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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "Marg" followed by a specific number

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention or focus on the name "Margaret."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.80
    enegger
    -0.79
    ctor
    -0.74
    footed
    -0.71
    GROUP
    -0.69
    ãģ¦
    -0.68
     hearing
    -0.67
     Parenthood
    -0.67
    INESS
    -0.66
    ÄŁ
    -0.65
    POSITIVE LOGITS
    aret
    1.14
    inal
    1.06
    olis
    1.06
    inally
    0.96
    reet
    0.95
    olicy
    0.87
    inals
    0.86
    illard
    0.86
    iana
    0.86
    ace
    0.85
    Act Density 0.021%

    No Known Activations