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

    Neuronpedia

    INDEX
    Explanations

    punctuation and syntax elements commonly used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.87
    <eos>
    -0.82
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.75
    }}}}
    -0.72
    ↵↵↵↵↵
    -0.71
     ostavi
    -0.71
    ↵↵↵↵↵↵
    -0.71
    ↵↵
    -0.71
    ↵↵↵↵
    -0.70
    ↵↵↵↵↵↵↵
    -0.69
    POSITIVE LOGITS
    </em>
    0.64
    GEBURTS
    0.60
    ,</
    0.58
    pherals
    0.56
    évaluateur
    0.56
     المعرف
    0.54
    apimachinery
    0.53
    ConstraintMaker
    0.52
    uminense
    0.51
    COUVER
    0.50
    Act Density 0.094%

    No Known Activations