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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     voiture
    -0.08
     huis
    -0.07
    青铜
    -0.07
     peril
    -0.07
     automobile
    -0.07
    qi
    -0.07
    departure
    -0.07
    /home
    -0.07
    _/
    -0.07
    July
    -0.07
    POSITIVE LOGITS
    ++);↵
    0.08
    _Enable
    0.07
    indr
    0.07
    唤醒
    0.07
    �
    0.07
    egers
    0.07
    חשבו
    0.07
    Sense
    0.06
     RNG
    0.06
     Cursors
    0.06
    Act Density 0.117%

    No Known Activations