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

    Neuronpedia

    INDEX
    Explanations

    words indicating emotions or exclamations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oord
    -0.17
    hol
    -0.16
     Union
    -0.15
    yd
    -0.14
    alian
    -0.14
    976
    -0.14
    ourced
    -0.14
    .Linked
    -0.13
    fare
    -0.13
     Thorn
    -0.13
    POSITIVE LOGITS
    çĦ¡ãģĹãģ
    0.17
    è¦ļ
    0.15
    tablename
    0.15
    หà¸Ļ
    0.14
    çļ
    0.14
    yonel
    0.14
    regor
    0.14
     opendir
    0.13
    xec
    0.13
    WAR
    0.13
    Act Density 0.247%

    No Known Activations