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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    om
    0.74
    elf
    0.70
    room
    0.68
    elves
    0.68
    otypes
    0.67
    一组
    0.67
    נ
    0.67
    ку
    0.67
    一只
    0.65
    nave
    0.65
    POSITIVE LOGITS
     estuvieron
    0.78
     vVertex
    0.78
     entitles
    0.77
     обязанности
    0.76
     alteraciones
    0.75
    ૂ
    0.75
     приобре
    0.75
    ఋ
    0.75
     ovvero
    0.74
     asesin
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.