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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     defend
    -0.07
     @{
    -0.07
    🛤
    -0.07
     promo
    -0.07
     Мари
    -0.07
     extend
    -0.07
    _dual
    -0.07
     summon
    -0.06
    wordpress
    -0.06
     אמנ
    -0.06
    POSITIVE LOGITS
    貌
    0.08
    scopy
    0.08
    𝗔
    0.07
    复查
    0.07
    せ
    0.07
    젹
    0.07
     coaches
    0.07
    ASS
    0.06
    >'+
    0.06
    رض
    0.06
    Act Density 0.121%

    No Known Activations