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

    Neuronpedia

    INDEX
    Explanations

    exclamation marks and expressions of excitement or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ese
    -0.18
    itor
    -0.16
    Xem
    -0.16
    ses
    -0.16
    iler
    -0.15
    nte
    -0.15
    ESA
    -0.15
    ctor
    -0.15
    ney
    -0.15
    ites
    -0.15
    POSITIVE LOGITS
    ?!
    0.28
    !--
    0.28
    [](
    0.27
    !(
    0.19
    and
    0.16
    owell
    0.16
    !!.
    0.15
    s
    0.15
    rames
    0.15
    apult
    0.15
    Act Density 0.138%

    No Known Activations