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

    Neuronpedia

    INDEX
    Explanations

    references to complex mathematical expressions or structured formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.85
     estekak
    -0.66
    '}}>
    -0.65
     ?>">
    -0.63
     незавершена
    -0.61
    uxxxx
    -0.61
    ]=="
    -0.61
    %。
    -0.58
    >>;
    -0.58
     the
    -0.57
    POSITIVE LOGITS
    1
    1.20
    zelfde
    0.60
    ১
    0.48
     newItem
    0.47
    １
    0.43
    १
    0.43
    topLeft
    0.42
    Lily
    0.42
    ی
    0.42
     Lily
    0.42
    Act Density 1.435%

    No Known Activations