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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms indicating consequences or outcomes related to rules and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hasattr
    -0.54
    ParallelGroup
    -0.48
    </h3>
    -0.45
     getattr
    -0.43
    läg
    -0.43
    Personendaten
    -0.42
     équ
    -0.41
    oneph
    -0.41
    rierte
    -0.41
    iterran
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    0.79
     BoxDecoration
    0.78
    NameInMap
    0.72
    exitRule
    0.69
    Koordinaten
    0.69
     مرئيه
    0.68
    IsMutable
    0.68
     InputDecoration
    0.66
     rhestr
    0.66
    SpringBootTest
    0.65
    Act Density 0.097%

    No Known Activations