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

    Neuronpedia

    INDEX
    Explanations

    the interjection "Oh"

    oai_token-act-pair · gpt-3.5-turbo

    expressive interjections of surprise or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUM
    -0.74
     fullest
    -0.69
     Construct
    -0.69
    perature
    -0.69
    -+-+
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    */(
    -0.65
    eers
    -0.64
    iership
    -0.63
     Reborn
    -0.61
    POSITIVE LOGITS
    hhhh
    0.94
    anian
    0.87
    oh
    0.86
    hh
    0.86
     dear
    0.85
    hhh
    0.85
     yeah
    0.81
    oy
    0.80
    oho
    0.80
    umph
    0.79
    Act Density 0.017%

    No Known Activations