    æIJ
    -0.14
     layer
    -0.13
    ijd
    -0.13
     Admission
    -0.13
    léd
    -0.13
    ("[%
    -0.13
     Baghd
    -0.13
    гов
    -0.13
    POSITIVE LOGITS
     expense
    0.29
     travel
    0.27
     Expense
    0.26
    Expense
    0.26
    expense
    0.25
     expenses
    0.24
     Travel
    0.24
     travelling
    0.23
    Travel
    0.23
     Expenses
    0.23
    Act Density 0.107%

    No Known Activations