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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    V
    0.51
    Martin
    0.48
    AS
    0.47
    s
    0.47
    L
    0.46
    Okay
    0.46
    window
    0.45
    LOS
    0.43
    Ste
    0.43
    AN
    0.42
    POSITIVE LOGITS
     LongNumber
    0.58
    |^{-
    0.55
    ,~
    0.50
    awcy
    0.49
    )~
    0.49
     UIFont
    0.47
     있도록
    0.47
     aqueles
    0.47
     یو
    0.46
    jno
    0.46
    Act Density 0.004%

    No Known Activations