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

    Neuronpedia

    INDEX
    Explanations

    references to employee benefits and labor regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olik
    -0.16
    amedi
    -0.15
    andr
    -0.15
    ADR
    -0.15
    ARGE
    -0.15
    anio
    -0.14
    ander
    -0.14
    asio
    -0.14
    ilden
    -0.13
    ieves
    -0.13
    POSITIVE LOGITS
     employees
    0.43
     employee
    0.40
     Employees
    0.36
     workers
    0.35
    employees
    0.35
     worker
    0.32
    Employees
    0.32
    employee
    0.31
     Employee
    0.31
    Employee
    0.28
    Act Density 0.264%

    No Known Activations