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

    Neuronpedia

    INDEX
    Explanations

    indications of code being present in various forms, such as declarations, functions, property methods, scope checks, or specific syntax elements

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    expo
    -0.53
     Ở
    -0.52
     Denken
    -0.51
    a
    -0.51
    ます
    -0.50
    GraphicsUnit
    -0.50
     disponibilités
    -0.49
    Dislikes
    -0.48
     Jolie
    -0.48
     Parcelable
    -0.48
    POSITIVE LOGITS
    should
    1.84
     shoulders
    1.33
    Should
    1.18
     Shoulders
    1.09
    shoulder
    1.05
     épaules
    1.00
     shoulder
    0.91
    hould
    0.90
     hombros
    0.89
     Shoulder
    0.87
    Act Density 0.005%

    No Known Activations