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

    Neuronpedia

    INDEX
    Explanations

    large or impressive physical objects and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     torebka
    -0.37
    참고
    -0.35
    נא
    -0.32
     rallado
    -0.32
     plaît
    -0.32
    TabLayout
    -0.32
    害
    -0.31
    微妙
    -0.31
    尖
    -0.31
    刻
    -0.31
    POSITIVE LOGITS
     gigantic
    1.20
     giant
    1.13
     large
    1.12
     gigantes
    1.12
    Large
    1.11
     Large
    1.05
    large
    1.04
     LARGE
    1.03
     big
    1.00
    Huge
    0.99
    Act Density 1.116%

    No Known Activations