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

    Neuronpedia

    INDEX
    Explanations

    references to people and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -1.00
    IUrlHelper
    -0.97
    RectangleBorder
    -0.96
    AndroidJUnit
    -0.95
    GEBURTSDATUM
    -0.95
     snippetHide
    -0.94
     חיצוניים
    -0.91
    webElementXpaths
    -0.90
    $")
    -0.88
    ousands
    -0.87
    POSITIVE LOGITS
     et
    0.58
    ,
    0.53
    -
    0.49
    her
    0.49
    p
    0.45
     Her
    0.44
    py
    0.42
    Her
    0.42
    n
    0.41
    for
    0.41
    Act Density 0.645%

    No Known Activations