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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and organizations in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ£
    -0.18
    ordan
    -0.17
    оза
    -0.17
    λον
    -0.15
    ITO
    -0.15
    ito
    -0.14
     Zuk
    -0.14
    alin
    -0.14
    lico
    -0.13
    kenin
    -0.13
    POSITIVE LOGITS
    bane
    0.18
    Ngh
    0.16
     Gen
    0.15
    .binding
    0.15
    erli
    0.14
    åıij
    0.14
     Türk
    0.14
     Axis
    0.14
     Manga
    0.14
    =:
    0.13
    Act Density 0.054%

    No Known Activations