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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     for
    0.74
    en
    0.57
     as
    0.52
    Baker
    0.50
    enar
    0.50
     were
    0.50
    ه
    0.49
    at
    0.48
     on
    0.48
    Energy
    0.47
    POSITIVE LOGITS
    öger
    0.52
    崩溃
    0.52
    árs
    0.51
    ရပ်
    0.51
    alış
    0.50
    ielle
    0.50
    kých
    0.50
    öse
    0.50
    üst
    0.49
    borderwidth
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.