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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "closed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.99
    ècie
    -0.81
     CreateTagHelper
    -0.80
    AppMethodBeat
    -0.78
    QMetaType
    -0.75
     réaliste
    -0.70
    ыгана
    -0.69
    ItemBackground
    -0.68
    EDEFAULT
    -0.67
     façons
    -0.67
    POSITIVE LOGITS
     closed
    1.64
     Closed
    1.56
    Closed
    1.47
     closes
    1.44
     clos
    1.42
     closing
    1.36
     CLOSED
    1.33
    closed
    1.32
     closures
    1.29
    losures
    1.27
    Act Density 0.093%

    No Known Activations