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

    Neuronpedia

    INDEX
    Explanations

    code structure elements, such as braces and access modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing braces and structural end points in code blocks.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     EClass
    -0.27
     HOLD
    -0.25
     ri
    -0.25
    flächen
    -0.25
    ся
    -0.23
    HtmlAttribute
    -0.23
     летом
    -0.23
    IBAction
    -0.22
     useAuth
    -0.22
    ổng
    -0.21
    POSITIVE LOGITS
     private
    1.43
    private
    1.40
     Private
    1.18
    Private
    1.13
     PRIVATE
    1.12
     privado
    1.10
     privately
    1.09
     privaten
    1.08
    PRIVATE
    1.03
    私
    1.03
    Act Density 0.121%

    No Known Activations