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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /
    -0.63
    -
    -0.54
    Xaml
    -0.54
    ,
    -0.49
    (
    -0.45
    xae
    -0.45
    X
    -0.44
    "
    -0.43
    ondy
    -0.42
    numRows
    -0.42
    POSITIVE LOGITS
     however
    1.21
    however
    1.11
    ;;;
    0.99
     moreover
    0.91
     hence
    0.88
     ")";
    0.85
     namely
    0.85
     namun
    0.85
    awtextra
    0.84
    _;
    0.82
    Act Density 0.147%

    No Known Activations