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

    Neuronpedia

    INDEX
    Explanations

    references to various types of weapons, particularly swords and knives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.69
     الرياضيه
    -0.69
     drey
    -0.68
    GEBURTSDATUM
    -0.61
     незавершена
    -0.60
     peanuts
    -0.59
     Roskov
    -0.59
    ρίες
    -0.58
    webElementXpaths
    -0.58
     ballast
    -0.57
    POSITIVE LOGITS
     knife
    1.14
     knives
    1.09
     sword
    1.09
     blade
    1.00
     swords
    0.99
     blades
    0.99
     Sword
    0.98
    Knife
    0.98
     Knife
    0.93
     cuchillo
    0.92
    Act Density 0.145%

    No Known Activations