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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.48
    /
    0.41
     *
    0.41
     \
    0.38
     א
    0.37
    (?)
    0.37
    -
    0.36
    }\\
    0.35
     &
    0.35
     (
    0.35
    POSITIVE LOGITS
     trzy
    0.39
     quatrième
    0.38
    पीड़न
    0.38
     magasins
    0.38
     businessmen
    0.37
     regering
    0.36
     psychotherapy
    0.36
     czter
    0.36
     ogrom
    0.35
     socialista
    0.35
    Act Density 0.000%

    No Known Activations