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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific weeks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific week in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.80
    jri
    -0.65
    pend
    -0.65
    itars
    -0.64
     Gems
    -0.63
     Tigers
    -0.62
    ected
    -0.60
    emort
    -0.60
    ufficient
    -0.57
    awei
    -0.56
    POSITIVE LOGITS
    days
    1.36
    night
    1.16
    DAY
    1.00
    iversary
    0.88
     mornings
    0.86
     afternoon
    0.83
    day
    0.81
     Ago
    0.78
    morning
    0.77
    orrow
    0.76
    Act Density 0.053%

    No Known Activations