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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events and occurrences happening at specific points in time

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases that indicate occurrences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    });
    -0.68
     Chosen
    -0.65
    uploads
    -0.64
    âĢ¢âĢ¢
    -0.62
     Returns
    -0.62
     experimented
    -0.62
    anooga
    -0.61
    assi
    -0.61
    ibles
    -0.60
     someday
    -0.60
    POSITIVE LOGITS
    quickShipAvailable
    0.85
    actionDate
    0.79
     stark
    0.73
     flanked
    0.71
     wake
    0.70
     Canaver
    0.69
     Alam
    0.69
     heels
    0.68
     spite
    0.68
    imaru
    0.68
    Act Density 0.272%

    No Known Activations