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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities and their significance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexContent
    -0.80
    Autoritní
    -0.75
    Filmografie
    -0.72
    XmlType
    -0.66
     defaultstate
    -0.61
    Idea
    -0.60
    IsContent
    -0.58
    солю
    -0.58
     surla
    -0.57
    philo
    -0.57
    POSITIVE LOGITS
    vábbi
    0.65
     whopping
    0.61
     таки
    0.57
     
    0.56
    venty
    0.55
    ！）
    0.54
     eight
    0.54
    tableFuture
    0.54
    thirty
    0.53
     six
    0.52
    Act Density 0.149%

    No Known Activations