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

    Neuronpedia

    INDEX
    Explanations

    containing the mention or concept of "Members."

    oai_token-act-pair · gpt-3.5-turbo

    references to membership in various groups or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.72
     Tropical
    -0.63
    BUS
    -0.61
    ijn
    -0.60
     Pwr
    -0.60
    fters
    -0.59
    trop
    -0.57
    enegger
    -0.57
    NRS
    -0.56
    uras
    -0.56
    POSITIVE LOGITS
    hips
    1.59
    hip
    1.07
    doms
    1.00
     dues
    0.88
    member
    0.87
    ials
    0.83
    meal
    0.81
    cius
    0.80
    ority
    0.79
     of
    0.79
    Act Density 0.074%

    No Known Activations