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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or describe something as a "so-called" concept or term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the "so-called" construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suel
    -0.39
     Constitucional
    -0.32
     przewod
    -0.30
     gré
    -0.30
    GEBURTSDATUM
    -0.29
     hydrauli
    -0.28
     distribuidor
    -0.28
     précédente
    -0.28
     Komunikasi
    -0.28
     frère
    -0.27
    POSITIVE LOGITS
     tzw
    0.81
    AndEndTag
    0.76
     sogen
    0.75
     sogenannte
    0.74
    ConstraintMaker
    0.68
     AssemblyCulture
    0.67
     sogenannten
    0.67
     Called
    0.65
     called
    0.65
    called
    0.64
    Act Density 0.064%

    No Known Activations