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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their formatting in commands or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "):
    -1.23
    )");
    -1.15
    "){
    -1.12
    '):
    -1.11
    ),”
    -1.09
    )*/
    -1.05
    .")
    -1.03
    "},
    -1.01
    )";
    -1.01
    "],
    -1.01
    POSITIVE LOGITS
    _
    0.65
    -
    0.61
    B
    0.61
     kasarigan
    0.60
    O
    0.60
    E
    0.59
    ;
    0.57
     -
    0.56
    b
    0.56
    <eos>
    0.56
    Act Density 0.947%

    No Known Activations