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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     for
    0.42
     촉
    0.37
    립니다
    0.36
     forensic
    0.36
     imgSrc
    0.36
    성에
    0.35
     a
    0.35
     colored
    0.35
     Derbyshire
    0.35
     lig
    0.35
    POSITIVE LOGITS
    Withdraw
    0.44
    forbidden
    0.41
    sibling
    0.39
    radiated
    0.39
    assume
    0.39
    accepted
    0.38
    withdrawal
    0.37
    的生活
    0.37
    talking
    0.37
    withdraw
    0.37
    Act Density 0.000%

    No Known Activations