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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    strong affirmative language related to effectiveness or ease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -1.01
    etheless
    -0.73
    foreseen
    -0.50
    ãĢİ
    -0.49
    [/
    -0.48
    ":[{"
    -0.47
    wcs
    -0.47
    luster
    -0.47
     showc
    -0.45
    accompan
    -0.45
    POSITIVE LOGITS
    )
    1.71
    ?)
    1.60
    )"
    1.59
    ),
    1.57
    !)
    1.56
    ),"
    1.54
    )?
    1.50
    ):
    1.50
    )|
    1.49
    )-
    1.49
    Act Density 0.874%

    No Known Activations