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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or strong emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cade
    -0.15
    ÑģÑĮ
    -0.15
    HEY
    -0.14
     Hmm
    -0.14
    seau
    -0.14
     hmm
    -0.14
     à¹Ģà¸ģม
    -0.14
    SizeMode
    -0.14
    illet
    -0.14
    nech
    -0.14
    POSITIVE LOGITS
     another
    0.17
    osh
    0.16
    aukee
    0.15
    ite
    0.15
     look
    0.15
    alm
    0.15
    another
    0.14
    azing
    0.14
    Utc
    0.14
    azon
    0.13
    Act Density 0.057%

    No Known Activations