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

    Neuronpedia

    INDEX
    Explanations

    references to scientific papers or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.75
    featureID
    -0.70
    AnchorStyles
    -0.66
    ########.
    -0.65
    UnusedPrivate
    -0.64
     AssemblyCulture
    -0.63
    setof
    -0.62
    Архівовано
    -0.60
    CppMethod
    -0.60
    存于互联网档案馆
    -0.60
    POSITIVE LOGITS
    ,
    0.86
     अलावा
    0.56
    新たに
    0.54
    ępnie
    0.53
     lisäksi
    0.52
    [toxicity=0]
    0.52
    uksessa
    0.49
     ,
    0.48
     ширина
    0.48
    titutes
    0.48
    Act Density 0.348%

    No Known Activations