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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    掊
    0.84
     drawbacks
    0.78
     shrubs
    0.77
    其实
    0.76
     fabricant
    0.75
     importanti
    0.75
    𝘽
    0.74
     drawback
    0.74
     sawmill
    0.73
    厂家
    0.73
    POSITIVE LOGITS
    ring
    0.75
     During
    0.68
    u
    0.68
    During
    0.67
    rey
    0.67
    range
    0.65
    0
    0.63
    2
    0.62
     during
    0.61
    regated
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.