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

    Neuronpedia

    INDEX
    Explanations

    exclamatory expressions expressing surprise or admiration

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or strong emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.75
    SPONSORED
    -0.73
    istrates
    -0.70
    Generally
    -0.69
     predomin
    -0.67
     hereafter
    -0.65
     primarily
    -0.65
     pse
    -0.65
    isSpecialOrderable
    -0.65
    etheless
    -0.65
    POSITIVE LOGITS
    !!
    1.02
    !!!!!
    0.97
    !!!
    0.96
    eeee
    0.95
    !!!!
    0.94
    !!!!!!!!
    0.92
    oooooooooooooooo
    0.87
    oooooooo
    0.85
    Wow
    0.85
    ?!
    0.83
    Act Density 0.312%

    No Known Activations