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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     primer
    -0.08
    엨
    -0.07
    ishop
    -0.07
    sale
    -0.07
    擒
    -0.07
    עיתונ
    -0.07
    -valu
    -0.07
     aficion
    -0.06
    under
    -0.06
     isAuthenticated
    -0.06
    POSITIVE LOGITS
    دى
    0.08
    骨骼
    0.08
     כפי
    0.08
    ないように
    0.08
    `}
    0.08
    帐
    0.07
    	Me
    0.07
    ▨
    0.07
     HDD
    0.07
    _RAW
    0.07
    Act Density 0.135%

    No Known Activations