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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     symbolized
    0.71
    aryn
    0.68
     comprehend
    0.67
     expresó
    0.67
     representa
    0.66
     accomplishes
    0.66
    분을
    0.65
     symbolizes
    0.65
    Represent
    0.65
     vowed
    0.64
    POSITIVE LOGITS
    支持
    2.06
     supports
    1.99
     support
    1.97
     SUPPORT
    1.97
     Supports
    1.96
     suggest
    1.92
    Supports
    1.89
     Support
    1.88
    不支持
    1.87
     supporting
    1.87
    Act Density 0.279%

    No Known Activations