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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or connections between people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ayr
    -0.16
    acob
    -0.16
    ault
    -0.15
     Robin
    -0.14
    anas
    -0.14
    visor
    -0.14
    opian
    -0.14
    姿
    -0.14
    faq
    -0.14
    chg
    -0.13
    POSITIVE LOGITS
     anything
    0.19
    anything
    0.17
     Anything
    0.17
    Anything
    0.16
     Westbrook
    0.15
    edy
    0.15
    ingers
    0.15
    mî
    0.14
    .gs
    0.14
    ingen
    0.14
    Act Density 0.060%

    No Known Activations