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

    Neuronpedia

    INDEX
    Explanations

    references to shadows and shadow-like imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppins
    -0.15
    587
    -0.15
    ipi
    -0.15
    anto
    -0.14
    wil
    -0.14
    viÄį
    -0.14
    avanaugh
    -0.13
    Ń
    -0.13
    ddy
    -0.13
     flaming
    -0.13
    POSITIVE LOGITS
    ed
    0.29
     cast
    0.29
    y
    0.28
    fax
    0.26
    lands
    0.25
    ing
    0.24
    boxing
    0.23
     Cast
    0.23
    alker
    0.23
    cast
    0.22
    Act Density 0.016%

    No Known Activations