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

    Neuronpedia

    INDEX
    Explanations

    code-related constructs such as function definitions and return statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.69
    "--
    -0.59
    bootstrapcdn
    -0.57
    لمانيا
    -0.56
    انجليز
    -0.54
    '--
    -0.52
     AssemblyVersion
    -0.52
    —.
    -0.52
    '__
    -0.52
    —"
    -0.51
    POSITIVE LOGITS
     mixed
    1.30
    mixed
    1.24
    Mixed
    0.83
     Mixed
    0.81
     string
    0.77
    string
    0.77
     \
    0.76
     mixte
    0.72
     integer
    0.71
     gemis
    0.70
    Act Density 0.129%

    No Known Activations