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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by specific keywords or phrases

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ument
    -0.75
    gart
    -0.67
     pastoral
    -0.65
     relat
    -0.64
    coat
    -0.62
    assetsadobe
    -0.60
    plom
    -0.59
     savior
    -0.59
     yield
    -0.59
     dest
    -0.59
    POSITIVE LOGITS
    ecause
    1.07
     Wonders
    1.04
    eenth
    0.92
    ioned
    0.91
    th
    0.89
    DAY
    0.89
    07
    0.89
    883
    0.88
    69
    0.87
    88
    0.86
    Act Density 0.084%

    No Known Activations