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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate exclusivity or limitations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     either
    -0.60
     RoutedEventArgs
    -0.59
    setdefault
    -0.59
    uticos
    -0.58
    Datuak
    -0.56
    ymce
    -0.54
    fontein
    -0.54
    adora
    -0.53
     s
    -0.53
     архивлан
    -0.53
    POSITIVE LOGITS
     itſelf
    0.71
     myſelf
    0.70
     animés
    0.67
     himſelf
    0.64
     blanches
    0.63
     moschino
    0.63
     själva
    0.61
     بلکه
    0.61
     termica
    0.60
     iſt
    0.59
    Act Density 0.240%

    No Known Activations