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

    Neuronpedia

    INDEX
    Explanations

    dates or specific days related to events or celebrations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific "Days" that celebrate or commemorate various events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.87
    umbn
    -0.78
    ancial
    -0.77
    acters
    -0.77
     gren
    -0.76
     glim
    -0.75
    merce
    -0.72
     crate
    -0.72
     pse
    -0.71
     constitu
    -0.71
    POSITIVE LOGITS
    dream
    1.31
    break
    0.91
    flower
    0.89
     Parade
    0.86
     Massacre
    0.80
    tri
    0.77
     Day
    0.76
    care
    0.74
    mond
    0.74
    leigh
    0.74
    Act Density 0.024%

    No Known Activations