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

    Neuronpedia

    INDEX
    Explanations

    references to organizational values and principles related to people and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intervening
    -0.18
    ä¹ĭéĹ´
    -0.17
    _firestore
    -0.17
    ppelin
    -0.16
    ô
    -0.15
    amilia
    -0.15
    á»įt
    -0.15
    coni
    -0.15
    ubber
    -0.15
    æł¹
    -0.15
    POSITIVE LOGITS
     centered
    0.15
    uala
    0.15
     centr
    0.15
    й
    0.15
    oder
    0.15
     Hass
    0.14
     Dead
    0.14
     dead
    0.14
    åģı
    0.14
    okus
    0.13
    Act Density 0.016%

    No Known Activations