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

    Neuronpedia

    INDEX
    Explanations

    question marks and response indicators in dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     why
    -0.43
     apakah
    -0.34
     warum
    -0.34
     does
    -0.32
     did
    -0.32
    آیا
    -0.29
     whoever
    -0.29
    這就是
    -0.28
    ViewImports
    -0.28
     maybe
    -0.28
    POSITIVE LOGITS
     How
    1.30
     What
    1.29
    How
    1.04
    What
    1.01
     Where
    0.91
     Which
    0.87
    Where
    0.78
     Who
    0.77
    httphttps
    0.72
    Which
    0.71
    Act Density 0.389%

    No Known Activations