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

    Neuronpedia

    INDEX
    Explanations

    references to shadows or shadowing, often in a metaphorical or thematic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anto
    -0.18
    Ń
    -0.17
    idl
    -0.15
    หมà¸Ķ
    -0.15
    ather
    -0.14
    ouch
    -0.14
    587
    -0.14
    .UnitTesting
    -0.14
    ZE
    -0.14
    ipi
    -0.14
    POSITIVE LOGITS
    ed
    0.23
     cast
    0.23
    y
    0.22
    fax
    0.20
     Cast
    0.20
     shadow
    0.20
    ing
    0.19
    ood
    0.19
    lands
    0.19
    alker
    0.18
    Act Density 0.017%

    No Known Activations