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

    Neuronpedia

    INDEX
    Explanations

    terms and definitions related to naming and denoting concepts or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CommonModule
    -0.37
    AutoresizingMask
    -0.36
    WindowConstants
    -0.35
     Constitucional
    -0.35
    bentar
    -0.33
     Tasche
    -0.33
    appui
    -0.33
     ciudadana
    -0.32
     peine
    -0.32
     Kombat
    -0.32
    POSITIVE LOGITS
     means
    0.58
     referirse
    0.57
    是指
    0.55
     nahilalakip
    0.54
     désigne
    0.54
    Means
    0.50
     Means
    0.50
     refers
    0.49
     MEANS
    0.49
    means
    0.48
    Act Density 0.723%

    No Known Activations