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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    爆炸
    -0.08
     dolphins
    -0.07
     hijos
    -0.07
    不惜
    -0.06
     cumpl
    -0.06
    走出
    -0.06
     remains
    -0.06
    _TIMESTAMP
    -0.06
    piar
    -0.06
     estoy
    -0.06
    POSITIVE LOGITS
    NECT
    0.07
    -R
    0.07
     theoret
    0.07
    DEVICE
    0.07
    Tabla
    0.07
    ernet
    0.07
     LINE
    0.07
    拉斯
    0.07
    REET
    0.07
    树木
    0.06
    Act Density 0.003%

    No Known Activations