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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions, such as specific durations or intervals

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enburg
    -0.68
    kef
    -0.61
    ukes
    -0.60
     Haram
    -0.60
    olini
    -0.60
     infl
    -0.60
    unci
    -0.60
    iola
    -0.59
    acus
    -0.57
     fortun
    -0.56
    POSITIVE LOGITS
     ago
    1.60
     Ago
    1.42
     elapsed
    0.96
    ago
    0.93
     Views
    0.79
     olds
    0.74
    inventoryQuantity
    0.74
     Ahead
    0.73
     Warranty
    0.72
     Anniversary
    0.71
    Act Density 0.062%

    No Known Activations