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

    Neuronpedia

    INDEX
    Explanations

    variations of the prefix "dis," indicating negation or removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chriftian
    -0.70
    IBOutlet
    -0.68
     ſche
    -0.66
     Majefty
    -0.65
    OPLE
    -0.64
     perſon
    -0.64
    سف
    -0.61
     Gött
    -0.60
     ſch
    -0.60
     daer
    -0.59
    POSITIVE LOGITS
     dis
    2.80
     desar
    0.96
     Dis
    0.96
     disarm
    0.94
    Dis
    0.87
     Dish
    0.85
     DIS
    0.84
     DISH
    0.84
     dish
    0.83
    dis
    0.82
    Act Density 0.085%

    No Known Activations