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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific conditional statements or indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Defensa
    -0.52
     Sociales
    -0.50
     inalámbrica
    -0.48
     Garantía
    -0.48
     Preguntas
    -0.46
    enquête
    -0.45
     Española
    -0.45
     kaupung
    -0.44
     deportivo
    -0.44
     Mitarbeit
    -0.44
    POSITIVE LOGITS
     IS
    1.38
     WAS
    1.20
     ARE
    1.20
     HAS
    1.14
     CAN
    0.94
     HAVE
    0.91
     DID
    0.88
     WERE
    0.87
     HAD
    0.84
     WOULD
    0.83
    Act Density 0.375%

    No Known Activations