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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [âĢ¦
    -0.21
    âĢ¦↵
    -0.16
     âĢ¦↵
    -0.15
     [âĢ¦]↵
    -0.15
     [âĢ¦]
    -0.14
     â
    -0.14
     âĢ¦↵↵
    -0.14
    Question
    -0.14
    âĢ¦↵↵
    -0.13
     &#
    -0.13
    POSITIVE LOGITS
    ÌĨ
    0.14
    liž
    0.13
    aeda
    0.12
    /OR
    0.12
    #ad
    0.12
    oÄį
    0.12
    ahkan
    0.12
    rello
    0.12
    Ģ
    0.11
    <?,
    0.11
    Act Density 3.138%

    No Known Activations