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

    Neuronpedia

    INDEX
    Explanations

    the presence of the token 'x' in various contexts, indicating a focus on numerical or data-related features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     viņ
    -0.31
    ’
    -0.31
     quedado
    -0.30
     recibido
    -0.29
     die
    -0.28
     høy
    -0.28
    NSMutable
    -0.28
     pł
    -0.27
     köl
    -0.26
     publicidad
    -0.26
    POSITIVE LOGITS
     kasarigan
    0.95
     autorytatywna
    0.94
     disambiguazione
    0.90
    rungsseite
    0.89
    ValueStyle
    0.88
    RegressionTest
    0.87
    GEBURTSDATUM
    0.86
    ViewFeatures
    0.85
    0.84
    ThroughAttribute
    0.83
    Act Density 0.104%

    No Known Activations