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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific punctuation marks and sentence structure indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    1
    -0.66
    2
    -0.64
    7
    -0.60
     évêque
    -0.58
     hypotension
    -0.56
    bbene
    -0.53
    4
    -0.52
     is
    -0.52
    io
    -0.52
     avanti
    -0.52
    POSITIVE LOGITS
     $_"
    1.01
    .~(\
    0.98
    "}")
    0.96
    клопе
    0.94
    `,
    0.89
    NUMX
    0.89
     lenker
    0.87
    WriteBarrier
    0.85
    ".
    0.84
    AccessorTable
    0.84
    Act Density 0.127%

    No Known Activations