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

    Neuronpedia

    INDEX
    Explanations

    patterns involving the word "ATION" in the text

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    ings
    -0.75
    NewReader
    -0.68
    érables
    -0.56
    ulations
    -0.52
    ViewImports
    -0.50
    WebControls
    -0.50
    ups
    -0.49
     ErrIntOverflow
    -0.48
    body
    -0.48
    FetchType
    -0.48
    POSITIVE LOGITS
    ATION
    2.19
    NUMX
    0.79
    ATIO
    0.64
     Italijanski
    0.64
    chkin
    0.62
    Programmer
    0.59
     dAtA
    0.59
     Programmer
    0.59
     Waray
    0.59
    ATIONAL
    0.58
    Act Density 0.001%

    No Known Activations