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

    Neuronpedia

    INDEX
    Explanations

    references to "white" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -1.03
     bezeichneter
    -0.85
    __":
    -0.80
    MessageTagHelper
    -0.77
     CreateTagHelper
    -0.75
    bewerken
    -0.74
    FormTagHelper
    -0.74
    rrggbb
    -0.74
    yntaxException
    -0.73
     MenuView
    -0.72
    POSITIVE LOGITS
     White
    1.32
    White
    1.23
     white
    1.16
     WHITE
    1.13
    WHITE
    1.12
    white
    1.10
     Whites
    1.06
    Whites
    0.93
    白
    0.91
     blanca
    0.85
    Act Density 0.088%

    No Known Activations