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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     every
    0.86
     κάθε
    0.83
     בכל
    0.82
     모든
    0.79
     atoms
    0.77
     versions
    0.76
     true
    0.76
     எல்லா
    0.74
    所有的
    0.73
     প্রতিটি
    0.73
    POSITIVE LOGITS
    lunch
    0.97
    晚餐
    0.93
     continuamos
    0.91
     दोपहर
    0.89
     journée
    0.86
    Lunch
    0.86
     lunch
    0.83
    Restaurant
    0.82
    Hotel
    0.80
    Optional
    0.79
    Act Density 0.276%

    No Known Activations