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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    xFA
    -0.07
    ꪱ
    -0.07
     cough
    -0.07
    首付
    -0.07
    郑州
    -0.07
    郤
    -0.07
    民心
    -0.06
    谳
    -0.06
    .Inst
    -0.06
     להי
    -0.06
    POSITIVE LOGITS
    (completion
    0.07
    🔁
    0.07
    scriber
    0.07
    ler
    0.07
    division
    0.07
    .locations
    0.07
    series
    0.06
     Shen
    0.06
    锵
    0.06
    ゜
    0.06
    Act Density 0.001%

    No Known Activations