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

    Neuronpedia

    INDEX
    Explanations

    references to dates and events related to women's issues and celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jan
    -0.40
     jan
    -0.37
    Jan
    -0.35
    -Jan
    -0.35
    jan
    -0.35
     JAN
    -0.35
     January
    -0.32
    January
    -0.30
     janvier
    -0.26
     Ñıн
    -0.23
    POSITIVE LOGITS
    March
    0.40
     March
    0.38
     march
    0.29
     Lent
    0.21
     marching
    0.19
     marches
    0.18
    Ash
    0.18
     Ash
    0.18
     lent
    0.18
     marzo
    0.17
    Act Density 0.059%

    No Known Activations