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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     (
    1.16
    ем
    0.93
     are
    0.91
    ,
    0.90
    ки
    0.89
     ít
    0.84
    你说
    0.84
     aliment
    0.82
    త
    0.81
     averse
    0.80
    POSITIVE LOGITS
    F
    1.70
    J
    1.57
    K
    1.55
    M
    1.49
    T
    1.48
    V
    1.46
    O
    1.42
    B
    1.41
    AT
    1.40
    W
    1.40
    Act Density 0.000%

    No Known Activations