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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional statements and questions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enis
    -0.15
     conver
    -0.14
     no
    -0.14
    ëŀĢ
    -0.14
     not
    -0.14
    lum
    -0.14
    ,
    -0.14
     rowspan
    -0.13
     QDir
    -0.13
    ras
    -0.13
    POSITIVE LOGITS
     plá
    0.20
     you
    0.17
     Angiospermae
    0.17
     we
    0.15
    oplevel
    0.15
    ÑĸÑĤи
    0.15
    uras
    0.15
    egral
    0.15
    /Area
    0.15
    -txt
    0.15
    Act Density 0.198%

    No Known Activations