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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "simple" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.88
    IsContent
    -0.81
     dégust
    -0.80
     "..\..\..\
    -0.79
     réfrig
    -0.77
     atteinte
    -0.76
     ContentValues
    -0.76
     AssemblyCompany
    -0.76
     "..\..\
    -0.75
     Protobuf
    -0.75
    POSITIVE LOGITS
     simple
    3.38
     Simple
    3.09
    simple
    3.03
    Simple
    2.97
     SIMPLE
    2.88
     simples
    2.58
    SIMPLE
    2.50
     simplicity
    2.27
     simplest
    2.21
     simpler
    2.16
    Act Density 0.079%

    No Known Activations