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

    Neuronpedia

    INDEX
    Explanations

    numbers and their variations within expressions or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.85
    '}}>
    -0.64
     estekak
    -0.62
     ?>">
    -0.60
    __*/
    -0.60
     незавершена
    -0.60
    uxxxx
    -0.59
    ereço
    -0.59
    %;">
    -0.59
    %。
    -0.58
    POSITIVE LOGITS
    1
    1.17
    zelfde
    0.57
    ১
    0.47
    esModule
    0.46
    ی
    0.44
    １
    0.42
     newItem
    0.41
    topLeft
    0.41
    १
    0.41
    Lily
    0.40
    Act Density 1.416%

    No Known Activations