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

    Neuronpedia

    INDEX
    Explanations

    numerical values in a specific format (e.g., 7-9)

    oai_token-act-pair · gpt-3.5-turbo

    sequences of the number seven

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ument
    -0.79
    gart
    -0.70
     pastoral
    -0.62
     relat
    -0.62
    assetsadobe
    -0.61
    plom
    -0.61
     tant
    -0.60
     savior
    -0.59
    ocard
    -0.59
     baptism
    -0.58
    POSITIVE LOGITS
     Wonders
    1.07
    ecause
    0.99
    ioned
    0.92
    th
    0.91
    eenth
    0.91
    883
    0.89
    69
    0.86
    88
    0.84
    ippi
    0.83
    07
    0.83
    Act Density 0.080%

    No Known Activations