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

    Neuronpedia

    INDEX
    Explanations

    programming-related metadata and documentation elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enci
    -0.16
     Uncomment
    -0.16
     Inherits
    -0.15
     Renders
    -0.15
    quate
    -0.14
     Defines
    -0.14
    дов
    -0.14
    gram
    -0.13
    eree
    -0.13
    еÑİ
    -0.13
    POSITIVE LOGITS
     Convenience
    0.23
     convenience
    0.22
    -wrapper
    0.19
    озвÑĢаÑīаеÑĤ
    0.19
     return
    0.18
     wrapper
    0.17
     retour
    0.16
     returns
    0.16
     Return
    0.15
    return
    0.15
    Act Density 0.107%

    No Known Activations