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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    "c
    -0.08
    𓏧
    -0.07
    骘
    -0.07
     Nur
    -0.07
    敢
    -0.07
     Integral
    -0.07
     xmax
    -0.06
    CORE
    -0.06
    chos
    -0.06
    	yy
    -0.06
    POSITIVE LOGITS
    (Note
    0.07
    (tweet
    0.07
    通讯员
    0.07
    あまり
    0.07
    ----------------------------
    0.07
    lj
    0.07
     같이
    0.07
    所谓
    0.07
    .Qual
    0.06
    完美的
    0.06
    Act Density 0.001%

    No Known Activations