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

    Neuronpedia

    INDEX
    Explanations

    special formatting markers or identifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -1.11
     Италијани
    -1.05
    oredCriteria
    -1.02
     >=",
    -1.01
    UnusedPrivate
    -0.94
    parsedMessage
    -0.87
    SharedDtor
    -0.87
     <=",
    -0.87
     дописавши
    -0.86
    XmlAccessType
    -0.83
    POSITIVE LOGITS
    <bos>
    0.95
    ↵
    0.91
    ↵↵
    0.91
    ↵↵↵
    0.63
     BoxDecoration
    0.58
    <eos>
    0.56
    logi
    0.45
     thiệu
    0.43
    ↵↵↵↵
    0.42
    [toxicity=0]
    0.42
    Act Density 0.074%

    No Known Activations