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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mixt
    -0.47
    pakt
    -0.44
    Opti
    -0.44
    tives
    -0.43
    xPos
    -0.43
    asti
    -0.43
    Protos
    -0.43
    vivi
    -0.43
     divi
    -0.43
     Dwayne
    -0.42
    POSITIVE LOGITS
     her
    1.43
    her
    1.06
     그녀
    1.03
    她的
    1.02
    Her
    1.01
     Her
    0.94
     její
    0.94
    彼女の
    0.92
     её
    0.89
     haar
    0.88
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.