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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the prefix "ex" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     numberOfRows
    -0.87
    QMetaType
    -0.85
     useParams
    -0.81
    Personendaten
    -0.79
    mobileqq
    -0.78
    earned
    -0.78
     kaynağından
    -0.78
     LatLng
    -0.77
    ########.
    -0.77
    Cordialement
    -0.77
    POSITIVE LOGITS
     ex
    2.63
    ex
    2.51
     Ex
    2.50
    Ex
    2.42
     EX
    2.07
    EX
    1.92
     eks
    1.27
     exc
    1.25
     Exo
    1.22
    exa
    1.19
    Act Density 0.105%

    No Known Activations