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

    Neuronpedia

    INDEX
    Explanations

    instances of text formatting or structuring hints in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onix
    -0.64
    omon
    -0.51
     "
    -0.51
     morning
    -0.51
     this
    -0.50
    rond
    -0.50
    estra
    -0.49
     modern
    -0.48
    ressor
    -0.47
     Egan
    -0.46
    POSITIVE LOGITS
    ⓧ
    0.93
    ]")]
    0.86
    تقاوى
    0.85
    -</
    0.85
    KommentareTeilen
    0.83
    elemField
    0.82
    MathML
    0.80
    ंदीखरीदारी
    0.80
    "]));
    0.80
    WithIOException
    0.78
    Act Density 0.133%

    No Known Activations