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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    致命
    -0.08
    %"↵
    -0.07
     bunk
    -0.07
     ///<
    -0.07
    .putText
    -0.07
    ’d
    -0.07
    😛
    -0.07
    这家
    -0.07
    ultipart
    -0.07
     """
↵
↵
    -0.07
    POSITIVE LOGITS
    徨
    0.07
     uncomp
    0.07
    woo
    0.07
     McKin
    0.07
    .Master
    0.07
    夸大
    0.07
     energies
    0.07
    جائ
    0.06
    즑
    0.06
     weapons
    0.06
    Act Density 0.001%

    No Known Activations