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

    Neuronpedia

    INDEX
    Explanations

    references to a specific brand or product name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udit
    -0.18
    omba
    -0.17
    pus
    -0.16
    thon
    -0.16
    pu
    -0.15
    æķı
    -0.15
    OLUMNS
    -0.14
    iqueta
    -0.14
    ailles
    -0.14
    ä¸Ī
    -0.14
    POSITIVE LOGITS
     Gu
    0.29
    Gu
    0.28
     gu
    0.26
    ilty
    0.23
    adal
    0.22
    adel
    0.22
    atem
    0.20
    o
    0.20
     GU
    0.20
    gu
    0.18
    Act Density 0.012%

    No Known Activations