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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pretext
    0.82
    ки
    0.81
    0.79
     chances
    0.79
     cenas
    0.79
    差别
    0.77
     coincidence
    0.76
     coincident
    0.76
     машиналары
    0.74
    引
    0.73
    POSITIVE LOGITS
    )",
    0.85
    urul
    0.83
    ichting
    0.81
    ared
    0.81
    orne
    0.78
    inescent
    0.78
    \'
    0.77
    )}_{
    0.75
    ,/
    0.74
    础
    0.73
    Act Density 0.000%

    No Known Activations