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

    Neuronpedia

    INDEX
    Explanations

    references to "white" or variations of the word in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.99
    FormTagHelper
    -0.95
     Permalink
    -0.94
    /*
    -0.93
    __":
    -0.93
     дописавши
    -0.92
     للاسماء
    -0.90
     henvisninger
    -0.88
     okuyayım
    -0.88
     propOrder
    -0.87
    POSITIVE LOGITS
     White
    1.81
    White
    1.64
     white
    1.50
     WHITE
    1.47
    white
    1.46
    WHITE
    1.45
     Whites
    1.41
     Whitehead
    1.26
    Whites
    1.23
    WhiteSpace
    1.21
    Act Density 0.077%

    No Known Activations