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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ya
    1.21
     hazard
    1.15
    私は
    1.14
    牧
    1.13
     conda
    1.06
     Бы
    1.05
     dendritic
    1.01
    šanu
    1.00
     tortured
    0.99
     pus
    0.99
    POSITIVE LOGITS
    ת
    1.31
    ो
    1.29
    র
    1.20
    י
    1.18
    𝐂
    1.15
    Prosecutors
    1.13
    ి
    1.13
    이
    1.13
     की
    1.11
    하고
    1.09
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.