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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    /trans
    -0.08
    �
    -0.07
    _SIDE
    -0.07
    .swap
    -0.07
    icode
    -0.07
    _SANITIZE
    -0.06
     nervous
    -0.06
     Kick
    -0.06
     remar
    -0.06
    .blue
    -0.06
    POSITIVE LOGITS
    World
    0.08
    	person
    0.07
    뵈
    0.07
    莫斯
    0.07
    銷售
    0.07
     Mỹ
    0.07
     Yourself
    0.07
     Markets
    0.07
     gods
    0.07
     jamais
    0.06
    Act Density 0.008%

    No Known Activations