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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oké
    -0.85
    iste
    -0.76
    tein
    -0.72
    paio
    -0.69
    illi
    -0.67
    iland
    -0.67
     sle
    -0.66
    igor
    -0.66
     gard
    -0.66
    ayn
    -0.66
    POSITIVE LOGITS
    ALK
    0.79
    VP
    0.78
    KN
    0.73
    ""
    0.71
    LER
    0.70
    969
    0.70
    TRY
    0.70
    ARGET
    0.67
    -+-+-+-+
    0.67
    ���
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.