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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to employment and labor relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    armor
    -0.16
    -map
    -0.16
    elize
    -0.16
    oloj
    -0.15
    utsch
    -0.15
    ény
    -0.14
    .TODO
    -0.14
     ãĥĬ
    -0.14
    olor
    -0.14
    ewe
    -0.14
    POSITIVE LOGITS
     employee
    0.26
     worker
    0.25
     Employee
    0.24
     Employees
    0.24
     Worker
    0.24
     workers
    0.23
     employees
    0.23
    -worker
    0.21
     Workers
    0.20
    employee
    0.20
    Act Density 0.710%

    No Known Activations