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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating various versions or iterations of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ologne
    -0.15
    ÃŃ
    -0.15
    pta
    -0.15
    cam
    -0.15
    elsing
    -0.15
    ameleon
    -0.14
    rance
    -0.14
    ocht
    -0.14
    egend
    -0.14
    undy
    -0.14
    POSITIVE LOGITS
    _singleton
    0.15
     Pall
    0.15
    ãĥ¬ãĥ¼
    0.14
    æł·çļĦ
    0.14
     bac
    0.14
    /null
    0.13
    KeyName
    0.13
    atak
    0.13
    anch
    0.13
     sorts
    0.13
    Act Density 0.152%

    No Known Activations