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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing surprise or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    exaggerated expressions of surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourse
    -0.83
    isle
    -0.81
    vale
    -0.80
    isse
    -0.75
    DragonMagazine
    -0.73
    ajor
    -0.66
    Ö¼
    -0.65
     guiActiveUn
    -0.65
    Ń·
    -0.65
    asons
    -0.65
    POSITIVE LOGITS
     hurry
    0.72
     Rebirth
    0.63
    OOOO
    0.62
     Buff
    0.61
    oooo
    0.61
    ooo
    0.61
    Wow
    0.60
    hov
    0.60
     kid
    0.60
    aan
    0.60
    Act Density 0.124%

    No Known Activations