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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     JK
    -0.08
     saber
    -0.07
    .Up
    -0.07
    מיכה
    -0.07
    自从
    -0.07
     mos
    -0.07
     Tết
    -0.07
    Detection
    -0.07
     rotated
    -0.07
     misog
    -0.07
    POSITIVE LOGITS
    ่ม
    0.08
    пром
    0.07
    adle
    0.07
    ACTER
    0.07
    水晶
    0.07
     attribute
    0.07
    'u
    0.07
    关联
    0.07
    」
    0.07
    habit
    0.07
    Act Density 0.028%

    No Known Activations