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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     té
    -0.07
     رد
    -0.07
     حد
    -0.07
     Bài
    -0.07
     Ones
    -0.07
    source
    -0.07
     generations
    -0.07
    Datum
    -0.07
    预料
    -0.06
     Token
    -0.06
    POSITIVE LOGITS
    automation
    0.07
    잼
    0.07
    ☫
    0.07
     ammunition
    0.07
     Choosing
    0.06
    	work
    0.06
    �
    0.06
    	un
    0.06
    IMPORTANT
    0.06
     kun
    0.06
    Act Density 0.018%

    No Known Activations