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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates, particularly in January

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    бло
    -0.70
     Wiese
    -0.66
    rell
    -0.65
    SHARE
    -0.62
    věř
    -0.60
    ضب
    -0.60
     carto
    -0.59
    stums
    -0.59
    Lik
    -0.59
     Waikato
    -0.59
    POSITIVE LOGITS
     JANUARY
    1.31
     January
    1.27
     Janus
    1.26
     JAN
    1.22
    JAN
    1.15
     Jann
    1.15
    January
    1.15
     Januar
    1.14
     january
    1.13
     Jan
    1.12
    Act Density 0.087%

    No Known Activations