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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     stroll
    0.67
     hallways
    0.66
     walks
    0.64
     ahead
    0.63
     elevates
    0.62
     sits
    0.61
     alleys
    0.61
     of
    0.61
     walked
    0.60
     days
    0.60
    POSITIVE LOGITS
    Original
    0.71
    无
    0.70
    Chocolate
    0.69
    INDOW
    0.67
    ディズニー
    0.67
    Angry
    0.66
    Фи
    0.66
    Фа
    0.66
    Fireworks
    0.66
    CLUSTER
    0.65
    Act Density 0.000%

    No Known Activations