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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ли
    0.96
    та
    0.86
    к
    0.83
    я
    0.81
    า
    0.80
    ;
    0.80
    ة
    0.76
    ை
    0.75
    tipo
    0.75
    ;";
    0.74
    POSITIVE LOGITS
    at
    1.13
    ت
    0.96
    it
    0.88
    on
    0.86
    in
    0.83
    as
    0.82
    고
    0.82
    oer
    0.78
    It
    0.77
    ah
    0.73
    Act Density 0.000%

    No Known Activations