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

    Neuronpedia

    INDEX
    Explanations

    the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itag
    -0.18
    uela
    -0.17
    ed
    -0.15
    archives
    -0.15
    ouver
    -0.15
    uel
    -0.15
    hawks
    -0.14
    ži
    -0.14
    ned
    -0.14
    positories
    -0.14
    POSITIVE LOGITS
    /her
    0.18
    odore
    0.17
    zelf
    0.16
    andre
    0.16
    -même
    0.15
    oretical
    0.15
    ##_
    0.15
    çuk
    0.15
    дÑĭ
    0.15
    à¹Ģà¸Ńà¸ĩ
    0.14
    Act Density 0.010%

    No Known Activations