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

    Neuronpedia

    INDEX
    Explanations

    time durations in months

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time, specifically in months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.90
     Haram
    -0.87
     hypocr
    -0.74
    oos
    -0.72
    otle
    -0.71
    inburgh
    -0.70
    aque
    -0.69
    Alias
    -0.68
    ocratic
    -0.67
     Behavior
    -0.66
    POSITIVE LOGITS
     ago
    1.07
    pring
    0.93
     Ples
    0.81
     Ukrain
    0.78
     gestation
    0.77
     pregnant
    0.77
    assetsadobe
    0.77
    hips
    0.76
     Ago
    0.72
    ruary
    0.70
    Act Density 0.043%

    No Known Activations