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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     strutt
    0.42
    🥂
    0.39
    Accessed
    0.38
    seriously
    0.38
     luxuri
    0.38
    を入
    0.37
     sucked
    0.37
    marshalO
    0.37
     গুলি
    0.37
    mf
    0.36
    POSITIVE LOGITS
     incidents
    0.44
     individual
    0.42
     hepatitis
    0.42
     घटनाएं
    0.41
    莠
    0.40
     unconditional
    0.40
     Individual
    0.39
     tình
    0.39
     事件
    0.39
     Hepatitis
    0.38
    Act Density 0.002%

    No Known Activations