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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inclusion or composition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lar
    -0.17
    alsy
    -0.16
    anger
    -0.15
    rus
    -0.15
    ÑĨик
    -0.14
    éļª
    -0.14
    uros
    -0.14
    zas
    -0.14
    .hm
    -0.14
    rado
    -0.14
    POSITIVE LOGITS
    erras
    0.18
    اختÛĮ
    0.14
    ech
    0.14
    573
    0.14
    chmod
    0.14
    íĶ
    0.13
    ABCDEFG
    0.13
     Tam
    0.13
    inue
    0.13
     details
    0.13
    Act Density 0.004%

    No Known Activations