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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    predicted
    0.48
     Kaya
    0.48
    running
    0.47
    🐏
    0.46
     spoiled
    0.46
     Schnitt
    0.46
     ejecución
    0.46
    輥
    0.46
     execution
    0.45
     وړاندوینه
    0.45
    POSITIVE LOGITS
    akos
    0.46
    Once
    0.40
    obiles
    0.40
    eward
    0.40
    herr
    0.40
    abri
    0.40
    aginaw
    0.40
    avil
    0.39
     Anywhere
    0.39
    积
    0.39
    Act Density 0.002%

    No Known Activations