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

    Neuronpedia

    INDEX
    Explanations

    specific dates and days mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "on" used in various contexts within statements or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amus
    -0.77
    ptin
    -0.70
    soDeliveryDate
    -0.67
     Entered
    -0.65
    MODE
    -0.65
    à©
    -0.64
    ENCY
    -0.64
    ratulations
    -0.62
    few
    -0.62
    ï¸ı
    -0.62
    POSITIVE LOGITS
     behalf
    1.65
    etime
    1.19
    erous
    1.00
    eness
    1.00
     Wednesday
    0.99
     Friday
    0.98
     Sunday
    0.96
    etheless
    0.96
     Saturday
    0.95
     occasion
    0.95
    Act Density 0.138%

    No Known Activations