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

    Neuronpedia

    INDEX
    Explanations

    references to a 'latter' or 'former' comparison in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernen
    -0.16
    nict
    -0.15
    vre
    -0.15
    uese
    -0.14
    -ng
    -0.14
    rå
    -0.14
    EMPLARY
    -0.13
    ıģı
    -0.13
    ÅĤ
    -0.13
    yy
    -0.13
    POSITIVE LOGITS
    most
    0.34
    -most
    0.23
    mentioned
    0.21
    -day
    0.21
    lain
    0.17
    MOST
    0.17
     mentioned
    0.17
     part
    0.16
    -than
    0.16
     ones
    0.16
    Act Density 0.021%

    No Known Activations