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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and expressions in equations and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.96
    abe
    -0.75
    +"'
    -0.74
    มาะ
    -0.74
    Appender
    -0.73
    हो
    -0.72
    Regel
    -0.72
     Wart
    -0.71
    lingo
    -0.70
    पे
    -0.70
    POSITIVE LOGITS
    {\
    2.83
     {\
    2.17
    ){\
    1.94
    }{\
    1.52
    ]{\
    1.49
    ,{\
    1.48
    {{\
    1.45
    ={\
    1.43
    ({\
    1.36
    ${\
    1.36
    Act Density 0.415%

    No Known Activations