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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ي
    0.81
    я
    0.81
    يها
    0.79
     favoriser
    0.74
    tas
    0.74
    י
    0.74
    as
    0.73
    tipo
    0.72
     Zusätzlich
    0.72
    tion
    0.71
    POSITIVE LOGITS
    |\
    0.78
    actively
    0.76
    ද්ධ
    0.75
    )+\
    0.74
    cling
    0.74
    }_{+}\
    0.72
    फ्ट
    0.72
     devastated
    0.72
    chs
    0.71
    lego
    0.71
    Act Density 0.017%

    No Known Activations