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

    Neuronpedia

    INDEX
    Explanations

    structures and relationships in data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Према
    -0.60
    WORTH
    -0.60
    ########.
    -0.59
     ostavi
    -0.58
    )$_
    -0.56
    :%.
    -0.56
    mindedness
    -0.55
     Wh
    -0.54
    вної
    -0.54
     Zw
    -0.54
    POSITIVE LOGITS
    BrowserModule
    0.77
     InputDecoration
    0.67
     otomatig
    0.61
     supérieurs
    0.60
    المناصب
    0.59
    Personendaten
    0.58
    ResponseWriter
    0.57
     يتيمه
    0.56
    Fitur
    0.56
    HomeAsUpEnabled
    0.56
    Act Density 0.634%

    No Known Activations