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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    acters
    -0.08
    女主
    -0.07
     digit
    -0.07
    [".
    -0.07
    Loan
    -0.07
    積
    -0.07
     nan
    -0.06
    -vis
    -0.06
    _ticket
    -0.06
     שאתה
    -0.06
    POSITIVE LOGITS
     weighting
    0.07
     refin
    0.07
    𫘜
    0.07
    �
    0.06
     Shades
    0.06
     Barnett
    0.06
    秬
    0.06
    薏
    0.06
     hải
    0.06
    媱
    0.06
    Act Density 0.018%

    No Known Activations