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

    Neuronpedia

    INDEX
    Explanations

    references to dates and temporal markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pumpkins
    -0.77
     pumpkin
    -0.77
     Pumpkin
    -0.75
    SEPTEMBER
    -0.73
    🎃
    -0.73
    OCTOBER
    -0.72
    Pumpkin
    -0.71
    Sept
    -0.71
    Aug
    -0.70
    __(/*!
    -0.69
    POSITIVE LOGITS
     March
    1.26
     February
    1.19
     January
    1.15
    February
    1.14
    March
    1.13
    January
    1.11
     Feb
    1.00
     MARCH
    0.98
     Valentine
    0.98
     FEBRUARY
    0.97
    Act Density 0.156%

    No Known Activations