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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "won."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    win an award or election

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GroupLayout
    -0.42
    riwal
    -0.42
    Tracce
    -0.41
    InitStruct
    -0.41
    aktur
    -0.41
    ylase
    -0.40
    tagHelper
    -0.39
    CHW
    -0.39
    ViewFeatures
    -0.39
    ymal
    -0.39
    POSITIVE LOGITS
     won
    0.88
     Won
    0.82
    Won
    0.82
    won
    0.74
     WON
    0.73
    WON
    0.64
     shan
    0.46
     wouldn
    0.44
    әрмәләр
    0.44
    ona
    0.43
    Act Density 0.006%

    No Known Activations