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

    Neuronpedia

    INDEX
    Explanations

    the Chinese word "的" which acts as a possessive or linking particle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fully
    -0.69
     Euri
    -0.65
    ReadInt
    -0.65
     stră
    -0.64
     Fath
    -0.63
     Aseg
    -0.62
     Nij
    -0.62
     esters
    -0.62
    Caste
    -0.61
    Kali
    -0.61
    POSITIVE LOGITS
    的
    1.40
    の
    0.87
    ChildScrollView
    0.78
    "]=
    0.77
    。
    0.77
    ']")
    0.75
    ，
    0.75
    ']='
    0.74
     的
    0.74
    Mə
    0.73
    Act Density 0.016%

    No Known Activations