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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community services and outreach efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astle
    -0.20
    olls
    -0.16
    ABLE
    -0.16
     pur
    -0.15
     lip
    -0.15
    ucu
    -0.15
    ifar
    -0.15
    abase
    -0.15
    emma
    -0.15
    able
    -0.15
    POSITIVE LOGITS
    ikan
    0.17
    ace
    0.16
    Ĥ
    0.16
    EG
    0.15
    ека
    0.15
    ê°ij
    0.14
     Ruth
    0.14
    æݪ
    0.14
    StateException
    0.14
    ACE
    0.14
    Act Density 0.018%

    No Known Activations