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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    2
    -0.09
    3
    -0.08
     detecting
    -0.07
    垃圾分类
    -0.07
     loop
    -0.07
    레
    -0.07
    ctic
    -0.07
    _
    -0.07
    .Hex
    -0.07
     diving
    -0.07
    POSITIVE LOGITS
     chairman
    0.09
    abilidad
    0.08
     Chairman
    0.07
     האמר
    0.07
    _CHAT
    0.07
    �
    0.07
     обесп
    0.07
    瞎
    0.07
     thuận
    0.07
    пал
    0.07
    Act Density 0.009%

    No Known Activations