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

    Neuronpedia

    INDEX
    Explanations

    references or citations within legal or academic texts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Hozzáférés
    -0.48
    ,
    -0.47
     the
    -0.47
     I
    -0.45
    QUADS
    -0.44
     including
    -0.43
     (
    -0.43
     referenties
    -0.42
     that
    -0.41
     as
    -0.41
    POSITIVE LOGITS
     للاسماء
    1.05
     Italijanski
    0.89
    aarrggbb
    0.85
     oprot
    0.83
    0.77
     propOrder
    0.77
    RuleContext
    0.74
     ſtate
    0.74
    ThroughAttribute
    0.74
     pleaſure
    0.73
    Act Density 0.003%

    No Known Activations