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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    肥胖
    -0.07
    ASET
    -0.07
    /tools
    -0.06
    营销
    -0.06
    דירות
    -0.06
    מופע
    -0.06
    城市
    -0.06
    济南
    -0.06
    ลบ
    -0.06
    vault
    -0.06
    POSITIVE LOGITS
     peach
    0.07
     Ire
    0.07
    IDI
    0.07
    \v
    0.07
    _BIND
    0.07
     leveled
    0.06
     wi
    0.06
    🐇
    0.06
    (ir
    0.06
    ':↵
    0.06
    Act Density 0.071%

    No Known Activations