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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Paul
    -0.06
     cre
    -0.06
    Loading
    -0.06
    MATRIX
    -0.06
    elsius
    -0.06
    ndata
    -0.06
     خام
    -0.06
    erta
    -0.06
     organs
    -0.06
    iro
    -0.06
    POSITIVE LOGITS
    aint
    0.06
    -proof
    0.06
     —↵
    0.06
     وز
    0.06
    dess
    0.06
    딩
    0.06
    .’
    0.06
     Lad
    0.06
     heights
    0.06
     소리
    0.06
    Act Density 0.001%

    No Known Activations