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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    핑크
    0.49
    尃
    0.49
     Vegan
    0.48
     pesar
    0.46
    χ
    0.46
    甴
    0.46
     Há
    0.45
    潵
    0.45
    各種
    0.44
     पड़ा
    0.44
    POSITIVE LOGITS
    house
    0.50
     pantry
    0.46
    dynam
    0.42
    u
    0.42
    一台
    0.42
    ilir
    0.42
    dry
    0.42
    work
    0.40
    inte
    0.40
     brisket
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.