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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "aw" that indicate surprise or admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    رش
    -0.16
     Ged
    -0.15
    agal
    -0.15
    aab
    -0.15
     Heb
    -0.14
    iets
    -0.14
    ognito
    -0.14
    arget
    -0.14
    uzzer
    -0.14
    ometown
    -0.13
    POSITIVE LOGITS
    oft
    0.17
    las
    0.15
     Henri
    0.14
    æ©
    0.14
    renc
    0.14
     Laur
    0.14
    ist
    0.13
    ampa
    0.13
    ekil
    0.13
    =__
    0.13
    Act Density 0.012%

    No Known Activations