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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     géné
    -0.48
    XMLSchema
    -0.45
     Sre
    -0.42
    Brace
    -0.42
     Respir
    -0.41
    関
    -0.41
    '
    -0.41
    bonucle
    -0.41
     Lump
    -0.40
     grafted
    -0.40
    POSITIVE LOGITS
     etc
    0.97
    цездатний
    0.91
    MigrationBuilder
    0.90
     Мексичка
    0.82
     jspb
    0.81
    etc
    0.79
     Италијани
    0.78
     그리고
    0.78
     ...)
    0.77
     …)
    0.76
    Act Density 0.285%

    No Known Activations