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

    Neuronpedia

    INDEX
    Explanations

    mentions of units of time, such as months, years, days, and hours

    oai_token-act-pair · gpt-3.5-turbo

    temporal measurements such as days, months, and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acted
    -0.80
    Sov
    -0.79
    alore
    -0.78
    tarian
    -0.73
    ierrez
    -0.71
     suspic
    -0.70
    \\\\\\\\
    -0.69
     Flavoring
    -0.67
    dinand
    -0.67
    artisan
    -0.67
    POSITIVE LOGITS
     Ago
    0.99
     ago
    0.94
     elapsed
    0.89
     spent
    0.81
    cake
    0.77
    pring
    0.77
    pec
    0.73
    glass
    0.73
    birth
    0.73
     consecut
    0.73
    Act Density 0.186%

    No Known Activations