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

    Neuronpedia

    INDEX
    Explanations

    references to employees in workplace contexts

    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
    Pac
    -0.70
    las
    -0.70
    geon
    -0.67
    COMPLE
    -0.67
    caster
    -0.66
    forward
    -0.65
    olithic
    -0.65
    soon
    -0.64
    ique
    -0.64
    POSITIVE LOGITS
     cafeteria
    0.85
     unions
    0.84
     Employees
    0.83
     employees
    0.76
    utenant
    0.74
    onomy
    0.74
     payroll
    0.73
     stationed
    0.71
    arers
    0.69
     employee
    0.69
    Act Density 0.053%

    No Known Activations