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

    Neuronpedia

    INDEX
    Explanations

    statistical reliability indicators and their associated values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bildeten
    -0.41
    Miss
    -0.39
     étrangers
    -0.39
    int
    -0.37
     Daddy
    -0.37
    ẵn
    -0.36
    طط
    -0.36
    unt
    -0.36
    бку
    -0.36
    bücher
    -0.36
    POSITIVE LOGITS
    awtextra
    1.06
    =.
    0.91
    (.
    0.89
     (.
    0.81
    {.
    0.71
    etcode
    0.69
    IntoConstraints
    0.69
     decimals
    0.67
     [.
    0.67
    ollectionView
    0.65
    Act Density 0.959%

    No Known Activations