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

    Neuronpedia

    INDEX
    Explanations

    punctuations and separator marks in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.54
    ver
    -0.52
    for
    -0.52
    ns
    -0.51
    M
    -0.51
    .
    -0.49
    T
    -0.49
     Corintios
    -0.49
    n
    -0.48
    ↵
    -0.48
    POSITIVE LOGITS
     propOrder
    1.21
    Personendaten
    1.20
     CreateTagHelper
    1.08
     Wikimedijinoj
    0.96
    脚注の使い方
    0.95
     الرياضيه
    0.92
     ***!
    0.88
    Hochspringen
    0.88
    Hentet
    0.85
    tagHelperRunner
    0.84
    Act Density 0.001%

    No Known Activations