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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pal
    -0.07
     Pal
    -0.07
    当作
    -0.07
    🅛
    -0.07
     Himal
    -0.06
     arasındaki
    -0.06
     hữu
    -0.06
    .There
    -0.06
    .flink
    -0.06
     Locker
    -0.06
    POSITIVE LOGITS
     Encoder
    0.07
    难道
    0.07
    後
    0.07
    Encoder
    0.06
    (set
    0.06
     أعلن
    0.06
    _choices
    0.06
     delet
    0.06
     Seen
    0.06
     postgres
    0.06
    Act Density 0.028%

    No Known Activations