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

    Neuronpedia

    INDEX
    Explanations

    exclamatory expressions of emotions

    oai_token-act-pair · gpt-3.5-turbo

    exclamation marks and expressions of strong emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atories
    -0.78
    lining
    -0.71
    ativity
    -0.70
     path
    -0.69
     outline
    -0.67
    ouf
    -0.67
    thal
    -0.66
    athering
    -0.65
     salient
    -0.63
    roup
    -0.62
    POSITIVE LOGITS
    !!!!!
    1.23
    !!!
    1.16
    !!
    1.14
    ?!
    0.98
     :-)
    0.98
    !/
    0.92
    !!!!
    0.92
    ??
    0.90
    @#&
    0.90
     ;)
    0.86
    Act Density 0.013%

    No Known Activations