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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     which
    1.16
     and
    1.13
    和
    0.95
    和你
    0.95
    사와
    0.93
     Esquire
    0.93
     आणि
    0.92
     your
    0.92
    Ма
    0.89
     jail
    0.89
    POSITIVE LOGITS
    ี
    0.94
    ↵↵
    0.93
     też
    0.87
    obnie
    0.87
     myös
    0.86
    </h6>
    0.84
    </h5>
    0.83
    ู
    0.82
    </h4>
    0.79
    iniai
    0.79
    Act Density 3.386%

    No Known Activations