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

    Neuronpedia

    INDEX
    Explanations

    references to personal development and social responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guy
    -0.17
    vek
    -0.16
    ile
    -0.16
     guys
    -0.15
    ond
    -0.15
    anc
    -0.15
     fav
    -0.15
    nat
    -0.14
    hips
    -0.14
    zie
    -0.14
    POSITIVE LOGITS
     citizens
    0.29
     citizen
    0.27
    Cit
    0.27
     Citizens
    0.26
     contributing
    0.26
    cit
    0.25
     Citizen
    0.25
     responsible
    0.24
     citiz
    0.23
     productive
    0.23
    Act Density 0.155%

    No Known Activations