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

    Neuronpedia

    INDEX
    Explanations

    exclamatory statements or punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ese
    -0.18
    ncy
    -0.16
    ney
    -0.15
    unders
    -0.15
     vast
    -0.15
    Xem
    -0.15
     comer
    -0.15
    veh
    -0.15
    ãĢĤãĢĤ↵↵
    -0.15
    ESA
    -0.14
    POSITIVE LOGITS
    ?!
    0.32
    [](
    0.31
    !--
    0.22
    s
    0.19
    :)
    0.18
    owell
    0.16
    '-
    0.16
    ''
    0.16
    @↵
    0.16
    _
    0.15
    Act Density 0.131%

    No Known Activations