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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afort
    -0.16
     bis
    -0.15
    erton
    -0.14
    cki
    -0.14
    isser
    -0.14
    urity
    -0.14
    	Copyright
    -0.14
    ãĥ¼ãĥ³
    -0.13
    rov
    -0.13
     Maul
    -0.13
    POSITIVE LOGITS
    ubb
    0.17
     سÙĥاÙĨ
    0.15
    qing
    0.15
    ाà¤Ĭ
    0.15
    prs
    0.14
    bul
    0.14
    ossip
    0.14
    ipar
    0.14
    argon
    0.14
    otel
    0.14
    Act Density 0.138%

    No Known Activations