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

    Neuronpedia

    INDEX
    Explanations

    locations and contexts specified by the word "where."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DPS
    -0.47
     Adu
    -0.45
    Puff
    -0.44
    DPS
    -0.43
    onOptions
    -0.43
     Ekiti
    -0.43
    onomian
    -0.43
     Riti
    -0.43
    Offensive
    -0.42
     Yi
    -0.42
    POSITIVE LOGITS
     where
    1.75
    where
    1.64
    Where
    1.45
     Where
    1.42
     WHERE
    1.41
    WHERE
    1.37
     donde
    1.26
     où
    1.16
     dónde
    1.15
    Dónde
    1.13
    Act Density 0.148%

    No Known Activations