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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating location or spatial relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.71
    ISupport
    -0.58
     AssemblyVersion
    -0.57
     Baillargeon
    -0.53
    writeFieldEnd
    -0.53
     GenerationType
    -0.52
    bolite
    -0.51
    Mű
    -0.51
    ViewFeatures
    -0.51
    cyklopedia
    -0.50
    POSITIVE LOGITS
     kteří
    0.60
     ktorí
    0.58
    sizeCache
    0.58
     ویکی‌پدیای
    0.57
     stanovnika
    0.57
    KommentareTeilen
    0.57
    сылкі
    0.56
    تفصیلات
    0.56
     whom
    0.55
    whom
    0.54
    Act Density 0.207%

    No Known Activations