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

    Neuronpedia

    INDEX
    Explanations

    references to specific equations or models in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    617
    -0.15
    amura
    -0.15
    ARGIN
    -0.15
    acey
    -0.14
    ReturnValue
    -0.14
    atal
    -0.14
    011
    -0.14
    à¸ģำ
    -0.14
    ITERAL
    -0.14
    ARRANT
    -0.14
    POSITIVE LOGITS
    ansen
    0.17
    iste
    0.16
    ãĤĿ
    0.15
    leigh
    0.14
    oldown
    0.14
    WR
    0.14
     Boeh
    0.14
    Č↵
    0.14
    isti
    0.14
    @Spring
    0.13
    Act Density 0.007%

    No Known Activations