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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "employee" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to employees and employment-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trop
    -0.77
    theless
    -0.74
    las
    -0.72
    COMPLE
    -0.67
    Pac
    -0.67
    ¥µ
    -0.65
    Reloaded
    -0.65
    rency
    -0.64
    lag
    -0.63
    iques
    -0.62
    POSITIVE LOGITS
     unions
    1.02
     Employees
    0.90
    hips
    0.86
     cafeteria
    0.86
     salaries
    0.83
     stationed
    0.82
     union
    0.82
     employees
    0.80
     payroll
    0.79
     hired
    0.79
    Act Density 0.052%

    No Known Activations