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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     conting
    -0.07
    短信
    -0.07
    ignore
    -0.07
    _NATIVE
    -0.07
    🎩
    -0.07
     pale
    -0.07
     pint
    -0.07
     الوز
    -0.07
     Scottish
    -0.07
    XL
    -0.06
    POSITIVE LOGITS
    (callback
    0.07
     resumed
    0.07
    '(
    0.07
    を使った
    0.07
    '})
    0.07
    二楼
    0.07
     thù
    0.06
    	Class
    0.06
    上が
    0.06
     lockdown
    0.06
    Act Density 0.020%

    No Known Activations