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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Население
    -0.56
     her
    -0.56
    ,
    -0.50
     som
    -0.49
     Pre
    -0.48
     works
    -0.48
     men
    -0.48
     par
    -0.46
     or
    -0.46
     for
    -0.46
    POSITIVE LOGITS
     محفوظة
    0.87
     betweenstory
    0.82
     Gregorian
    0.81
     utafitiHapana
    0.80
     photolibrary
    0.79
     Monfieur
    0.79
    出版年
    0.77
    enumi
    0.77
     ་་
    0.77
    ">//
    0.75
    Act Density 0.268%

    No Known Activations