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

    Neuronpedia

    INDEX
    Explanations

    numerical data corresponding to experimental results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ↵
    -0.57
    r
    -0.46
     New
    -0.45
    full
    -0.45
     values
    -0.45
    .
    -0.44
    <eos>
    -0.43
     r
    -0.42
    cutt
    -0.42
    “
    -0.42
    POSITIVE LOGITS
    OGND
    1.06
     Normdatei
    1.01
    complexContent
    0.98
     للاسماء
    0.97
     autorytatywna
    0.94
    脚注の使い方
    0.88
    HtmlAttribute
    0.87
     صوتيه
    0.86
    \{\\
    0.83
    ScopeManager
    0.82
    Act Density 0.030%

    No Known Activations