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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     masuk
    0.48
     allocate
    0.45
     distribusi
    0.44
    Finish
    0.44
     Αγ
    0.43
    abag
    0.42
    𝘞
    0.42
    DebugType
    0.41
    ują
    0.41
    oryt
    0.41
    POSITIVE LOGITS
     対
    0.53
     Legion
    0.52
     Korn
    0.51
    cings
    0.49
     жизнью
    0.48
     Harvard
    0.48
     Beaux
    0.48
     Confucian
    0.48
     Lawyer
    0.48
     Cornerstone
    0.48
    Act Density 0.000%

    No Known Activations