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

    Neuronpedia

    INDEX
    Explanations

    specific locations or settings

    oai_token-act-pair · gpt-3.5-turbo

    the word "where" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sudo
    -0.59
    ena
    -0.59
    activ
    -0.57
    });
    -0.54
    itely
    -0.53
    erity
    -0.52
    uno
    -0.51
    endo
    -0.50
    ovich
    -0.50
    elve
    -0.49
    POSITIVE LOGITS
     where
    3.12
    where
    2.64
     wherein
    2.02
     whence
    2.02
     WHERE
    1.93
     Where
    1.86
    Where
    1.83
     whereby
    1.63
    WHERE
    1.39
     wherever
    1.25
    Act Density 0.067%

    No Known Activations