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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     none
    0.57
     continue
    0.53
     other
    0.50
     including
    0.50
    ද්ග
    0.48
    ુ
    0.47
     that
    0.47
     styling
    0.47
     be
    0.47
     any
    0.47
    POSITIVE LOGITS
    Course
    0.50
    侵害
    0.47
     ライト
    0.47
    ALING
    0.45
     مضر
    0.44
     电
    0.44
    }-
    0.43
    }:
    0.43
     الج
    0.43
    MANAGER
    0.42
    Act Density 0.000%

    No Known Activations