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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieux
    -0.16
    ajo
    -0.15
     Chest
    -0.15
    iei
    -0.14
    rens
    -0.13
    ieu
    -0.13
    hp
    -0.13
    svp
    -0.13
     creators
    -0.13
    qli
    -0.13
    POSITIVE LOGITS
    егоÑĢ
    0.16
    ume
    0.15
    enting
    0.15
    elles
    0.14
     nÄĥ
    0.14
    /apis
    0.13
    addtogroup
    0.13
    asse
    0.13
    avage
    0.13
    meldung
    0.13
    Act Density 0.055%

    No Known Activations