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

    Neuronpedia

    INDEX
    Explanations

    phrases related to relationships and familial bonds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iegel
    -0.16
    mund
    -0.13
    ')."
    -0.12
    ãģ¡ãĤĩ
    -0.11
    ruta
    -0.11
    rq
    -0.11
    หาร
    -0.11
    male
    -0.11
    OURCES
    -0.11
    lah
    -0.11
    POSITIVE LOGITS
    lessly
    0.17
    ablish
    0.14
    perature
    0.14
    (...)↵
    0.14
    idth
    0.14
    ῦ
    0.14
    -than
    0.14
    typings
    0.13
    //**↵
    0.12
    -либо
    0.12
    Act Density 6.214%

    No Known Activations