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

    Neuronpedia

    INDEX
    Explanations

    distances and measurements indicated in kilometers, miles, feet, and meters

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to distances and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.97
    edIn
    -0.76
    resso
    -0.72
    ernaut
    -0.68
    ():
    -0.65
    ritch
    -0.64
    quished
    -0.63
    estro
    -0.62
    ernel
    -0.60
    drive
    -0.60
    POSITIVE LOGITS
    ),"
    1.29
    )
    1.16
    )."
    1.15
    ),
    1.15
    %)
    1.14
    )"
    1.10
    )=
    1.10
    ).[
    1.08
    ).
    1.07
    %).
    1.07
    Act Density 0.199%

    No Known Activations