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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     screech
    0.58
     racer
    0.56
     disagreeable
    0.56
    vine
    0.54
     comical
    0.54
     chutney
    0.54
     intrat
    0.53
     paparazzi
    0.53
     cabaret
    0.52
     prevalent
    0.52
    POSITIVE LOGITS
    ER
    0.60
    F
    0.60
    E
    0.59
    RE
    0.55
    Warning
    0.54
    EL
    0.54
    参数
    0.54
    ا
    0.53
    ON
    0.53
    Gen
    0.53
    Act Density 0.000%

    No Known Activations