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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ot
    0.79
    ined
    0.73
    ip
    0.70
     $
    0.69
    ap
    0.69
    0.66
    ian
    0.65
    т
    0.65
    ia
    0.64
    y
    0.64
    POSITIVE LOGITS
     perasaan
    1.02
     appelez
    0.96
    汰
    0.91
     adhé
    0.90
     ondas
    0.89
     khawatir
    0.88
     powerAll
    0.86
    的感觉
    0.86
     ribu
    0.84
     verrez
    0.84
    Act Density 0.001%

    No Known Activations