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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     stellt
    -0.08
     Obj
    -0.07
    กรม
    -0.07
    -it
    -0.07
    引っ
    -0.07
    🍆
    -0.07
    臃
    -0.07
     хоз
    -0.07
    짚
    -0.06
    _dead
    -0.06
    POSITIVE LOGITS
     delighted
    0.07
    ولوجي
    0.07
    췸
    0.07
     Harold
    0.06
    rado
    0.06
     lavoro
    0.06
     Kenneth
    0.06
    onne
    0.06
    关闭
    0.06
    퀼
    0.06
    Act Density 0.001%

    No Known Activations