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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sucked
    -0.08
    קרה
    -0.07
    .Username
    -0.07
     Cần
    -0.07
     aşağı
    -0.07
    滗
    -0.07
     tornado
    -0.07
    ᕼ
    -0.06
    explode
    -0.06
    ้ำ
    -0.06
    POSITIVE LOGITS
    ,
    0.08
     VP
    0.07
     Prof
    0.07
     vo
    0.07
     faculty
    0.07
    Prof
    0.07
     PTSD
    0.07
     proficiency
    0.07
    褐
    0.07
    爵
    0.07
    Act Density 0.045%

    No Known Activations