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

    Neuronpedia

    INDEX
    Explanations

    the context or formatting of sections in a document, particularly those marked with specific tags such as <bos>

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __))
    -0.70
    "}")
    -0.69
    ();)
    -0.63
     تانيه
    -0.63
    Diwedd
    -0.61
    AnchorStyles
    -0.61
     jScrollPane
    -0.61
    ])));
    -0.60
    estens
    -0.58
    (;;)
    -0.56
    POSITIVE LOGITS
    ThroughAttribute
    0.72
    oredCriteria
    0.64
     scolaires
    0.61
     rémun
    0.56
     devons
    0.55
    TypedDataSet
    0.53
     frequenza
    0.53
    ఔ
    0.53
     étoit
    0.52
     liné
    0.51
    Act Density 0.066%

    No Known Activations