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

    Neuronpedia

    INDEX
    Explanations

    the concept of simplicity or straightforwardness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     passim
    -0.88
     atteinte
    -0.82
    IBarButtonItem
    -0.82
    endregion
    -0.75
     turquesa
    -0.75
     perpétu
    -0.73
    XmlAccessorType
    -0.73
     duquel
    -0.72
     Laub
    -0.71
     EntityManager
    -0.71
    POSITIVE LOGITS
     SIMPLE
    1.26
     Simple
    1.17
     simple
    1.13
    simpleType
    1.09
    SIMPLE
    1.07
    Simple
    1.03
    simple
    0.94
     simples
    0.92
     simpl
    0.89
     Plain
    0.86
    Act Density 0.085%

    No Known Activations