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

    Neuronpedia

    INDEX
    Explanations

    time-related terms related to durations of 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
    -0.83
    oos
    -0.75
     Haram
    -0.74
     hypocr
    -0.74
    Alias
    -0.74
    \\\\\\\\
    -0.71
    aque
    -0.68
    icket
    -0.67
    inburgh
    -0.67
    ocratic
    -0.66
    POSITIVE LOGITS
     ago
    1.05
    pring
    0.93
    assetsadobe
    0.82
     pregnant
    0.80
     Ago
    0.79
     Ples
    0.78
     Ukrain
    0.76
    theless
    0.76
    mith
    0.74
    ths
    0.74
    Act Density 0.044%

    No Known Activations