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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     —
    0.47
    Families
    0.44
    (
    0.44
    -
    0.43
     trois
    0.43
     ήταν
    0.43
     tři
    0.43
    logne
    0.42
    —
    0.41
    Coordinates
    0.41
    POSITIVE LOGITS
     వైద్య
    0.47
    ordat
    0.44
    㤓
    0.43
     naturalmente
    0.43
    olome
    0.42
    umbered
    0.42
    orice
    0.40
    atenated
    0.40
     Naturally
    0.40
    混合
    0.40
    Act Density 0.006%

    No Known Activations