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

    Neuronpedia

    INDEX
    Explanations

    references to different types of "service", especially military service

    oai_token-act-pair · gpt-3.5-turbo

    references to military service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Stage
    -0.69
    Ze
    -0.65
     Stam
    -0.65
    romeda
    -0.64
    Detailed
    -0.64
    VB
    -0.61
    Plot
    -0.60
     fertile
    -0.60
    arest
    -0.59
    storms
    -0.59
    POSITIVE LOGITS
     acad
    0.92
    rifice
    0.88
     Employees
    0.83
    service
    0.80
     obligation
    0.79
    hire
    0.79
    lyak
    0.75
    irmation
    0.73
    able
    0.72
    avement
    0.72
    Act Density 0.032%

    No Known Activations