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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     incongru
    1.23
     полага
    1.09
    starred
    1.08
    禎
    1.07
    你看
    1.06
    TimeSeries
    1.05
     baryons
    1.03
    បាន
    1.02
     Decorated
    1.01
     exaggerate
    1.00
    POSITIVE LOGITS
    i
    1.50
    ുന്ന
    1.34
    ed
    1.23
    iq
    1.16
     الجزء
    1.14
    خدم
    1.14
    duh
    1.13
    gis
    1.13
    fo
    1.11
    ké
    1.10
    Act Density 0.000%

    No Known Activations