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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "how"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uely
    -0.17
    飯
    -0.16
    ermen
    -0.15
    ören
    -0.15
    uate
    -0.15
    cente
    -0.15
    adele
    -0.15
    uman
    -0.15
    uisse
    -0.15
    uent
    -0.15
    POSITIVE LOGITS
    soever
    0.28
    itz
    0.26
    itzer
    0.24
    beit
    0.24
    arth
    0.20
    ards
    0.16
    ARD
    0.15
    麼
    0.15
    egg
    0.15
    æł·
    0.15
    Act Density 0.102%

    No Known Activations