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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    at
    0.68
    im
    0.63
    con
    0.55
    ing
    0.55
    h
    0.55
    n
    0.53
    up
    0.52
    disc
    0.52
    dis
    0.51
    hill
    0.51
    POSITIVE LOGITS
    ंगर
    0.50
     Robles
    0.45
    INUS
    0.44
     Ambul
    0.44
     pedro
    0.44
    比如說
    0.44
    ંદર
    0.43
    ά
    0.42
    繳
    0.42
     waż
    0.42
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.