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

    Neuronpedia

    INDEX
    Explanations

    structured code elements and their declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Private
    -0.20
     Private
    -0.20
     const
    -0.18
    害
    -0.17
    .private
    -0.17
    private
    -0.16
    Const
    -0.16
     PRIVATE
    -0.16
    const
    -0.16
    .Private
    -0.16
    POSITIVE LOGITS
     abstract
    0.33
     default
    0.29
    abstract
    0.28
     interface
    0.26
     void
    0.26
    default
    0.25
    void
    0.20
    "default
    0.19
     abstraction
    0.19
    interface
    0.19
    Act Density 0.035%

    No Known Activations