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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sail
    0.89
     darn
    0.88
     dozen
    0.86
     tempi
    0.85
    𝘬
    0.85
     interstellar
    0.85
     gols
    0.84
     із
    0.83
     час
    0.82
     отказаться
    0.82
    POSITIVE LOGITS
    lak
    1.01
    屿
    0.98
    უნქ
    0.97
    աց
    0.96
    lact
    0.96
     мира
    0.94
    forEach
    0.90
     něk
    0.88
    uiDesigner
    0.86
     plenum
    0.85
    Act Density 0.069%

    No Known Activations