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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "closed" and related concepts indicating closure or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.93
    AppMethodBeat
    -0.79
    ècie
    -0.74
     CreateTagHelper
    -0.72
    ItemBackground
    -0.72
    QMetaType
    -0.68
     partea
    -0.68
     arbet
    -0.67
     âgées
    -0.67
    ыгана
    -0.67
    POSITIVE LOGITS
     closed
    1.69
     Closed
    1.60
    Closed
    1.51
     closes
    1.48
     clos
    1.45
     closing
    1.43
    closed
    1.38
     CLOSED
    1.37
     closures
    1.36
     Closing
    1.33
    Act Density 0.116%

    No Known Activations