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

    Neuronpedia

    INDEX
    Explanations

    references to leadership roles and authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elpers
    -0.17
    onen
    -0.15
    -dashboard
    -0.15
    arel
    -0.15
    aired
    -0.15
    uset
    -0.14
    ndo
    -0.14
     dash
    -0.14
    ük
    -0.14
    yers
    -0.14
    POSITIVE LOGITS
     cl
    0.16
    reon
    0.14
     Bottom
    0.14
    isLoggedIn
    0.13
    omain
    0.13
     excell
    0.13
     بخ
    0.13
    ibble
    0.13
    ount
    0.13
    æŀ
    0.13
    Act Density 0.140%

    No Known Activations