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

    Neuronpedia

    INDEX
    Explanations

    specific dates or time references, particularly within January

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Ambro
    -0.67
    hamdu
    -0.59
     Wiese
    -0.58
    věř
    -0.57
     thư
    -0.57
    rell
    -0.57
     Điều
    -0.55
    ávat
    -0.55
     Moos
    -0.54
    Lass
    -0.54
    POSITIVE LOGITS
     JANUARY
    1.34
     Janus
    1.34
     January
    1.27
     january
    1.23
     JAN
    1.23
    january
    1.17
    January
    1.15
     januari
    1.15
     Jan
    1.13
     janvier
    1.11
    Act Density 0.022%

    No Known Activations