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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain the start of a document or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    новништво
    -0.78
    transQ
    -0.68
    Referanser
    -0.66
    OGND
    -0.66
     للمعارف
    -0.63
     '\\;'
    -0.61
     Numerade
    -0.60
     zoude
    -0.59
    colgante
    -0.59
     ब्रेकडाउन
    -0.59
    POSITIVE LOGITS
    The
    0.62
    <bos>
    0.56
    【
    0.52
     the
    0.49
    avel
    0.46
    De
    0.45
     
    0.45
    '
    0.44
    In
    0.44
     The
    0.44
    Act Density 0.024%

    No Known Activations