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

    Neuronpedia

    INDEX
    Explanations

    numerical values or statistics related to health metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -1.00
    :✨
    -0.86
    LookAnd
    -0.85
     purpoſe
    -0.84
    contentLoaded
    -0.81
     itſelf
    -0.78
    IVEREF
    -0.77
     חיצוניים
    -0.76
     članak
    -0.76
     propOrder
    -0.76
    POSITIVE LOGITS
     
    0.59
    {\"
    0.59
    نامج
    0.59
    ‐
    0.54
    Revenir
    0.53
    iParam
    0.51
     C
    0.47
    ेंगे
    0.47
    −
    0.47
    同じく
    0.45
    Act Density 0.390%

    No Known Activations