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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     eateries
    0.86
     wholeheartedly
    0.85
     rehearsals
    0.79
     ciudadanía
    0.79
     billionaires
    0.78
     chromosphere
    0.77
     urma
    0.76
     boyhood
    0.76
     cały
    0.76
     classrooms
    0.75
    POSITIVE LOGITS
    ن
    0.77
     Role
    0.73
    adding
    0.71
    Ao
    0.71
    Altri
    0.70
    いた
    0.70
    Ai
    0.70
    دور
    0.70
    it
    0.69
     App
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.