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

    Neuronpedia

    INDEX
    Explanations

    numerical scores or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.76
    orem
    -0.65
     satell
    -0.59
    plin
    -0.58
    equality
    -0.57
    iewicz
    -0.57
    merce
    -0.57
     autonom
    -0.55
     ."
    -0.54
     compr
    -0.54
    POSITIVE LOGITS
    %)
    1.73
    %),
    1.50
    +)
    1.43
    )/
    1.39
    %).
    1.39
    )
    1.38
    )=
    1.36
    ),"
    1.34
    ):
    1.33
    )!
    1.32
    Act Density 0.098%

    No Known Activations